Technology for heart rate detection

Abstract

Methods, systems, and devices for heart rate detection are described. The method includes receiving physiological data associated with a user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user. The method includes determining a state quality metric associated with the time interval based on the received motion data and temperature data. The state quality metric indicates a relative quality of the physiological data collected over the time interval for determining a heart rate measurement. The method includes sampling photoplethysmogram (PPG) data of the user by the wearable device based on the state quality metric satisfying a threshold metric value and the timer satisfying a first threshold duration. The method includes determining a heart rate measurement of the user based at least in part on the sampled PPG data.

Description

[Technical Field]

[0001] The following relates to wearable devices and data processing, including techniques for heart rate detection. [Background technology]

[0002] Some wearable devices may be configured to collect data from a user related to the user's heart rate, such as motion data, temperature data, photoplethysmogram (PPG) data, etc. In some cases, some wearable devices may be configured to detect one or more sets of data under preset conditions. Conventional techniques for detecting data according to preset conditions may be improved. [Brief explanation of the drawings]

[0003] [Figure 1] 1 illustrates an example of a system that supports techniques for heartbeat detection according to aspects of the present disclosure. [Figure 2] 1 illustrates an example of a system that supports techniques for heartbeat detection according to aspects of the present disclosure. [Figure 3] 1 illustrates an example of a heartbeat determination procedure supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 4] 1 illustrates an example of a heartbeat determination procedure supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 5] 1 illustrates an example of a channel selection procedure supporting techniques for heartbeat detection according to an aspect of the present disclosure. [Figure 6] 1 illustrates an example of a channel selection procedure supporting techniques for heartbeat detection according to an aspect of the present disclosure. [Figure 7] 1 illustrates an example of a channel selection procedure supporting techniques for heartbeat detection according to an aspect of the present disclosure. [Figure 8] 1 illustrates an example of a heartbeat determination procedure supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 9]1 illustrates an example of a graphical user interface (GUI) supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 10] 1 illustrates a block diagram of a device supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 11] FIG. 1 illustrates a block diagram of a wearable application supporting techniques for heart rate detection according to aspects of the present disclosure. [Figure 12] 1 shows a diagram of a system including devices supporting techniques for heartbeat detection according to aspects of the present disclosure. [Figure 13] 1 shows a flowchart illustrating a method for supporting techniques for heartbeat detection according to an aspect of the present disclosure. [Figure 14] 1 shows a flowchart illustrating a method for supporting techniques for heartbeat detection according to an aspect of the present disclosure. [Figure 15] 1 shows a flowchart illustrating a method for supporting techniques for heartbeat detection according to an aspect of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0004] A user may use a device (e.g., a wearable device) to determine the user's physiological measurements, such as heart rate. Resting heart rate (RHR) may refer to the number of heartbeats per minute of a user during periods of "rest," such as periods when the user is abstaining from activity, such as while sleeping, meditating, or otherwise relaxing. RHR may be used to determine sleep quality, recovery, stress response, activity level, and the user's overall health. To measure a user's heart rate, such as RHR, a wearable device may use a photoplethysmogram (PPG) to measure the user's heart rate over time. For example, a wearable device may measure the user's RHR by detecting changes in pulse rate with a PPG sensor (e.g., an infrared (IR) PPG sensor, an infrared light-emitting diode (LED)) within the wearable device. Each time a user's heart beats, blood is pumped through the arteries in the user's hands and fingers. PPG sensors can detect changes in blood flow (e.g., arterial flow, venous flow) and volume using light reflection and absorption. With each heartbeat, the arteries in a user's fingers expand and contract. By shining light onto the user's skin, particularly the skin of the finger, changes in light absorbed by the blood and reflected from the varying volume of red blood cells in the arteries are taken into account. From here, PPG can represent these changes in blood flow through a visual waveform that represents the user's cardiac activity (e.g., heartbeat).

[0005] In some cases, wearable devices may determine a user's heart rate variability (HRV). HRV is a measure of the change in time (e.g., milliseconds) between heartbeats and can be used as an indicator of how well a user's body balances the two branches of the autonomic nervous system—the sympathetic and parasympathetic nervous systems—and thus can indicate the user's current ability to manage stress, provide indications of the user's illness or fatigue, and so on. Wearable devices may calculate HRV using the root mean square of successive differences (rMSSD) between heartbeats. rMSSD can be obtained by first calculating each successive time difference between heartbeats in milliseconds. Each value is then squared, the results are averaged, and the square root of the sum is taken. rMSSD is used as a measure of HRV because it reflects the beat-to-beat variance of HR.

[0006] Heart rate (e.g., RHR) and HRV are sensitive metrics that can change based on activities performed by a user (e.g., drinking a glass of water, standing up, watching TV). Certain activities can cause heart rate, HRV, or both to spike up or down; such fluctuations are sometimes referred to as noise in the data. During periods of rest when a user is abstaining from activity, particularly during sleep, the body is in a stable state (e.g., the most stable state over a 24-hour period), resulting in reduced fluctuations associated with heart rate and HRV. Therefore, some wearable devices may measure a user's heart (e.g., RHR), HRV, or both during rest periods (e.g., periods when noise is reduced) to determine accurate heart rate and HRV data. However, determining heart rate measurements only during rest periods can significantly reduce the number of heart rate measurements that can be collected for a user over any given period of time. As a result, some conventional wearable devices cannot efficiently track a user's heart rate throughout the day and may provide only a limited indication of the user's heart rate and, therefore, the user's overall health.

[0007] The technology described herein is directed to wearable devices configured with the ability to measure heart rate data regardless of whether the user is resting (e.g., when the user is awake, active, or resting). Thus, the wearable device may determine a user's heart rate data during periods of activity, rest, or a combination thereof to provide a more complete representation of the user's heart rate, HRV, or both over time. The wearable devices described herein may be configured with procedures for measuring heart data (e.g., while the user is active, while the user is not resting, while the user is not sleeping, during the day) while reducing noise in the data.

[0008] A procedure for determining heart rate data (e.g., non-sleep data, daytime data, or a combination of daytime and nighttime data) may include the wearable device measuring physiological data associated with the user, such as temperature and movement data. In some cases, to reduce the power consumption of the wearable device, the wearable device may use the physiological data to detect moments to measure PPG. For example, rather than constantly measuring PPG, the wearable device may use the user's physiological data to detect moments that may result in PPG data that meet a quality threshold. Upon detecting moments to measure PPG data, the wearable device may measure PPG for a certain duration and measure the signal quality of the PPG. If the PPG signal quality meets the threshold quality, the wearable device may estimate the user's heart rate based on the PPG data. Thus, the procedure described herein may be configured to determine accurate heart rate data while conserving the power of the wearable device.

[0009] For example, a method may include receiving physiological data associated with the user, where the physiological data may include motion data and temperature data collected over a time interval by a wearable device associated with the user. The method may include determining a condition quality metric associated with the time interval based on the received motion data and temperature data. The condition quality metric may indicate a relative quality of the physiological data collected over the time interval for determining a heart rate measurement. The method may include sampling photoplethysmogram (PPG) data of the user by the wearable device based on the condition quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration. The method may include determining the user's heart rate measurement based on the sampled PPG data.

[0010] In some implementations, the procedure for determining heart rate may include selecting one or more “channels” (e.g., PPG sensors) for sampling PPG data. For example, a wearable device may be configured with multiple PPG sensors, which may include emitters (e.g., LEDs), receivers (e.g., photodetectors), or both, with a pair of PPG sensors including at least one emitter and at least one receiver comprising an optical path (e.g., channel) used for PPT measurements. In some cases, a PPG sensor may refer to one or more green LEDs, one or more red LEDs, one or more IR LEDs, or any other set of LEDs. In some aspects, some PPG sensors may exhibit better signal quality in some environments compared to other sensors. For example, a green LED may provide the highest quality heart rate measurement in many environments, while an IR diode may provide better quality in other environments, such as during vigorous movement or low skin temperature. In this regard, some aspects of the present disclosure are directed to techniques that enable a wearable device to "test" which PPG sensor / channel exhibits the best signal quality and, therefore, select a different PPG sensor / channel to be used for heart rate measurement.

[0011] In this regard, the wearable device may be configured to select one or more PPG sensors for acquiring PPG data based on signal quality associated with one or more selected sensors and / or signal quality associated with other PPG sensors (non-selected PPG sensors). In some cases, the wearable device may be configured to analyze a set of one or more PPG sensors (e.g., some or all of the PPG sensors configured for the wearable device). For example, the wearable device may determine (e.g., measure, calculate) the quality of the output from each PPG sensor. In some cases, the wearable device may be configured to compare the signal quality of each PPG sensor to one or more signal quality thresholds and / or compare the signal quality of each PPG sensor to other determined signal qualities. For example, the wearable device may select the PPG sensor associated with the highest signal quality and / or select one or more PPG sensors that satisfy one or more signal quality thresholds. For example, in some cases, the wearable device may measure signals from each green LED and each IR channel, compare the signal qualities, and select whether heart rate measurement is performed using the green LED or the IR diode.

[0012] In some cases, the wearable device may be configured with a default PPG sensor (e.g., a particular PPG sensor) or default PPG sensor type (e.g., one or more IR LEDs, green LEDs, etc.) to use to sample PPG data. The wearable device may determine whether the default PPG sensor satisfies a signal quality threshold. If the default PPG sensor satisfies the threshold, the wearable device may sample the PPG sensor using the default PPG sensor. However, if the default PPG sensor fails to meet the threshold, the wearable device may switch to and / or analyze a second set of one or more PPG sensors. For example, if the default PPG sensor does not meet the threshold, the wearable device may be configured to sample PPG data using the second set of one or more PPG sensors. In another example, if the default PPG sensor does not meet the threshold, the wearable device may be configured to determine whether the second set of one or more PPG sensors meets a signal quality threshold. Thus, the wearable device may select one or more PPG sensors to sample the PPG data to improve the PPG data based on signal quality.

[0013] In some cases, the signal quality criteria used to select a PPG sensor may be based on a use case. The signal quality criteria may be based on one or more parameters, including a user illness (e.g., pneumonia), a user disease (e.g., apnea, atrial fibrillation (AFib)), a current workout, a previous workout, or a planned future workout. For example, one or more of the parameters may relate to different types of signals, signal shapes, etc., and thus the signal quality criteria may vary based on the one or more parameters. Thus, the device may identify one or more parameters (e.g., use cases) to apply and determine the signal quality criteria, if any, to use to select one or more PPG sensors.

[0014] In some implementations, the procedure for determining the heart rate may include outputting heart rate data based on comparing the heart rate data to heart rate criteria (e.g., one or more thresholds) to improve the heart rate data provided to the user. If the heart rate data satisfies the heart rate criteria, the device may output the heart rate data to the user. If the heart rate data fails to satisfy the heart rate criteria, the device may stop outputting the heart rate data. In such cases, "gaps" in the heart rate data may occur even if the data is accurate and reliable.

[0015] To reduce the occurrence of gaps in the output heart rate data, the wearable device may be configured with multiple sets of criteria (e.g., multiple thresholds), with later criteria being more relaxed than earlier criteria within the multiple sets. For example, a first set of criteria may be associated with the most stringent criteria, a second set of criteria less stringent than the first set but more stringent than the third set, etc. Thus, the device may first compare the measurement data with the first set of criteria, and if the data satisfies the first set of criteria, the device may output the heart rate data. If the data fails to satisfy the first set of criteria, the device may then compare the heart rate data with the second set of criteria, etc. In some cases, the device may label the output data with a quality label. For example, because heart rate data that passes the second set of criteria but not the first set of criteria is not as reliable as data that passes the first set of criteria, the device may label all data, the most reliable data, or any data that fails to pass the first set of criteria with a label indicating the quality of the output data. Thus, the device may provide heart rate data to the user with no gaps or with minimal gaps in the data.

[0016] Aspects of the present disclosure are first described in the context of a system that supports collection of physiological data from a user by a wearable device. The aspects are then described with reference to a heart rate determination procedure, a channel selection procedure, and a graphical user interface (GUI). Aspects of the present disclosure are further represented by and described with reference to apparatus diagrams, system diagrams, and flowcharts relating to techniques for heart rate detection.

[0017] 1 illustrates an example of a system 100 that supports techniques for heartbeat detection according to aspects of the present disclosure. The system 100 includes multiple electronic devices (e.g., wearable devices 104, user devices 106) that can be worn and / or operated by one or more users 102. The system 100 further includes a network 108 and one or more servers 110.

[0018] The electronic devices may include any electronic devices known in the art, including wearable devices 104 (e.g., ring wearable devices, watch wearable devices, etc.), and user devices 106 (e.g., smartphones, laptops, tablets). The electronic devices associated with each user 102 may include one or more of the following functions: 1) measuring physiological data, 2) storing the measured data, 3) processing the data, 4) providing output to the user 102 (e.g., via a GUI) based on the processed data, and 5) exchanging data with each other and / or other computing devices. Different electronic devices may perform one or more of the functions.

[0019] Exemplary wearable devices 104 may include wearable computing devices such as a ring computing device (hereinafter “ring”) configured to be worn on a finger of a user 102, a wrist computing device (e.g., a smartwatch, fitness band, or bracelet) configured to be worn on a wrist of a user 102, and / or a head-mounted computing device (e.g., glasses / goggles). Wearable devices 104 may also include bands, straps (e.g., flexible or non-flexible bands or straps), stick-on sensors, etc. that may be positioned elsewhere, such as around the head (e.g., a forehead headband), arm (e.g., a forearm band and / or an upper arm band), and / or leg (e.g., a thigh or calf band), behind the ear, under the arm, etc. Wearable devices 104 may also be attached to or included in an article of clothing. For example, wearable devices 104 may be included in a pocket and / or pouch of clothing. As another example, the wearable device 104 may be clipped and / or pinned to clothing or otherwise maintained near the user 102. Examples of clothing items include, but are not limited to, hats, shirts, gloves, pants, socks, outerwear (e.g., jackets), and underwear. In some embodiments, the wearable device 104 may be included with other types of devices, such as training / sports devices used during physical activity. For example, the wearable device 104 may be attached to or included in a bicycle, skis, tennis racket, golf club, and / or training weights.

[0020] Much of the present disclosure may be described in relation to a ring wearable device 104. Accordingly, the terms “ring 104,” “wearable device 104,” and the like may be used interchangeably unless otherwise stated herein. However, the use of the term “ring 104” should not be considered limiting, as it is contemplated herein that aspects of the present disclosure may be implemented using other wearable devices (e.g., watch wearable devices, necklace wearable devices, bracelet wearable devices, earring wearable devices, anklet wearable devices, etc.).

[0021] In some embodiments, the user device 106 may include portable mobile computing devices such as smartphones and tablet computing devices. The user device 106 may also include personal computers such as laptops and desktop computing devices. Another example of a user device 106 is a server computing device capable of communicating with other electronic devices (e.g., via the Internet). In some implementations, the computing device may include a medical device such as an external wearable computing device (e.g., a Holter monitor). The medical device may also include an implantable medical device such as a pacemaker and a defibrillator. Other examples of the user device 106 include home computing devices such as Internet of Things (IoT) devices (e.g., IoT devices), smart televisions, smart speakers, smart displays (e.g., video calling displays), hubs (e.g., wireless communication hubs), security systems, smart appliances (e.g., thermostats and refrigerators), and fitness equipment.

[0022] Some electronic devices (e.g., wearable device 104, user device 106) may measure physiological parameters of each user 102, such as photoplethysmogram waveform, continuous skin temperature, pulse waveform, respiratory rate, heart rate, heart rate variability (HRV), actigraphy, galvanic skin response, pulse oximetry, and / or other physiological parameters. Some electronic devices that measure physiological parameters may also perform some / all of the calculations described herein. Some electronic devices may not measure physiological parameters but may perform some / all of the calculations described herein. For example, a ring (e.g., wearable device 104), a mobile device application, or a server computing device may process received physiological data measured by other devices.

[0023] In some implementations, the user 102 may operate or be associated with multiple electronic devices, some of which are capable of measuring physiological parameters and some of which are capable of processing the measured physiological parameters. In some implementations, the user 102 may have a ring (e.g., a wearable device 104) that measures physiological parameters. The user 102 may also have or be associated with a user device 106 (e.g., a mobile device, smartphone), where the wearable device 104 and the user device 106 are communicatively coupled to each other. In some cases, the user device 106 may receive data from the wearable device 104 and perform some / all of the calculations described herein. In some implementations, the user device 106 may also measure the physiological parameters described herein, such as movement / activity parameters.

[0024] 1 , a first user 102-a (user 1) may operate or be associated with a wearable device 104-a (e.g., ring 104-a) and a user device 106-a, which may operate as described herein. In this example, the user device 106-a associated with user 102-a may process / store physiological parameters measured by ring 104-a. In comparison, a second user 102-a (user 2) may be associated with a ring 104-b, a watch wearable device 104-c (e.g., watch 104-c), and a user device 106-b, and the user device 106-b associated with user 102-b may process / store physiological parameters measured by ring 104-b and / or watch 104-c. Additionally, an nth user 102-n (user N) can be associated with an arrangement of electronic devices (e.g., rings 104-n, user devices 106-n) described herein. In some aspects, wearable devices 104 (e.g., rings 104, watches 104) and other electronic devices can be communicatively coupled to the user devices 106 of each user 102 via Bluetooth, Wi-Fi, and other wireless protocols.

[0025] In some implementations, the ring 104 (e.g., wearable device 104) of system 100 may be configured to collect physiological data from each user 102 based on arterial blood flow, venous blood flow, etc., in the user's finger. In particular, the ring 104 may collect physiological data based on arterial blood flow in the user's finger using one or more LEDs (e.g., red LED, green LED) that emit light on the palm side of the user's finger. In some implementations, the ring 104 may acquire physiological data using a combination of both green and red LEDs. The physiological data may include any physiological data known in the art, including, but not limited to, temperature data, acceleration data (e.g., motion / exercise data), heart rate data, HRV data, blood oxygenation data, or any combination thereof.

[0026] The use of both green and red LEDs may offer several advantages over other solutions, as red and green LEDs have been found to have distinct advantages, such as when acquiring physiological data from different parts of the body under different conditions (e.g., light / dark, active / inactive). For example, green LEDs have been found to perform better during exercise. Furthermore, the use of multiple LEDs (e.g., green and red LEDs) distributed around the ring 104 has been found to perform better than wearable devices that utilize LEDs positioned close to each other, such as in a watch wearable device. Furthermore, the blood vessels (arteries, capillaries, etc.) in the fingers are more easily accessible via LEDs than the blood vessels in the wrist. In particular, the arteries in the wrist are located at the bottom of the wrist (e.g., on the palm side of the wrist), meaning that only the capillaries are accessible at the top of the wrist (e.g., on the back side of the wrist), where wearable watch devices and similar devices are typically worn. Therefore, the use of LEDs and other sensors in the ring 104 has been found to perform better than wearable devices worn on the wrist. This is because the ring 104 has greater access to the arteries (as compared to the capillaries), thereby providing a stronger signal and more useful physiological data.

[0027] The electronic devices of the system 100 (e.g., the user device 106, the wearable device 104) may be communicatively coupled to one or more servers 110 via wired or wireless communication protocols. For example, as shown in FIG. 1 , the electronic devices (e.g., the user device 106) may be communicatively coupled to one or more servers 110 via a network 108. The network devices may implement a Transmission Control Protocol and Internet Protocol (TCP / IP), such as the Internet, or may implement other network 108 protocols. The network connection between the network 108 and each electronic device may facilitate the transport of data via email, web, text message, or any other suitable form of interaction within the computer network 108. For example, in some implementations, a ring 104-a associated with a first user 102-a may be communicatively coupled to a user device 106-a, which is communicatively coupled to the server 110 via the network 108. In further or alternative cases, the wearable device 104 (e.g., ring 104, watch 104) may be communicatively coupled directly to the network 108.

[0028] The system 100 may provide on-demand database services between the user devices 106 and one or more servers 110. In some cases, the servers 110 may receive data from the user devices 106 over the network 108 and may store and analyze the data. Similarly, the servers 110 may provide data to the user devices 106 over the network 108. In some cases, the servers 110 may be located in one or more data centers. The servers 110 may be used for data storage, management, and processing. In some implementations, the servers 110 may provide a web-based interface to the user devices 106 via a web browser.

[0029] In some aspects, the system 100 may detect periods during which the user 102 is asleep and classify the periods during which the user 102 is asleep into one or more sleep stages (e.g., sleep stage classification). For example, as shown in FIG. 1, the user 102-a may be associated with a wearable device 104-a (e.g., a ring 104-a) and a user device 106-a. In this example, the ring 104-a may collect physiological data associated with the user 102-a, including temperature, heart rate, HRV, respiratory rate, etc. In some aspects, the data collected by the ring 104-a may be input into a machine learning classifier, which is configured to determine periods during which the user 102-a is (or was) asleep. Furthermore, the machine learning classifier may be configured to classify the periods into different sleep stages, including a wake sleep stage, a rapid eye movement (REM) sleep stage, a light sleep stage (non-REM (NREM)), and a deep sleep stage (NREM). In some aspects, the classified sleep stages may be displayed to the user 102-a via a GUI on the user device 106-a. The sleep stage classification may be used to provide feedback to the user 102-a regarding the user's sleep patterns, such as a recommended bedtime, a recommended wake-up time, etc. Additionally, in some implementations, the sleep stage classification techniques described herein may be used to calculate scores for each user, such as sleep scores, readiness scores, etc.

[0030] In some embodiments, the system 100 may utilize features derived from circadian rhythms to further improve physiological data collection, data processing procedures, and other techniques described herein. The term circadian rhythm may refer to the natural bodily processes that regulate an individual's sleep-wake cycle, which repeats approximately every 24 hours. In this regard, the techniques described herein may utilize circadian rhythm adjustment models to improve physiological data collection, analysis, and data processing. For example, the circadian rhythm adjustment model may be input into a machine learning classifier along with physiological data collected from the user 102-a by the wearable device 104-a. In this example, the circadian rhythm adjustment model may be configured to "weight" or adjust the physiological data collected over the user's natural, approximately 24-hour circadian rhythm. In some implementations, the system may initially start with a "baseline" circadian rhythm adjustment model and modify the baseline model using physiological data collected from each user 102 to generate an adjusted personal circadian rhythm adjustment model that is unique to each individual user 102.

[0031] In some embodiments, system 100 may utilize other physiological rhythms to further refine the collection, analysis, and processing of physiological data by the phase of these other rhythms. For example, if a weekly rhythm is detected in an individual's baseline data, the model may be configured to adjust the "weight" of the data by day of the week. Biological rhythms that may require adjustment to the model in this manner include: 1) ultradian rhythms (shorter than daily rhythms), including sleep cycles and sub-hourly to multi-hourly oscillations in physiological variables measured during the sleep state; 2) circadian rhythms; 3) non-endogenous life rhythms that have been shown to be imposed in addition to circadian rhythms, such as work schedules; 4) weekly rhythms or other exogenously imposed artificial time periodicities (e.g., a hypothetical culture with a 12-day "week" might use a 12-day rhythm); 5) multi-day ovarian rhythms in women and spermatogenic rhythms in men; 6) lunar rhythms (associated with individuals living with little or no artificial light); and 7) seasonal rhythms.

[0032] Biological rhythms are not always fixed rhythms. For example, many women experience ovarian cycle lengths that vary from cycle to cycle, and ultradian rhythms cannot be expected to occur at exactly the same time or periodically across days, even in the same user. Therefore, signal processing techniques sufficient to quantify the frequency structure of these rhythms while maintaining the temporal resolution of these rhythms in physiological data can be used to improve the detection of these rhythms and assign a phase to each measured instant, thereby adjusting adjustment models and comparisons of time intervals. Biological rhythm adjustment models and parameters can be added in linear or nonlinear combinations as needed to more accurately capture the dynamic physiological metrics of an individual or group of individuals.

[0033] In some embodiments, each device in system 100 may support techniques for determining a user's heart rate data based on physiological data (e.g., motion data, temperature data) collected by the wearable device. The system may support techniques for determining heart rate data regardless of whether the user is in a resting state, etc. In particular, system 100 depicted in FIG. 1 may support techniques for determining heart rate data for user 102 and causing a user device 106 corresponding to user 102 to display an indication of the heart rate data. In some cases, displaying the heart rate data may be based on comparing the heart rate data to one or more sets of thresholds prior to display to display the heart rate data based on the quality of the data. In some cases, determining the quality of the data may be performed according to an iterative (e.g., stepwise) comparison procedure.

[0034] For example, as shown in FIG. 1 , user 1 (user 102-a) may be associated with wearable device 104-a (e.g., ring 104-a) and user device 106-a. In this example, ring 104-a may collect data associated with user 102-a, including movement, temperature, heart rate, HRV, etc. In some aspects, ring 104-a may be used to collect physiological data of the user, which may be used to determine whether ring 104-a should perform PPG monitoring. In some cases, wearable device 104-a may select a channel (e.g., a set of one or more sensors) on which to collect PPG data. For example, wearable device 104-a may be configured with multiple PPG sensors, and a PPG sensor can be a pair of an emitter (e.g., an LED) and a receiver (e.g., a photodetector) that constitutes an optical path (e.g., a channel) for PPG measurement. In some cases, the PPG sensors may refer to one or more green LEDs, one or more red LEDs, one or more IR LEDs, or any other set of LEDs, and one or more PPG sensors may be selected to acquire PPG data based on signal quality associated with one or more of the PPG sensors.

[0035] The ring 104-a may determine the heartbeat data based on the PPG monitoring. The physiological data collection, PPG monitoring, and heartbeat data determination may be performed by any of the components of the system 100, including the ring 104-a associated with the user 1, the user device 106-a, one or more servers 110, or any combination thereof. During the determination of the heartbeat data, the system 100 may selectively display all or a portion of the heartbeat data in the GUI of the user device 106-a.

[0036] Those skilled in the art will appreciate that one or more aspects of the present disclosure may be implemented in system 100 to solve additional or alternative problems other than those described above. Moreover, aspects of the present disclosure may provide technical improvements over the "conventional" systems or processes described herein. However, the specification and accompanying drawings include only examples of technical improvements obtained by implementing aspects of the present disclosure and, therefore, do not represent the full scope of the technical scope provided within the claims.

[0037] 2 illustrates an example of a system 200 that supports techniques for heartbeat detection according to aspects of the present disclosure. System 200 may implement or be implemented by system 100. In particular, system 200 illustrates an example of ring 104 (e.g., wearable device 104), user device 106, and server 110 described with reference to FIG.

[0038] In some embodiments, ring 104 may be configured to be worn around a user's finger and may determine one or more user physiological parameters when worn around the user's finger. Examples of measurements and determinations may include, but are not limited to, user skin temperature, pulse waveform, respiratory rate, heart rate, HRV, blood oxygenation, etc.

[0039] The system 200 further includes a user device 106 (e.g., a smartphone) that communicates with the ring 104. For example, the ring 104 may communicate wirelessly and / or wired with the user device 106. In some implementations, the ring 104 may transmit measured and processed data (e.g., temperature data, PPG data, motion / acceleration data, ring input data, etc.) to the user device 106. The user device 106 may also transmit data to the ring 104, such as firmware / settings updates for the ring 104. The user device 106 may process the data. In some implementations, the user device 106 may transmit the data to the server 110 for processing and / or storage.

[0040] The ring 104 may include a housing 205, which may include an inner housing 205-a and an outer housing 205-b. In some embodiments, the housing 205 of the ring 104 may store or otherwise contain various components of the ring, including, but not limited to, device electronics, a power source (e.g., a battery 210 and / or a capacitor), one or more boards (e.g., printed circuit boards) interconnecting the device electronics and / or electrodes, etc. The device electronics may include device modules (e.g., hardware / software) such as a processing module 230-a, a memory 215, a communication module 220-a, a power module 225, etc. The device electronics may also include one or more sensors. Examples of sensors may include, but are not limited to, one or more temperature sensors 240, a PPG sensor assembly (e.g., a PPG system 235), and one or more motion sensors 245.

[0041] The sensors may include associated modules (not shown) configured to communicate with and generate signals associated with each sensor in the ring 104. In some aspects, each of the components / modules in the ring 104 may be communicatively coupled to one another via wireless or wired connections. Additionally, the ring 104 may include additional and / or alternative sensors or other components configured to collect physiological data from the user, including optical sensors (e.g., LEDs), oximeters, etc.

[0042] The ring 104 described and illustrated with reference to FIG. 2 is provided for illustrative purposes only. Thus, the ring 104 may include additional or alternative components to those depicted in FIG. 2. Other rings 104 may be manufactured that provide the functionality described herein. For example, rings 104 may be manufactured with fewer components (sensors). In specific examples, a ring 104 may be manufactured with a single temperature sensor 240 (or other sensor), a power source, and device electronics configured to read the single temperature sensor 240 (or other sensor). In other examples, the temperature sensor 240 (or other sensor) may be attached to a user's finger (e.g., using a clamp, a spring-loaded clamp, etc.). In this case, the sensor may be wired to another computing device, such as a wrist-worn computing device, that reads the temperature sensor 240 (or other sensor). In other examples, rings 104 may be manufactured that include additional sensors and processing capabilities.

[0043] The housing 205 may include one or more housing 205 components. The housing 205 may include an outer housing 205-b component (e.g., a shell) and an inner housing 205-a component (e.g., a molding). The housing 205 may include additional components (e.g., additional layers) not explicitly shown in FIG. 2 . For example, in some implementations, the ring 104 may include one or more insulating layers that electrically insulate the device electronics and other conductive materials (e.g., electrical traces) from the outer housing 205-b (e.g., a metal outer housing 205-b). The housing 205 may provide structural support for the device electronics, battery 210, substrate, and other components. For example, the housing 205 may protect the device electronics, battery 210, and substrate from mechanical forces such as pressure and impact. The housing 205 may also protect the device electronics, battery 210, and substrate from water and / or other chemicals.

[0044] The outer housing 205-b can be manufactured from one or more materials. In some implementations, the outer housing 205-b can include a metal such as titanium, which can provide strength and wear resistance while being relatively lightweight. The outer housing 205-b can also be manufactured from other materials, such as polymers. In some implementations, the outer housing 205-b can be protective as well as decorative.

[0045] The inner housing 205-a may be configured to interface with a user's finger. The inner housing 205-a may be formed from a polymer (e.g., a medical-grade polymer) or other material. In some implementations, the inner housing 205-a may be transparent. For example, the inner housing 205-a may transmit light emitted by a PPG light-emitting diode (LED). In some implementations, components of the inner housing 205-a may be molded onto the outer housing 205-b. For example, the inner housing 205-a may include a polymer that is molded (e.g., injection molded) to fit into the metal shell of the outer housing 205-b.

[0046] The ring 104 may include one or more substrates (not shown). The device electronics and battery 210 may be included on one or more substrates. For example, the device electronics and battery 210 may be mounted on one or more substrates. Examples of substrates may include one or more printed circuit boards (PCBs), such as flexible PCBs (e.g., polyimide). In some implementations, the electronics / battery 210 may include surface-mounted devices (e.g., surface-mount technology (SMT) devices) on a flexible PCB. In some implementations, the one or more substrates (e.g., one or more flexible PCBs) may include electrical traces that provide electrical communication between the device electronics. The electrical traces may also connect the battery 210 to the device electronics.

[0047] The device electronics, battery 210, and substrate may be arranged in a variety of ways on ring 104. In some implementations, one substrate containing the device electronics may be mounted along the bottom (e.g., bottom half) of ring 104 so that sensors (e.g., PPG system 235, temperature sensor 240, motion sensor 245, and other sensors) interface with the underside of a user's finger. In such implementations, battery 210 may be included along the top of ring 104 (e.g., on another substrate).

[0048] The various components / modules of ring 104 represent functions (e.g., circuits and other components) that may be included in ring 104. A module may include any discrete and / or integrated electronic circuit components that implement analog and / or digital circuitry capable of producing the functions attributed to the module herein. For example, a module may include analog circuitry (e.g., amplification circuitry, filtering circuitry, analog-to-digital conversion circuitry, and / or other signal conditioning circuitry). A module may include digital circuitry (e.g., combinational or sequential logic circuitry, memory circuitry, etc.).

[0049] The memory 215 (memory module) of the ring 104 may include volatile, nonvolatile, magnetic, or electrical media, such as random access memory (RAM), read-only memory (ROM), nonvolatile RAM (NVRAM), electrically erasable programmable ROM (EEPROM), flash memory, or any other memory device. The memory 215 may store any of the data described herein. For example, the memory 215 may be configured to store data collected by each sensor and the PPG system 235 (e.g., motion data, temperature data, PPG data). Additionally, the memory 215 may include instructions that, when executed by one or more processing circuits, cause the module to perform various functions attributed to the module herein. The device electronics of the ring 104 described herein are merely exemplary device electronics. Thus, the types of electronic components used to implement the device electronics can vary based on design considerations.

[0050] The functionality attributed to the modules of ring 104 described herein may be embodied as one or more processors, hardware, firmware, software, or any combination thereof. The depiction of various functions as modules is intended to highlight various functional measures and does not necessarily imply that such modules must be realized by separate hardware / software components. Rather, functionality associated with one or more modules may be performed by separate hardware / software components or incorporated within a common hardware / software component.

[0051] The processing module 230-a of the ring 104 may include one or more processors (e.g., processing units), microcontrollers, digital signal processors, systems-on-chips (SOCs), and / or other processing devices. The processing module 230-a communicates with the modules of the ring 104. For example, the processing module 230-a may transmit data to or receive data from the modules and other components (e.g., sensors) of the ring 104. As described herein, the modules may be implemented by various circuit components. Thus, the modules may also be referred to as circuits (e.g., communication circuits and power circuits).

[0052] Processing module 230-a may be in communication with memory 215. Memory 215 may include computer-readable instructions that, when executed by processing module 230-a, cause processing module 230-a to perform various functions attributed to processing module 230-a herein. In some implementations, processing module 230-a (e.g., a microcontroller) may include additional functionality associated with other modules, such as communication functionality provided by communications module 220-a (e.g., an integrated Bluetooth Low Energy transceiver) and / or additional on-board memory 215.

[0053] The communication module 220-a may include circuitry for providing wireless and / or wired communication with the user device 106 (e.g., the communication module 220-b of the user device 106). In some implementations, the communication modules 220-a, 220-b may include wireless communication circuitry, such as Bluetooth circuitry and / or Wi-Fi circuitry. In some implementations, the communication modules 220-a, 220-b may include wired communication circuitry, such as Universal Serial Bus (USB) communication circuitry. Using the communication module 220-a, the ring 104 and the user device 106 may be configured to communicate with each other. The processing module 230-a of the ring 104 may send data to or receive data from the user device 106 via the communication module 220-a. Examples of data may include, but are not limited to, athletic data, temperature data, pulse waveforms, heart rate data, HRV data, PPG data, and status updates (e.g., charging status, battery charge level, and / or configuration settings of the ring 104). The processing module 230-a of the ring 104 may also be configured to receive updates (eg, software / firmware updates) and data from the user devices 106.

[0054] The ring 104 may include a battery 210 (rechargeable battery 210). Examples of the battery 210 may include a lithium-ion or lithium polymer type battery 210, although various battery 210 options are possible. The battery 210 may be wirelessly charged. In some implementations, the ring 104 may include a power source other than the battery 210, such as a capacitor. The power source (e.g., the battery 210 or capacitor) may be curved to match the curve of the ring 104. In some aspects, the charger or other power source may include additional sensors that may be used to collect data in addition to or complementary to data collected by the ring 104. Furthermore, the charger or other power source for the ring 104 may function as the user device 106, in which case the charger or other power source for the ring 104 may be configured to receive data from the ring 104, store and / or process data received from the ring 104, and exchange data between the ring 104 and the server 110.

[0055] In some embodiments, the ring 104 includes a power module 225 that can control the charging of the battery 210. For example, the power module 225 can interface with an external wireless charger that charges the battery 210 when interfaced with the ring 104. The charger can include datum structures that mate with datum structures on the ring 104 to create a specific orientation with the ring 104 while charging. The power module 225 can also regulate the voltage of the device electronics, regulate the power output to the device electronics, and monitor the state of charge of the battery 210. In some implementations, the battery 210 can include a protection circuit module (PCM) that protects the battery 210 from high current discharge, overvoltage while charging the battery 104, and undervoltage while discharging the battery 104. The power module 225 can also include electrostatic discharge (ESD) protection.

[0056] One or more temperature sensors 240 may be electrically coupled to the processing module 230-a. The temperature sensor 240 may be configured to generate a temperature signal (e.g., temperature data) indicative of a temperature read or sensed by the temperature sensor 240. The processing module 230-a may determine the user's temperature at the location of the temperature sensor 240. For example, in the ring 104, the temperature data generated by the temperature sensor 240 may include the user's temperature (e.g., skin temperature) at the user's finger. In some implementations, the temperature sensor 240 may contact the user's skin. In other implementations, a portion of the housing 205 (e.g., the inner housing 205-a) may form a barrier (e.g., a thin thermally conductive barrier) between the temperature sensor 240 and the user's skin. In some implementations, the portion of the ring 104 configured to contact the user's finger may comprise a thermally conductive portion and a thermally insulating portion. The thermally conductive portion may conduct heat from the user's finger to the temperature sensor 240. The thermal insulating portion can insulate portions of the ring 104 (eg, the temperature sensor 240) from the ambient temperature.

[0057] In some implementations, the temperature sensor 240 may generate a digital signal (e.g., temperature data) that the processing module 230-a can use to determine the temperature. As another example, if the temperature sensor 240 includes a passive sensor, the processing module 230-a (or a module of the temperature sensor 240) may measure the current / voltage generated by the temperature sensor 240 and determine the temperature based on the measured current / voltage. Examples of the temperature sensor 240 may include a thermistor, such as a negative temperature coefficient (NTC) thermistor, or other types of sensors including resistors, transistors, diodes, and / or other electrical / electronic components.

[0058] The processing module 230-a may sample the user's temperature over time. For example, the processing module 230-a may sample the user's temperature according to a sampling rate. An example sampling rate may include one sample per second, although the processing module 230-a may be configured to sample the temperature signal at other sampling rates higher or lower than one sample per second. In some implementations, the processing module 230-a may sample the user's temperature continuously throughout the day and night. Sampling at a sufficient rate (e.g., one sample per second) throughout the day may provide sufficient temperature data for the analyses described herein.

[0059] The processing module 230-a may store the sampled temperature data in the memory 215. In some implementations, the processing module 230-a may process the sampled temperature data. For example, the processing module 230-a may determine an average temperature value over a period of time. In one example, the processing module 230-a may determine an average temperature value per minute by summing the temperature values ​​collected in one minute and dividing by the number of samples over the one minute. In an example where the temperature is sampled at one sample per second, the average temperature may be the sum of all sampled temperatures for one minute divided by 60 seconds. The memory 215 may store average temperature values ​​over time. In some implementations, the memory 215 may store average temperatures (e.g., one per minute) rather than sampled temperatures to conserve memory 215.

[0060] The sampling rate, which may be stored in memory 215, is configurable. In some implementations, the sampling rate may be the same throughout the day and night. In other implementations, the sampling rate may vary throughout the day / night. In some implementations, ring 104 may filter out / reject temperature readings, such as large spikes in temperature that do not indicate a physiological change (e.g., a temperature spike due to a hot shower). In some implementations, ring 104 may filter out / reject temperature readings that may be unreliable due to other factors, such as excessive movement of ring 104 while exercising (e.g., as indicated by motion sensor 245).

[0061] The ring 104 (e.g., a communications module) may transmit the sampled temperature data and / or average temperature data to the user device 106 for storage and / or further processing. The user device 106 may forward the sampled temperature data and / or average temperature data to the server 110 for storage and / or further processing.

[0062] Although ring 104 is depicted as including a single temperature sensor 240, ring 104 may include multiple temperature sensors 240 positioned in one or more locations, for example, along inner housing 205-a near a user's finger. In some implementations, temperature sensor 240 may be a stand-alone temperature sensor 240. Additionally or alternatively, one or more temperature sensors 240 may be included (e.g., packaged with other components), for example, with an accelerometer and / or a processor.

[0063] The processing module 230-a may obtain and process data from multiple temperature sensors 240 in a manner similar to that described for a single temperature sensor 240. For example, the processing module 230-a may sample, average, and store temperature data from each of the multiple temperature sensors 240 individually. In other examples, the processing module 230-a may sample the sensors at different rates and average / store different values ​​for different sensors. In some implementations, the processing module 230-a may be configured to determine a single temperature based on an average of two or more temperatures determined by two or more temperature sensors 240 at different locations on the finger.

[0064] The temperature sensor 240 of the ring 104 may acquire a distal temperature at a user's finger (e.g., any finger). For example, one or more temperature sensors 240 of the ring 104 may acquire the user's temperature from the underside of the finger or at different locations on the finger. In some implementations, the ring 104 may continuously acquire the distal temperature (e.g., at a sampling rate). Although distal temperatures measured by the ring 104 at a finger are described herein, other devices may measure temperatures at the same or different locations. In some cases, the distal temperature measured at a user's finger may differ from the temperature measured at the user's wrist or other external body location. Furthermore, the distal temperature measured at a user's finger (e.g., "shell" temperature) may differ from the user's core temperature. Thus, the ring 104 may provide a useful temperature signal that may not be acquired at other internal / external body locations. In some cases, continuous temperature measurement at a finger may capture temperature fluctuations (e.g., small or large fluctuations) that may not be apparent in the core temperature. For example, continuous temperature measurements on a finger may capture minute-to-minute or hourly temperature fluctuations that provide additional insight that may not be provided by other temperature measurements elsewhere on the body.

[0065] The ring 104 may include a PPG system 235. The PPG system 235 may include one or more optical transmitters that transmit light. The PPG system 235 may also include one or more optical receivers that receive light transmitted by the one or more optical transmitters. The optical receivers may generate a signal (hereinafter, a "PPG signal") indicative of the amount of light received by the optical receivers. The optical transmitters may illuminate an area on the user's finger. The PPG signal generated by the PPG system 235 may indicate blood perfusion in the illuminated area. For example, the PPG signal may indicate changes in blood volume in the illuminated area caused by the user's pulse pressure. The processing module 230-a may sample the PPG signal and determine the user's pulse waveform based on the PPG signal. The processing module 230-a may determine various physiological parameters, such as the user's respiratory rate, heart rate, HRV, oxygen saturation, and other circulatory parameters, based on the user's pulse waveform.

[0066] In some implementations, the PPG system 235 may be configured as a reflective PPG system 235 in which the optical receiver receives transmitted light reflected by a region of the user's finger. In some implementations, the PPG system 235 may be configured as a transmissive PPG system 235 in which the optical transmitter and optical receiver are positioned opposite each other so that light is transmitted directly through a portion of the user's finger to the optical receiver.

[0067] The number and proportion of transmitters and receivers included in the PPG system 235 can vary. An example of an optical transmitter is a light-emitting diode (LED). The optical transmitter may transmit light in the infrared spectrum and / or other spectrums. Examples of optical receivers include, but are not limited to, photosensors, phototransistors, and photodiodes. The optical receiver may be configured to generate a PPG signal in response to wavelengths received from the optical transmitters. The locations of the transmitters and receivers can vary. Furthermore, a single device may include a reflective and / or transmissive PPG system 235.

[0068] 2 may include a reflective PPG system 235 in some implementations. In such implementations, the PPG system 235 may include a centrally located optical receiver (at the bottom of the ring 104) and two optical transmitters located on either side of the optical receiver. In this implementation, the PPG system 235 (e.g., the optical receiver) may generate a PPG signal based on light received from one or both of the optical transmitters. In other implementations, other arrangements, combinations, and / or configurations of one or more optical transmitters and / or optical receivers are contemplated.

[0069] The processing module 230-a may control one or both of the optical transmitters to transmit light while sampling the PPG signal generated by the optical receiver. In some implementations, the processing module 230-a may cause the optical transmitter with the stronger received signal to transmit light while sampling the PPG signal generated by the optical receiver. For example, the selected optical transmitter may emit light continuously while the PPG signal is sampled at a sampling rate (e.g., 250 Hz).

[0070] Sampling the PPG signal generated by the PPG system 235 can result in a pulse waveform, which may also be referred to as a "PPG." The pulse waveform may indicate blood pressure over time for multiple cardiac cycles. The pulse waveform may include peaks indicative of cardiac cycles. Additionally, the pulse waveform may include respiratory-induced variations, which may be used to determine respiratory rate. In some implementations, the processing module 230-a may store the pulse waveform in memory 215. The processing module 230-a may process the pulse waveform as the pulses are generated and / or from memory 215 to determine the physiological parameters described herein.

[0071] The processing module 230-a may determine the user's heart rate based on the pulse waveform. For example, the processing module 230-a may determine the heart rate (e.g., in beats per minute) based on the time between peaks of the pulse waveform. The time between the peaks may be referred to as the interbeat interval (IBI). The processing module 230-a may store the determined heart rate value and IBI in the memory 215.

[0072] The processing module 230-a may determine HRV over time. For example, the processing module 230-a may determine HRV based on variations in IBI. The processing module 230-a may store the HRV values ​​over time in memory 215. Additionally, the processing module 230-a may determine the user's respiration rate over time. For example, the processing module 230-a may determine the respiration rate based on frequency modulation, amplitude modulation, or baseline modulation of the user's IBI values ​​over a period of time. The respiration rate may be calculated in breaths per minute or other respiration rate (e.g., breaths per 30 seconds). The processing module 230-a may store the user's respiration values ​​over time in memory 215.

[0073] The ring 104 may include one or more motion sensors 245, such as one or more accelerometers (e.g., 6-D accelerometers) and / or one or more gyroscopes (gyros). The motion sensors 245 may generate motion signals indicative of sensor motion. For example, the ring 104 may include one or more accelerometers that generate acceleration signals indicative of acceleration of the accelerometer. As another example, the ring 104 may include one or more gyro sensors that generate gyro signals indicative of angular motion (e.g., angular velocity) and / or changes in orientation. The motion sensors 245 may be included in one or more sensor packages. An exemplary accelerometer / gyro sensor is the Bosch BMI160 inertial microelectromechanical system (MEMS), which can measure angular velocity and acceleration in three orthogonal axes.

[0074] The processing module 230-a may sample the motion signals at a sampling rate (e.g., 50 Hz) and determine the motion of the ring 104 based on the sampled motion signals. For example, the processing module 230-a may sample the acceleration signals to determine the acceleration of the ring 104. As another example, the processing module 230-a may sample the gyro signals to determine the angular motion. In some implementations, the processing module 230-a may store the motion data in the memory 215. The motion data may include the sampled motion data as well as motion data calculated based on the sampled motion signals (e.g., acceleration and angular values).

[0075] The ring 104 may store various data described herein. The ring 104 may store temperature data, such as raw sampled temperature data and calculated temperature data (e.g., average temperature). As another example, the ring 104 may store PPG signal data, such as pulse waveforms and data calculated based on the pulse waveforms (e.g., heart rate, IBI, HRV, and respiration values). The ring 104 may also store motion data, such as sampled motion data indicative of linear and angular motion.

[0076] The ring 104, or other computing device, may calculate and store additional values ​​based on the sampled / calculated physiological data. For example, the processing module 230-a may calculate and store various metrics, such as sleep metrics (e.g., sleep scores), activity metrics, and readiness metrics. In some implementations, the additional values / metrics may be referred to as "derived values." The ring 104, or other computing / wearable device, may calculate various values / metrics related to movement. Examples of derived values ​​of movement data may include, but are not limited to, movement counts, regularity values, intensity values, metabolic equivalence of task values ​​(METs), and direction values. The movement counts, regularity values, intensity values, and METs may indicate the amount (e.g., speed / acceleration) of the user's movement over time. The direction value may indicate how the ring 104 is oriented on the user's finger and whether the ring 104 is worn on the left or right hand.

[0077] In some implementations, the movement count and regularity values ​​may be determined by counting the number of acceleration peaks within one or more periods (e.g., one or more 30-second to 1-minute clusters). The intensity value may indicate the number of movements and the associated strength of the movements (e.g., acceleration values). The intensity values ​​may be classified as low, medium, and high depending on the associated threshold acceleration value. The MET may be determined based on the movement intensity, the regularity / irregularity of the movements, and the number of movements associated with different intensities over a period (e.g., 30 seconds).

[0078] In some implementations, the processing module 230-a may compress data stored in memory 215. For example, the processing module 230-a may perform calculations based on the sampled data and then delete the sampled data. As another example, the processing module 230-a may average data over a longer period of time to reduce the number of stored values. In a specific example, if a user's average body temperature for one minute is stored in memory 215, the processing module 230-a may calculate the average body temperature over five minutes for storage and then delete the one-minute average body temperature data. The processing module 230-a may compress data based on various factors, such as the total amount of used / available memory 215 and / or the amount of time since the ring 104 last transmitted data to the user device 106.

[0079] The user's physiological parameters may be measured by a sensor included in ring 104, although other devices may measure the user's physiological parameters. For example, the user's body temperature may be measured by a temperature sensor included in ring 104, although other devices may measure the user's body temperature. In some examples, other wearable devices (e.g., wrist devices) may include sensors that measure the user's physiological parameters. Furthermore, medical devices, such as external medical devices (e.g., wearable medical devices) and / or implantable medical devices, may measure the user's physiological parameters. One or more sensors in any type of computing device may be used to implement the techniques described herein.

[0080] The physiological measurements may be taken continuously throughout the day and / or night. In some implementations, the physiological measurements may be taken during a portion of the day and / or a portion of the night. In some implementations, the physiological measurements may be taken in response to determining that the user is in a particular state, such as an active state, a resting state, and / or a sleeping state. For example, the ring 104 may take physiological measurements in a resting / sleeping state to obtain a cleaner physiological signal. In one example, the ring 104 or other device / system may detect when the user is resting and / or sleeping and obtain physiological parameters (e.g., body temperature) for the detected state. The device / system may use the resting / sleeping physiological data and / or other data when the user is in other states to implement the techniques of this disclosure.

[0081] In some implementations, the ring 104 may be configured to collect, store, and / or process data, as previously described herein, and may store and / or transfer any of the data described herein to the user device 106 for storage. In some aspects, the user device 106 includes a wearable application 250, an operating system (OS), a web browser application (e.g., web browser 280), one or more additional applications, and a GUI 275. The user device 106 may further include other modules and components, including sensors, audio devices, haptic feedback devices, etc. The wearable application 250 may include one example of an application (e.g., an “APP”) that may be installed on the user device 106. The wearable application 250 may be configured to acquire data from the ring 104, store the acquired data, and process the acquired data, as described herein. For example, the wearable application 250 may include a user interface (UI) module 255, an acquisition module 260, a processing module 230-b, a communication module 220-b, and a storage module (e.g., a database 265) configured to store application data.

[0082] The various data processing operations described herein may be performed by the ring 104, the user devices 106, the server 110, or any combination thereof. For example, in some cases, data collected by the ring 104 may be pre-processed and transmitted to the user devices 106. In this example, the user devices 106 may perform some data processing operations on the received data, or transmit the data to a server for data processing, or both. For example, in some cases, the user devices 106 may perform processing operations that require relatively low processing power and / or operations that require relatively low latency, while the user devices 106 may transmit data to the server 110 for processing operations that require relatively high processing power and / or operations that can tolerate relatively high latency.

[0083] In some aspects, the ring 104, user device 106, and server 110 of system 200 may be configured to evaluate a user's sleep patterns. In particular, each component of system 200 may be used to collect data from the user via ring 104 and generate one or more scores (e.g., sleep score, readiness score) for the user based on the collected data. For example, as previously described herein, the ring 104 of system 200 may be worn by a user to collect data from the user, including body temperature, heart rate, HRV, etc. The data collected by ring 104 may be used to determine when the user is asleep to evaluate the user's sleep for a given "sleep day." In some aspects, a score may be calculated for the user for each sleep day, whereby a first sleep day is associated with a first set of scores, a second sleep day is associated with a second set of scores, and so on. A score may be calculated for each sleep day based on the data collected by ring 104 for each sleep day. Scores may include, but are not limited to, a sleep score, a readiness score, and the like.

[0084] In some cases, "sleep days" may coincide with traditional calendar days, such that a given sleep day runs from midnight to midnight on each calendar day. In other cases, sleep days may be offset relative to the calendar day. For example, a sleep day may last from 6:00 PM (18:00) on one calendar day to 6:00 PM (18:00) on the next calendar day. In this example, 6:00 PM serves as a "cutoff time," with data collected from the user before 6:00 PM being counted as the current sleep day and data collected from the user after 6:00 PM being counted as the next sleep day. Due to the fact that most people sleep best at night, offsetting sleep days relative to the calendar day may enable system 200 to assess a user's sleep patterns in a manner consistent with the user's sleep schedule. In some cases, users may be able to selectively adjust the timing of sleep days relative to the calendar day (e.g., via a GUI) so that the sleep days coincide with each user's usual sleep times.

[0085] In some implementations, a user's respective overall score (e.g., sleep score, readiness score) for each day may be determined / calculated based on one or more "factors," "contributing factors," or "contributing factors." For example, a user's overall sleep score may be calculated based on a set of factors including total sleep, efficiency, rest, REM sleep, deep sleep, latency, timing, or any combination thereof. A sleep score may include any number of factors. A "total sleep" factor may refer to the sum of all sleep periods on a sleep day. An "efficiency" factor may reflect the proportion of time asleep compared to time awake in bed and may be calculated using an efficiency average of the longer sleep periods (e.g., main sleep periods) on a sleep day, weighted by the duration of each sleep period. A "restfulness" factor may indicate how restful a user's sleep is and may be calculated using an average of all sleep periods on a sleep day, weighted by the duration of each period. The rest factor may be based on "wake-up count" (the sum of all wake-ups (when the user wakes up) detected during different sleep periods), excessive movement, and "wake-up count" (e.g., the sum of all wake-ups (when the user gets out of bed) detected during different sleep periods).

[0086] The "REM sleep" factor can refer to the total REM sleep duration across all sleep periods on a sleep day, including REM sleep. Similarly, the "deep sleep" factor can refer to the total deep sleep duration across all sleep periods on a sleep day, including deep sleep. The "latency" factor can indicate the time it takes a user to fall asleep (e.g., average, median, longest) and can be calculated using an average of long sleep periods across a sleep day, weighted by the duration of each period and the number of such periods (e.g., a given sleep stage or the integration of multiple sleep stages can be its own contributing factor or weighted by other contributing factors). Finally, the "timing" factor can refer to the relative timing of sleep periods within a sleep day and / or calendar day and can be calculated using an average of all sleep periods on a sleep day, weighted by the duration of each period.

[0087] As another example, a user's overall readiness score may be calculated based on a set of factors including sleep, sleep balance, heart rate, HRV balance, recovery index, temperature, activity, activity balance, or any combination thereof. A readiness score may include any number of factors. The "sleep" factor may refer to the combined sleep score of all sleep periods during a sleep day. The "sleep balance" factor may refer to the cumulative duration of all sleep periods during a sleep day. In particular, sleep balance may indicate to a user whether the sleep a user has obtained over a period of time (e.g., the past two weeks) is balanced with the user's needs. Typically, adults require 7 to 9 hours of sleep each night to stay healthy, alert, and perform at their best mentally and physically. However, because occasional nights of poor quality sleep are normal, the sleep balance factor considers long-term sleep patterns to determine whether each user's sleep needs are being met. The "resting heart rate" factor may indicate the lowest heart rate from the longest sleep period (e.g., the primary sleep period) during a sleep day and / or the lowest heart rate from a nap taken after the primary sleep period.

[0088] Continuing to refer to the "factors" (e.g., contributing factors) of the readiness score, the "HRV Balance" factor may indicate the highest HRV average from the primary sleep period and the nap taken after the primary sleep period. The HRV Balance factor may help a user track their recovery status by comparing the user's HRV trend over a first period (e.g., two weeks) with the user's HRV trend over a second, longer period (e.g., three months). The "Recovery Index" factor may be calculated based on the longest sleep period. The recovery index measures how long it takes the user's resting heart rate to stabilize during the night. A sign of very good recovery is when the user's resting heart rate stabilizes during the first half of the night, i.e., at least six hours before the user wakes up, allowing the body time to recover for the next day. The "Temperature" factor may be calculated based on the longest sleep period (e.g., the primary sleep period) or based on a nap taken after the longest sleep period, if the user's maximum body temperature during the nap is at least 0.5°C higher than the maximum body temperature during the longer period. In some embodiments, the ring can measure the user's temperature while the user is asleep, and the system 200 can display the user's average temperature relative to the user's baseline temperature. If the user's temperature is outside of the normal range (e.g., significantly higher or lower than 0.0), the temperature factor can be highlighted (e.g., transitioned to a "pay attention" state) or otherwise generate a warning to the user.

[0089] In some aspects, system 200 may support techniques for determining a user's heart rate based on physiological data (e.g., movement data, temperature data) collected by a wearable device. In some aspects, ring 104, user device 106, and server 110 of system 200 may be configured to determine the user's heart rate data, regardless of whether the user is at rest or not. In particular, each component of system 200 may be used to determine the user's heart rate data based on the user's physiological data (e.g., movement, temperature). For example, each component of system 200 may determine the moment at which to measure PPG and, therefore, heart rate to ensure that the PPG and heart rate data meet quality thresholds based on the physiological data. Accordingly, these moments may be detected by utilizing a sensor on ring 104 of system 200.

[0090] For example, as previously described herein, the ring 104 of the system 200 may be worn by a user to collect data from the user including temperature, heart rate, movement, etc. The ring 104 of the system 200 may collect physiological data from the user based on arterial blood flow, venous blood flow, etc. The physiological data collected by the ring 104 may be used by the system 200 to determine when to collect PPG and heart rate data. The system 200 may selectively display all or a portion of the heart rate data on the GUI 275 of the user device 106.

[0091] In some cases, system 200 may select a channel (e.g., a set of one or more sensors) for collecting PPG data. For example, ring 104 may be configured with multiple PPG sensors, where a PPG sensor may be a pair of an emitter (e.g., an LED) and a receiver (e.g., a photodetector) that make up an optical path (e.g., a channel). In some cases, a PPG sensor may refer to one or more green LEDs, one or more red LEDs, one or more IR LEDs, or any other set of LEDs, and system 200 may select one or more PPG sensors from which to acquire PPG data based on signal quality associated with one or more of the PPG sensors.

[0092] For example, in some implementations, ring 104 may simultaneously measure the signal quality of each green LED channel and each IR channel, compare the signal qualities, and select the channel with the best signal quality to be used for heart rate measurement (e.g., select the green LED channel, select the IR channel). As another example, in other cases, ring 104 may measure the signal quality of the IR channel and use the IR channel for heart rate measurement if the signal quality of the IR channel is above a quality threshold, or use another channel (e.g., the green LED channel) if the signal quality of the IR channel is below the quality threshold.

[0093] In some cases, displaying the heart rate data may be based on comparing the heart rate data to a set of one or more thresholds prior to display to display the heart rate data based on the quality of the data. In some cases, determining the quality of the data may be performed according to an iterative (step-wise) comparison procedure. The procedure for determining the heart rate data may be further shown and described with reference to FIGS. 3-8.

[0094] 3 illustrates an example heart rate determination procedure 300 that supports techniques for heart rate detection according to aspects of the present disclosure. The heart rate determination procedure 300 may implement or be implemented by aspects of system 100, system 200, or both. For example, in some implementations, the heart rate determination procedure 300 may result in heart rate data (e.g., diurnal heart rate data, awake heart rate data) that can be displayed to a user via GUI 275 of user device 106, as shown in FIG.

[0095] As described in further detail herein, system 200 may be configured to estimate 320 a user's heart rate data based on the user's physiological data and PPG data. Thus, heart rate determination procedure 300 represents a procedure for determining a user's heart rate data, such as circadian heart rate data, awake heart rate data, and non-resting heart rate data, based on the user's physiological data and PPG data. Thus, the wearable device may detect a user's heart rate throughout a day, throughout the duration of time the user is awake, throughout the duration of time the user is active (i.e., not resting), or combinations thereof, in accordance with heart rate determination procedure 300. For example, at 305, system 200 may sample the user's motion data and temperature data. Then, at 310, system 200 may detect a moment to acquire a PPG based on the acquired motion data and temperature data. At 315, based on the detection of the moment to acquire a PPG, system 200 may sample the PPG and evaluate the PPG signal. At 320, based on the signal quality of the PPG signal, system 200 may estimate the user's heart rate. In some cases, system 200 may determine or estimate the user's heart rate data based on the user's heart rate data and / or PPG data collected by ring 104. In other cases, ring 104 may determine or estimate the user's heart rate data through other sensors, such as an accelerometer, a temperature sensor, an LED (e.g., an infrared LED, a green LED, a red LED, a yellow LED), etc.

[0096] At 305, a wearable device (e.g., system 200, an element of system 200, e.g., ring 104 or user device 106) may sample the user's motion data, temperature data, or both. For example, the wearable device may include one or more temperature sensors (e.g., temperature sensor 240 depicted in FIG. 2) that the wearable device can use to detect the user's temperature data. Specifically, the wearable device may detect temperature data of the user's skin, body, etc. (rather than the ambient temperature around the user). Concurrently (e.g., simultaneously) with acquiring the temperature data, or at a different time, the wearable device may acquire motion data associated with the user. For example, the wearable device may include one or more motion sensors (e.g., motion sensor 245 depicted in FIG. 2) that the wearable device can use to detect the user's motion data. In some cases, motion data can refer to acceleration data. In such cases, the motion sensor of the wearable device can refer to an accelerometer (e.g., a three-dimensional (3D) accelerometer) that can detect the user's acceleration.

[0097] At 310, a wearable device (e.g., system 200, an element of system 200, e.g., ring 104 or user device 106) may detect moments to acquire a PPG. In some cases, it may be advantageous for the wearable device to detect moments to acquire a PPG rather than continuously acquiring the PPG. For example, by acquiring a PPG over a set of discrete moments rather than continuously, the wearable device can reduce power consumption, conserve battery power, etc. Because the wearable device may be limited to acquiring a PPG signal during a series of moments, to ensure the wearable device acquires high-quality PPG data, the wearable device may be configured to detect moments when the PPG signal is likely to meet a quality threshold.

[0098] For example, detecting the appropriate moment may be based on an amount of time (e.g., the amount of time since the most recent heart rate measurement), physiological data of the user (e.g., temperature data, movement data), or a combination thereof. In some cases, the wearable device may determine or set a condition, such as a time interval, for detecting a PPG moment (e.g., the moment to start acquiring PPG). For example, the wearable device may determine an interval of X minutes or set such an interval otherwise. In some cases, the wearable device may detect a PPG moment according to the interval, such as every X minutes. It should be understood that the interval need not be limited to minutes, but may instead be in units of milliseconds, seconds, hours, etc. In some cases, the wearable device may detect a PPG moment based on a set of conditions, for example, a time interval and physiological data of the user. In some cases, the wearable device may detect a PPG moment based on reaching the end of the interval (e.g., after X minutes have passed) and based on one or more physiological conditions meeting a quality threshold. For example, every X minutes (e.g., according to an interval), the wearable device may determine whether one or more physiological conditions satisfy a quality threshold. If one or more physiological conditions satisfy the quality threshold, the wearable device may detect the end of the interval as the moment to acquire a PPG. If one or more physiological data do not satisfy the quality threshold, the wearable device may decide not to acquire a PPG at the end of the interval. In either case, after another X minutes (or after another suitable period or interval), the wearable device may again determine whether one or more physiological conditions satisfy a threshold to detect a PPG moment, etc. In some cases, the interval X may be equal to 5 minutes.

[0099] In some cases, the wearable device may be configured with a maximum amount of time that the wearable device will wait between PPG measurements. For example, the wearable device may determine or otherwise configure a maximum time equal to Y minutes, where Y is greater than X. Thus, if the wearable device does not detect a PPG acquisition moment within Y minutes, the wearable device may determine to acquire a PPG (e.g., regardless of physiological condition quality). In some cases, the maximum time Y may be equal to 10 minutes. In such a case, the system 200 may be configured to sample the PPG and / or determine a heart rate measurement of the user at least every 10 minutes. It should be understood that the maximum time Y need not be limited to minutes, but may instead be in units of milliseconds, seconds, hours, etc. In some cases, the wearable device may determine to acquire a PPG at all times (e.g., continuously).

[0100] The wearable device may acquire PPG data based on the detected instant. The wearable device may acquire PPG data via a PPG system (e.g., PPG system 235). For example, the wearable device may begin sampling PPG at the beginning of the detected instant and continue acquiring PPG data for a duration of Z minutes. In some cases, the wearable device may determine or receive an indication of the duration for acquiring PPG data or specify a preset duration. For example, the duration of Z minutes, or an indication to stop PPG sampling, may be determined by a physiological signal (e.g., movement or temperature) or may be variously determined based on the acquired heart rate value satisfying a quality threshold. In some cases, the duration of Z minutes may be related to an interval of X minutes. For example, the duration of Z minutes may be shorter than the interval of X minutes. In some cases, the PPG duration Z may be equal to 1 minute (e.g., system 200 samples PPG data for 1 minute). The PPG duration Z may not be limited to minutes and may instead be in units of milliseconds, seconds, hours, etc.

[0101] At 315, the wearable device (e.g., system 200, an element of system 200, e.g., ring 104 or user device 106) may evaluate a PPG signal acquired during the detected moment. In some cases, evaluating the PPG signal may include determining a quality of the PPG signal. In some cases, the wearable device may determine whether the PPG signal satisfies at least a quality threshold. In some cases, the wearable device may determine whether to use the PPG signal to determine the heart rate based on the PPG signal satisfying the threshold. In some cases, the wearable device may determine whether a portion of the PPG signal satisfies a quality threshold. The wearable device may use the portion of the PPG signal that satisfies the quality threshold to determine the heart rate.

[0102] In some implementations, the wearable device 104 may select a channel (e.g., a set of one or more sensors) for collecting PPG data. For example, the wearable device 104 may be configured with multiple PPG sensors, where a PPG sensor may be a pair of an emitter (e.g., an LED) and a receiver (e.g., a photodetector) that forms an optical path (e.g., a channel) for PPG measurement. In some cases, a PPG sensor may refer to one or more green LEDs, one or more red LEDs, one or more IR LEDs, or any other set of LEDs, and the wearable device may select one or more PPG sensors from which to acquire PPG data based on signal quality associated with one or more of the PPG sensors. For example, the wearable device may select one or more sets of PPG sensors for sampling PPG data based on the one or more sets of PPG sensors being associated with the highest signal quality and / or meeting a signal quality threshold.

[0103] At 320, a wearable device (e.g., system 200, an element of system 200, e.g., ring 104 or user device 106) may estimate the user's heart rate based on the acquired PPG signal. Each time the user's heart beats, blood is pumped through the arteries in the hand and fingers. A PPG sensor (of PPG system 235 described with reference to FIG. 2) in the wearable device can detect these changes in blood flow and volume using light reflection and absorption. With each heartbeat, the arteries in the fingers expand and contract. By shining light on the skin, e.g., with an LED, changes in reflected light from the fluctuating volume of red blood cells in the arteries are taken into account. From this, the PPG can represent these changes in blood flow through a visual waveform that represents the user's cardiac activity and, therefore, heart rate. In some cases, the wearable device may determine the user's heart rate based on the PPG signal meeting a quality threshold, or based on portions of the PPG signal meeting a quality threshold. For example, the wearable device may determine one or more portions of the PPG signal that accurately represent the user's heart rate.

[0104] A wearable device may be configured to perform all or part of the heart rate determination procedure 300 to determine a user's heart rate data. In some cases, the wearable device may obtain diurnal heart rate data, awake heart rate data, heart rate data whether the user is resting or not, or any combination thereof. Thus, the wearable device may perform one or more steps of the heart rate determination procedure 300 based on the time of day, such as within a 24-hour window of time, based on the user being awake, etc. In some cases, the wearable device may perform one or more steps of the heart rate determination procedure 300 to obtain the user's heart rate data at all times (e.g., regardless of the time of day and whether the user is awake or not). Additionally or alternatively, each step and procedure of the heart rate determination procedure 300 may be performed by any of the components of the system 200, such as the ring 104, the user device 106, the server 110, or any combination thereof.

[0105] 4 illustrates an example of a heartbeat determination procedure 400 that supports techniques for heartbeat detection according to aspects of the present disclosure. The heartbeat determination procedure 400 may implement or be implemented by aspects of the system 100, the system 200, the heartbeat determination procedure 300, or a combination thereof. For example, in some implementations, the heartbeat determination procedure 400 may result in heartbeat data (e.g., circadian heartbeat data, awake heartbeat data) that can be displayed to a user via the GUI 275 of the user device 106, as shown in FIG. 2. In some cases, the heartbeat determination procedure 400 may be related to all or a portion of the heartbeat determination procedure 300, or vice versa.

[0106] As described herein, a system such as system 200, or a portion of system 200, such as a wearable device (e.g., ring 104), can determine a user's heart rate based on a set of conditions, which can refer to one or more thresholds, physiological data, PPG data, or a combination thereof. In some cases, the wearable device may detect a user's heart rate throughout the day, or throughout the duration of time the user is awake, or throughout the duration of time the user is active (i.e., not resting), or a combination thereof, according to a heart rate determination procedure 400.

[0107] At 405, the wearable device may measure motion data associated with the user. In some cases, the wearable device may measure motion data continuously or periodically (e.g., according to a periodicity). In some cases, the wearable device may measure motion for a set duration, and the wearable device may be set or receive an indication of the set duration, or may determine the set duration. To measure the motion data, the wearable device may utilize one or more sensors on the wearable device (e.g., motion sensor 245). In some cases, the motion data may refer to an accelerometer (e.g., a 3D accelerometer) that can detect the user's acceleration, such as 3D acceleration. In some cases, the accelerometer may measure the user's acceleration as 50 Hz or other frequencies.

[0108] At 410, the wearable device may measure temperature data associated with the user. In some cases, the wearable device may measure temperature data continuously or periodically (e.g., according to a periodicity). In some cases, the wearable device may measure the temperature for a set duration, and the wearable device may be set with or receive an indication of the set duration, or may determine the set duration. For example, the wearable device may measure the user's temperature once every minute (1 temperature measurement / minute). To measure the temperature data, the wearable device may utilize one or more temperature sensors on the wearable device (e.g., temperature sensor 240).

[0109] At 415, the wearable device may preprocess the motion data. For example, the wearable device may preprocess 3D acceleration data (e.g., raw data) to obtain processed or velocity data. In some cases, one or more of steps 405, 410, and 415 may be performed in parallel. For example, the wearable device may acquire temperature data and motion data in parallel and then preprocess the motion data. In some cases, the wearable device may acquire motion data and process the motion data in parallel with acquiring temperature data.

[0110] At 420, once the athletic data has been preprocessed, the preprocessed athletic data and temperature data are input to a feature extraction module. The feature extraction module may determine one or more features for the temperature data, the preprocessed athletic data, or a combination thereof. For example, the feature extraction module may determine the standard deviation, variance, range, mean, etc., of the temperature data, the preprocessed athletic data, or a combination thereof. In some cases, the feature extraction module may determine one or more features for a time window of the acquired data, such as a three-second window. The wearable device may be configured with the time window to use to determine the features, or may otherwise determine such a time window.

[0111] At 425, the wearable device may calculate a condition quality index (CQI) associated with the temperature data, the motion data, or a combination thereof. To calculate the CQI, the wearable device may use the temperature data, the preprocessed motion data, one or more features of the data (e.g., the one or more features determined in 420), or a combination thereof. In some aspects, the CQI metric may indicate the relative quality of the physiological data collected over a given time interval for determining a heart rate measurement. In other words, the CQI metric for a given time interval may indicate whether the physiological data collected within each time interval is good for performing a heart rate measurement. In some cases, the wearable device may determine a single CQI to reflect the quality of the temperature data and the motion data. In some other cases, the wearable device may determine a CQI for the motion data and a separate CQI for the temperature data. In some cases, the wearable device may calculate the CQI constantly or periodically. For example, the wearable device may calculate a CQI value every three seconds. The wearable device may use one or more CQI calculations as an indication of the quality of the temperature data, the motion data, or both acquired by the wearable device.

[0112] In some aspects, system 200 may input the features determined at 420 to a classifier to generate a CQI metric. For example, system 200 may input the features to a classifier (e.g., a machine learning classifier, a neural network), where the classifier is configured to determine one or more CQI metrics based on the received features. For example, system 200 can determine mean motion and mean temperature at 420 and input these features to a classifier, where the classifier determines a CQI metric based on the mean motion and mean temperature.

[0113] At 430, the wearable device may execute PPG sampling logic to determine whether to initiate PPG sampling. In some cases, the wearable device may be configured to minimize power consumption of the wearable device. Accordingly, the wearable device may limit PPG recording. The wearable device may determine whether to record PPG based on one or more conditions, such as periodicity (e.g., latency, interval), CQI, or a combination thereof. In some cases, system 200 may determine whether to perform PPG sampling based on the CQI metric calculated in 425 satisfying (or not satisfying) some threshold metric value. For example, in some cases, system 200 may determine the CQI metric based on the features extracted in 425, including average motion and average temperature. In such a case, system 200 may calculate the CQI metric and determine that the CQI metric satisfies the threshold metric value based on the average motion being below the motion threshold and the average temperature being above the temperature threshold.

[0114] Additionally or alternatively, the underlying condition for determining whether to initiate PPG may be periodicity. For example, the wearable device may be configured to evaluate whether to initiate PPG every X minutes, e.g., every 5 minutes. In other words, system 200 may evaluate whether to perform PPG sampling every 5 minutes. To evaluate whether to initiate PPG sampling at the X-minute mark, the wearable device may evaluate data being acquired by the wearable device, such as temperature data and motion data. For example, the wearable device may evaluate the data to ensure that the limited PPG data acquired by the wearable device is high-quality PPG data. High-quality PPG data may be based on the user's movement, the user's temperature, the position of the wearable device on the user, etc. For example, high-quality PPG data may be acquired when the user's movement is below the motor threshold, when the user's skin temperature is above the temperature threshold, when the position of the wearable device on the user is such that the wearable device is acquiring accurate data (e.g., motion data, temperature data), or a combination thereof.

[0115] For example, the temperature data (e.g., skin temperature) may relate to blood circulation, such as blood circulation in a body part where the wearable device is located (e.g., a finger if the wearable device is a ring 104). Ambient temperature, exercise, etc. may affect blood circulation. In some cases, blood circulation and temperature may be directly correlated, so that when blood circulation decreases, skin temperature may decrease. If the skin temperature is below a threshold, this may indicate that the wearable device may not be able to accurately detect blood circulation and therefore may not be able to obtain an accurate pulse reading. In some cases, the wearable device may be set or specify a reference temperature or reference temperature range for the user. The wearable device may compare the temperature measurement (instantaneous temperature measurement) to the reference temperature (or range). For example, the wearable device may compare the instantaneous temperature measurement with a lower threshold of a reference range; if the instantaneous temperature is below the lower threshold, the instantaneous temperature may be too low to obtain accurate pulse data.

[0116] Thus, every X minutes, the wearable device may evaluate temperature data, motion data, CQI, or a combination thereof. For example, if the amount of time elapsed since the last evaluation (e.g., a wait time) is greater than or equal to X minutes and the CQI is greater than or equal to a CQI threshold, the wearable device may start recording a PPG. However, if the CQI does not satisfy the CQI threshold, the wearable device may not start recording (e.g., refrain from sampling the PPG). In some cases, the CQI threshold may be equal to zero. Thus, the wearable device may use a CQI calculation to determine the moment to acquire a PPG. In some cases, the wearable device may use a set of CQI calculations to determine whether to start sampling a PPG. Thus, the wearable device may determine whether to start sampling a PPG by comparing each CQI in the set to a CQI threshold, or by comparing the average CQI of the set to a CQI threshold, etc.

[0117] In some cases, the wearable device may be configured with a maximum amount of time (e.g., Y minutes) that the wearable device can go without recording a PPG and / or performing a heart rate measurement. Y is greater than X. In some cases, Y may be equal to 10 minutes. In other words, system 200 may be configured to sample PPG and / or obtain a heart rate measurement of the user at least every 10 minutes. For example, if the time since the last PPG recording (or last performed heart rate measurement) is Y minutes or more, the wearable device may begin recording a PPG regardless of the CQI. The initiation of a PPG due to reaching Y minutes may be referred to as a mandatory measurement. In some cases, a mandatory measurement may be treated differently from a PPG measurement obtained based on the CQI satisfying a CQI threshold at X minutes. For example, a mandatory measurement may be evaluated additionally, compared to a quality threshold, weighted less than a non-mandatory measurement, etc.

[0118] The wearable device may be configured to record PPG for a defined time interval, such as Z minutes. In some cases, Z may equal 1 minute. Thus, at 435, the wearable device may begin PPG recording according to the PPG sampling logic for Z minutes. The wearable device may sample the PPG at a set of conditions, such as a frequency (e.g., 50 Hz).

[0119] In some cases, a wearable device may sample a user's PPG data using one or more pairs of PPG sensors, each pair of PPG sensors including at least one LED and at least one photodetector. For example, a wearable device may include a first pair of PPG sensors including a first LED and a first photodetector, and a second pair of PPG sensors including a second LED and a second photodetector. In other words, a wearable device may include two separate "channels" for acquiring PPG data (e.g., two separate PPG signals from each of two pairs of sensors). In some cases, a wearable device may sample the PPG sensors using the first pair of PPG sensors and the second pair of PPG sensors simultaneously. Additionally or alternatively, a wearable device may sample PPG data using the first pair of PPG sensors and the second pair of PPG sensors sequentially. For example, a wearable device may sequentially control the active states of the first pair of PPG sensors and the second pair of PPG sensors (e.g., the first pair is in an active state when the second pair is in an inactive state, and vice versa). Thereafter, different sets / pairs of PPGs can be activated, each improving the quality and accuracy of the PPG signal and reducing interference, resulting in more accurate heart rate measurements.

[0120] At 440, upon sampling the PPG, the wearable device may reset a wait time so that the wearable device can evaluate the PPG sampling logic again in another X minutes. Thereafter, or in parallel, at 445, the wearable device may preprocess the PPG data. For example, the wearable device may filter the PPG data to remove erroneous samples. In some cases, processing the PPG data may include selecting PPG data obtained from a particular sensor (e.g., green LED, infrared LED, red LED, yellow LED) or set of PPG sensors, averaging PPG data obtained across multiple sensors, etc.

[0121] For example, in some cases, a wearable device may monitor PPG signals from multiple sets of sensors. For example, system 200 may determine a first PPG signal from a first set of PPG sensors and a PPG signal from a second set of PPG sensors, each set of PPG sensors including at least one LED and at least one photodetector. In the context of a ring wearable device, each of the sensors (e.g., LEDs, photodetectors) used for PPG sampling may be positioned at a different radial position along the inner circumference of the ring. In this example, the first or second PPG signal from one or more of the multiple PPG sets may be more reliable than PPG signals obtained from others of the multiple sensors, depending, for example, on the location of the sensor around the wearable device relative to the user, the relative quality of skin contact with each sensor or LED, etc. For example, a sensor located on the underside (e.g., palm side) of a user's finger may provide more accurate PPG data than a sensor located above the finger bone (e.g., on the back side of the finger). As another example, the relative positioning of the wearable devices may result in lower quality PPG data compared to a second sensor due to less skin contact with one first sensor compared to a second sensor.

[0122] Thus, in some cases, the wearable device may determine whether to acquire and / or utilize PPG data collected from a particular sensor or whether to combine PPG data acquired across multiple sets of PPG sensors using various mathematical operations, e.g., averaging operations, weighted averaging operations, etc. In other words, system 200 may combine multiple PPG signals collected by multiple sets of PPG sensors to generate a “synthetic” PPG signal that is used to determine a heart rate measurement of the user.

[0123] In some implementations, as described in further detail with reference to FIGS. 5-7 , the wearable device 104 may select a channel (e.g., a set of one or more sensors) for collecting PPG data based on signal quality, where signal quality may be affected based on the location of the PPG sensors on the user, the user's activity, the user's body temperature, etc. For example, the wearable device may be configured with multiple PPG sensors, such as one or more green LEDs, one or more red LEDs, one or more IR LEDs, or any other set of LEDs, and may select one or more PPG sensors for acquiring PPG data based on signal quality associated with one or more of the PPG sensors. For example, the wearable device may select one or more sets of PPG sensors for sampling PPG data based on the one or more sets of PPG sensors being associated with the highest signal quality and / or satisfying a signal quality threshold.

[0124] In some cases, the signal quality criteria used to select a PPG sensor may be based on a use case. The signal quality criteria may be based on one or more parameters, which may include a user illness (e.g., pneumonia), a user disease (e.g., apnea, atrial fibrillation (AFib)), a current workout, a previous workout, or a planned future workout. For example, one or more of the parameters may relate to different types of signals, signal shapes, etc., and thus the signal quality criteria may vary based on one or more parameters. Thus, the device may identify one or more parameters (e.g., use cases) to apply and determine the signal quality criteria, if any, to use to select one or more PPG sensors.

[0125] The wearable device may select a channel in any combination and / or order with any of the steps described herein.

[0126] At 450, the wearable device may apply an algorithm to the PPG data. In some cases, the algorithm may be called an S-pulse algorithm. In some cases, the algorithm may output one or more measurements such as an IBI value (e.g., ibiCorrected, ibiQuality, ibi, timestamp of the ibi value (tibi)).

[0127] At 455, simultaneously with or at a different time from applying the algorithm to the PPG at 450, the wearable device may calculate a PPG quality indicator (PQI) (e.g., a PPG quality metric) associated with the PPG data, where the PQI may provide an indication of the quality of the PPG data in whole or in part. In other words, the PPG quality metric may indicate the relative quality of the sampled PPG data. In some cases, system 200 may determine the PPG quality metric (e.g., PQI) by comparing the sampled PPG data at 435 to other PPG data previously collected for the same user, to PPG data collected from other users, or both. In other words, system 200 may determine the relative quality of the sampled PPG data (e.g., the PQI of the sampled PPG data) by comparing the sampled PPG data to reference PPG data sampled from the user and / or other users.

[0128] At 460, one or more outputs of the algorithm (e.g., ibiQuality), the CQI, and the PQI determined at 450 may be input to a cardiac output module. The wearable device may use the cardiac output module to select a cardiac value for the user based on the PPG data satisfying a quality threshold. For example, the wearable device may filter out erroneous cardiac data. In other words, system 200 may be configured to determine a cardiac measurement for the user based on a PPG quality metric (e.g., PQI) satisfying a threshold PPG metric value. By evaluating the determined PPG quality metric with respect to some threshold PPG metric value, system 200 can ensure that the sampled PPG data can provide an accurate cardiac measurement. One or more aspects of the cardiac output selection at 460 may be described in further detail with reference to FIG. 8 .

[0129] In some cases, selecting a heart rate value may be based on comparing the heart rate data to a set of one or more thresholds to display the heart rate data based on the quality of the data, as described in further detail with reference to FIG. 8. In some cases, determining the quality of the data may be performed according to an iterative (e.g., stepwise) comparison procedure. In some cases, each heart rate data point (or a series of heart rate data points) may be labeled to indicate the quality of the heart rate data point.

[0130] At 465, the time series of heart rate data may be displayed in an application (e.g., GUI 275). Presentation of heart rate data is further shown and described below with reference to FIG.

[0131] In some cases, steps 405-455 may be performed by firmware of a wearable device, such as ring 104. In some cases, the wearable device may communicate one or more results of step 405 with a device associated with the wearable device, such as a user device (e.g., user device 106). Step 460 may be performed by the wearable device, the user device, or a combination thereof. Step 465 may be performed by the wearable device, the user device, an application (e.g., an application on the user device), or a combination thereof.

[0132] FIG. 5 illustrates an example of a channel selection procedure 500 that supports techniques for heartbeat detection according to aspects of the present disclosure. The channel selection procedure 500 may implement or be implemented by aspects of system 100, system 200, heartbeat determination procedures 300 and 400, or a combination thereof. For example, in some implementations, the channel selection procedure 500 may result in the selection of one or more PPG sensors to use to sample PPG data, which may be used to determine heartbeat data (e.g., circadian heartbeat data, awake heartbeat data) that may be displayed to a user via GUI 275 of user device 106 as shown in FIG. 2 . In some cases, the channel selection procedure 500 may relate to all or part of the heartbeat determination procedures 300 or 400, or vice versa. For example, the channel selection procedure 500 may be implemented at steps 430 and / or 435 described with reference to FIG. 4 .

[0133] As described herein, a wearable device may use one or more PPG sensors (e.g., channels, LEDs) to sample PPG data for determining a user's heart rate data. For example, in some cases, a wearable device may be configured to acquire PPG data using one or more PPG sensors. For example, a wearable device may be configured to acquire PPG data using the same PPG sensor or the same set of PPG sensors to acquire PPG data each time a heart rate is measured. For example, a wearable device may be configured to sample PPG data using a green LED and photodetector, such as green LED channel 1 (e.g., GRE1_PD1) of 505-a including a first green LED and a first photodetector, or green LED channel 2 (e.g., GRE2_PD2) of 505-b including a second green LED and a second photodetector, or a combination thereof. In some cases, a wearable device may be configured to acquire PPG data using one or more green LEDs. In particular, green LEDs may provide the most accurate data (e.g., compared to other LED types) under certain conditions (e.g., ideal conditions).

[0134] However, in some cases, the performance of one or more PPG sensors (e.g., green LEDs) configured to acquire PPG data may degrade and / or fall below a threshold. Additionally or alternatively, one or more other sensors (e.g., red LEDs, IR LEDs, other colored LEDs, e.g., yellow LEDs) of the wearable device may perform as well as or better than the green LEDs. For example, in some cases, the signal quality of a first PPG sensor may be more affected by environmental parameters than a second PPG sensor. Environmental parameters may include ring rotation, ring fit (e.g., which may change over time, such as over the course of a day and / or over months or years), the state of the wearable device and / or its sensors (e.g., newer devices may perform differently from older devices), the temperature of the user's skin, the ambient temperature, etc. For example, under ideal conditions (e.g., low movement, warm skin temperature, and PPG sensors positioned on the palmar sides of the user's fingers), a green LED may produce more accurate PPG data than an IR LED.

[0135] However, in less ideal conditions or as conditions change, green LEDs may not perform as well as IR LEDs (e.g., IR LEDs can be more robust and substantial). For example, IR diodes may perform better compared to green LEDs, e.g., during vigorous movement (e.g., during exercise) and / or when skin temperature is low. Additionally or alternatively, some PPG sensors may be more bothersome to the user than other PPG sensors. For example, during use, LEDs that utilize the visible light spectrum (e.g., green LEDs) may be visible to the user, while LEDs that do not utilize the visible light spectrum (e.g., IR LEDs) are invisible to the user.

[0136] Therefore, it may be beneficial for the wearable device to be able to flexibly switch sensors and / or sensor types (e.g., green LEDs vs. IR LEDs vs. red LEDs, etc.) to sample PPG data used for heart rate measurement. For example, the wearable device may select one or more sensors for acquiring PPG data used for heart rate measurement based on signal quality associated with one or more of the sensors. The signal quality threshold may be the number of pulses detected per time interval, a PPG quality index, other signal quality index, etc. For example, the wearable device may select one or more sets of sensors for sampling PPG data based on the one or more sets of sensors being associated with the highest signal quality and / or satisfying a signal quality threshold. Thus, the wearable device may acquire PPG data of improved quality and reliability. Upon selecting one or more sets of PPG sensors, the wearable device samples and processes the PPG data (at 510) and performs pulse detection (515), as described in more detail herein.

[0137] FIG. 6 illustrates an example of a channel selection procedure 600 supporting techniques for heartbeat detection according to aspects of the present disclosure. The channel selection procedure 600 may implement or be implemented by aspects of system 100, system 200, heartbeat determination procedures 300 and 400, channel selection procedure 500, or a combination thereof. For example, in some implementations, the channel selection procedure 600 may result in the selection of one or more PPG sensors to use to sample PPG data, which may be used to determine heartbeat data (e.g., circadian heartbeat data, awake heartbeat data) that may be displayed to a user via GUI 275 of user device 106 as shown in FIG. 2 . In some cases, the channel selection procedure 600 may relate to all or part of the heartbeat determination procedures 300 or 400, or vice versa. For example, the channel selection procedure 600 may be implemented at steps 430 and / or 435 described with reference to FIG. 4 .

[0138] As described herein, the procedure for determining heart rate may include selecting a channel (e.g., a sensor from which PPG data can be obtained) for sampling PPG data. For example, a wearable device may be configured with multiple PPG sensors, such as one or more green LEDs (e.g., green LED channels 1 and 2), one or more red LEDs, one or more IR LEDs (e.g., IR LED channels 1-4), or any other set of LEDs (e.g., other colored LEDs, such as yellow LEDs). For example, a wearable device may include any number of IR LEDs, such as two, and any number of photodetectors, such as two, where a combination of an IR LED and a photodetector may be referred to as a channel. Thus, IR channel 1 may correspond to a first IR LED and a first photodetector (e.g., IR1_PD1), IR channel 2 may correspond to a first IR LED and a second photodetector (e.g., IR1_PD2), IR channel 3 may correspond to a second IR LED and a first photodetector (e.g., IR12_PD1), and IR channel 4 may correspond to a second IR LED and a second photodetector (e.g., IR12_PD2).

[0139] Similarly, a wearable device may include any number of green LEDs, such as one, and any number of photodetectors, such as one, and the combination of a green LED and a photodetector may be referred to as a channel. In some cases, green LED and photodetector pairs may not be interchangeable. Thus, green LED channel 1 may correspond to a first green LED and a first photodetector (e.g., GRE1_PD1), and green LED channel 2 may correspond to a second green LED and a second photodetector (e.g., GRE2_PD2). In some cases, the wearable device may be configured to select one or more PPG sensors for acquiring PPG data based on signal quality associated with one or more of the PPG sensors. In other words, the wearable device may be configured to select which channel is used to collect PPG data used for heart rate measurement.

[0140] For example, a wearable device may be configured to analyze a set of one or more PPG sensors (e.g., some or all of the PPG sensors configured for the wearable device). For example, the wearable device may acquire data from one or more PPG sensors. In some cases, as described with reference to FIG. 2 , the wearable device may acquire PPG data from one or more sensors based on a set of conditions (e.g., minimum latency, maximum latency, quality metric, sampling duration), which may be the same for each of the one or more PPG sensors or may differ among the one or more PPG sensors. For example, the wearable device may initiate PPG sampling for each PPG sensor of one or more PPG sensors when a minimum latency time has been reached since the last sampling and when the CQI is greater than a threshold. Additionally or alternatively, the wearable device may initiate PPG sampling for each PPG sensor of one or more PPG sensors when a maximum latency time has been reached since the last sampling (regardless of the CQI). In some cases, the wearable device may be configured to sample PPG data from each of one or more PPG sensors according to a sampling duration (e.g., 1 minute).

[0141] In some cases, the wearable device may be configured to sample PPG data at 605-a and 605-b (e.g., corresponding to green LED channels 1 and 2, respectively) and / or sample PPG data at 610-a through 610-b (e.g., corresponding to IR LED channels 1 through 4, respectively) according to a set of conditions. For example, in some implementations, the wearable device may be configured to sequentially activate / deactivate each of the green and IR channels to sample each channel at each of 605-a through 610-b.

[0142] The wearable device may perform a signal quality determination procedure at 615. At this time, the wearable device may determine (e.g., measure, calculate) the quality of the output (e.g., signal quality) from each PPG sensor from which the wearable device sampled data. For example, if the wearable device sampled data from one or more of 605-a and 605-b, the wearable device may perform signal quality determination for green LED channel 1 and green LED channel 2, respectively. If the wearable device sampled data from one or more of 610-a through 610-b, the wearable device may perform signal quality determination for IR LED channel 1 through IR LED channel 4. In some cases, the wearable device may sample data from all or some combination of 605-a, 605-b, 610-a, 610-b, 610-c, and 610-d.

[0143] In some cases, the wearable device may be configured to compare the signal quality of each PPG sensor to one or more signal quality thresholds and / or compare the signal quality of each PPG sensor to other determined signal qualities. At 620, the wearable device may select one or more PPG sensors associated with the highest signal quality. For example, the wearable device may be configured to select the top N sensors associated with the highest signal quality, where N can be any number greater than zero. Additionally or alternatively, the wearable device may select one or more PPG sensors that satisfy one or more signal quality thresholds. For example, the wearable device may select a PPG sensor if it satisfies a signal quality threshold and is associated with the highest signal quality. In another example, if a PPG sensor is associated with the highest signal quality but fails to satisfy the signal quality threshold, the wearable device may refrain from selecting the PPG sensor (e.g., refrain from performing a heart rate measurement).

[0144] In some cases, at 620, the wearable device may deactivate one or more PPG sensors, such as any PPG sensors that the wearable device does not activate. In other words, the wearable device may deactivate PPG sensors / channels that are not used for PPG collection and heart rate detection. Deactivating one or more PPG sensors may include turning off one or more sensors, transitioning one or more sensors to a standby state, etc. Deactivating one or more sensors may enable power conservation in the wearable device and may reduce user disturbance related to visible light that may be caused by one or more sensors remaining active. In some cases, such as for other non-PPG-related purposes, the wearable device may be configured to reactivate one or more deactivated PPG sensors, and / or one or more deactivated sensors may be configured to reactivate themselves according to a timer.

[0145] In some implementations, the wearable device (and / or other components of system 200) may perform the PPG channel selection procedure depicted in FIG. 6 each time heart rate data should be collected. Furthermore, in some implementations, the wearable device may be configured to implement a “feedback loop” to reevaluate channel quality even after a channel is selected. For example, the wearable device may initially select green LED channel 1 and use green LED channel 1 to collect PPG data to be used for heart rate measurement. However, in this example, conditions may subsequently change, such as the signal quality of green LED channel 1 deteriorating. In such a case, the wearable device may be configured to remeasure all or some of the channels at 605-a, 605-b, 610-a, 610-b, 610-c, and / or 610-d to reevaluate which channels should be used for heart rate measurement.

[0146] Thus, the wearable device can obtain PPG data of improved quality and reliability. Upon selecting a set of one or more PPG sensors, the wearable device can sample the PPG data, process the PPG data (at 625), and perform pulse detection (630), as described in more detail herein.

[0147] FIG. 7 illustrates an example of a channel selection procedure 700 that supports techniques for heartbeat detection according to aspects of the present disclosure. The channel selection procedure 700 may implement or be implemented by aspects of system 100, system 200, heartbeat determination procedures 300 and 400, channel selection procedures 500 and 600, or a combination thereof. For example, in some implementations, the channel selection procedure 700 may result in the selection of one or more PPG sensors to use to sample PPG data, which may be used to determine heartbeat data (e.g., circadian heartbeat data, awake heartbeat data) that may be displayed to a user via GUI 275 of user device 106 as shown in FIG. 2 . In some cases, the channel selection procedure 700 may relate to all or part of the heartbeat determination procedures 300 or 400, or vice versa. For example, the channel selection procedure 700 may be implemented at steps 430 and / or 435 described with reference to FIG. 4 .

[0148] As described herein, a wearable device may be configured to select one or more PPG sensors (e.g., channels) for acquiring PPG data based on signal quality. In some cases, a wearable device may include any number of IR LEDs, such as two, and any number of photodetectors, such as two, and the combination of an IR LED and a photodetector may be referred to as a channel. Thus, IR channel 1 may correspond to a first IR LED and a first photodetector (e.g., IR1_PD1), IR channel 2 may correspond to a first IR LED and a second photodetector (e.g., IR1_PD2), IR channel 3 may correspond to a second IR LED and a first photodetector (e.g., IR12_PD1), and IR channel 4 may correspond to a second IR LED and a second photodetector (e.g., IR12_PD2). Similarly, a wearable device may include any number of green LEDs, such as one, and any number of photodetectors, such as one, and the combination of a green LED and a photodetector may be referred to as a channel. In some cases, the green LED and photodetector pairs may not be interchangeable. Thus, green LED channel 1 may correspond to a first green LED and a first photodetector (e.g., GRE1_PD1), and green LED channel 2 may correspond to a second green LED and a second photodetector (e.g., GRE2_PD2).

[0149] A wearable device may be configured to analyze a set of one or more PPG channels (e.g., some or all of the PPG sensors configured for the wearable device). For example, the wearable device may acquire data from one or more PPG sensors. In some cases, the wearable device may be configured with a default PPG sensor (e.g., a particular PPG sensor) or default PPG sensor type (e.g., one or more IR LEDs, one or more green LEDs, etc.) to use for sampling PPG data. For example, the wearable device may be configured to use one or more IR sensors, such as IR LED channels 1-4, as a default for PPG sampling as long as the one or more IR sensors meet a signal quality threshold.

[0150] Thus, the wearable device may sample PPG data from one or more IR channels at 705-a, 705-b, 705-c, and 705-d. At 710, the wearable device may determine signal quality for each of IR channels 1-4. In some cases, the wearable device may be configured to compare the signal quality of each IR sensor to one or more signal quality thresholds and / or compare the signal quality of each IR sensor to the signal quality of the other IR sensors. For example, at 715, the wearable device may determine whether one or more of IR channels 1-4 meet a signal quality higher than a threshold. If so, the wearable device may select one or more of the IR channels for acquiring PPG data. The wearable device may select one or more IR channels if those IR channels meet the signal quality threshold. In some cases, the wearable device may select one or more IR channels associated with the highest signal quality. For example, the wearable device may be configured to select the top N IR sensors associated with the highest signal quality. where N can be any number greater than zero. For example, the wearable device may select an IR sensor if it meets a signal quality threshold and the IR sensor is associated with the highest signal quality. Upon selecting one or more IR sensors, the wearable device samples the PPG data, processes the PPG data (at 720), and performs pulse detection (725), as described in further detail herein.

[0151] If none of IR channels 1-4 meets the signal quality threshold, the wearable device may analyze one or more other channels, such as green LED channels 1 and 2. In some cases, the wearable device may first activate one or more other channels and sample PPG data from one or more other channels. For example, all other channels other than the default channel (e.g., the IR channel) may be deactivated and / or refrain from sampling during steps 705-710. Thus, the wearable device may sample PPG data via green LED channel 1 at 730-a and via green LED channel 2 at 730-b. At 735, the wearable device may determine signal quality associated with each of green LED channels 1 and 2. At 740, the wearable device may be configured to select the top N green LED channels associated with the highest signal quality, where N can be any number greater than zero. For example, the wearable device may select the green LED sensor associated with the highest signal quality.

[0152] Additionally or alternatively, in some cases, the wearable device may compare one or more of the green LED channels to a signal quality threshold. In some cases, the wearable device may use one or more of the green LED channels based on one or more green LED channels meeting the threshold. In some cases, if multiple green LED channels meet the quality threshold, the wearable device may select one or more green LED channels based, for example, on the highest signal quality. In some cases, if none of the green LED channels meet the quality threshold, the wearable device may continue to use one or more of the green LED channels. In some cases, if none of the green LED channels meet the quality threshold, the wearable device may restart the channel selection procedure at 705.

[0153] In some cases, upon determining that none of IR channels 1-4 meets the signal quality threshold, the wearable device may deactivate one or more of the IR channels. Deactivating one or more IR channels may include turning off one or more IR sensors, transitioning one or more IR sensors to a standby state, etc. In some cases, such as for other non-PPG-related purposes, the wearable device may be configured to reactivate one or more deactivated IR sensors, and / or one or more deactivated IR sensors may be configured to reactivate themselves according to a timer.

[0154] As previously described herein, the wearable device (and / or other components of system 200) may perform the PPG channel selection procedure depicted in FIG. 6 each time heart rate data should be collected. Furthermore, in some implementations, the wearable device may be configured to implement a “feedback loop” to reevaluate channel quality even after a channel is selected. For example, the wearable device may initially select IR channel 1 and use it to collect PPG data used for heart rate measurement. However, in this example, conditions may subsequently change, such as the signal quality of IR channel 1 deteriorating. In such a case, the wearable device may be configured to remeasure all or some of the IR channels at 705-a, 705-b, 705-c, and / or 705-d to reevaluate which channels should be used for heart rate measurement. As another example, upon determining that the signal quality of IR channel 1 has degraded, the wearable device may revert to measuring the green LED channel at 730-a and / or 730-b to determine whether the green LED channel is likely to exhibit better signal quality (and therefore a more accurate heart rate measurement) compared to the IR channel.

[0155] Thus, the wearable device can obtain PPG data of improved quality and reliability. Upon selecting a set of one or more PPG sensors (e.g., IR sensors or green LED sensors), the wearable device can sample the PPG data, process the PPG data (at 720), and perform pulse detection (725), as described in more detail herein.

[0156] In some implementations, selecting one or more PPG sensors with reference to the channel selection procedures described with reference to Figures 5-7 may be subject to changing conditions, and the wearable device may therefore be configured to perform all or part of one or more of the channel selection procedures (e.g., a feedback loop) to ensure signal quality.

[0157] As previously mentioned herein, in some cases, the signal quality criteria (e.g., signal quality thresholds) used to select a PPG sensor may be based on a use case, e.g., a user illness (e.g., pneumonia), a user disease (e.g., apnea, atrial fibrillation (AFib)), a current workout, a previous workout, or a planned future workout, etc. In this regard, the signal quality thresholds used throughout the channel selection procedure 700 may be selected / adjusted based on one or more use cases or parameters associated with the user, where the use case, parameters / characteristics, or both may be determined based on collected physiological data, user input (e.g., via a GUI on the user device), or both.

[0158] FIG. 8 illustrates an example of a heartbeat determination procedure 800 that supports techniques for heartbeat detection according to aspects of the present disclosure. The heartbeat determination procedure 800 may implement or be implemented by aspects of system 100, system 200, heartbeat determination procedures 300 and 400, channel selection procedures 500, 600, and 700, or a combination thereof. For example, in some implementations, the heartbeat determination procedure 800 may result in heartbeat data (e.g., circadian heartbeat data, awake heartbeat data) that can be displayed to a user via GUI 275 of user device 106 as shown in FIG. 2. In some cases, the heartbeat determination procedure 800 may relate to all or part of the heartbeat determination procedures 300 and 400, or vice versa. For example, the heartbeat determination procedure 800 may include the heartbeat determination procedure 400 described with reference to FIG. 4o.

[0159] As described herein, the wearable device may use the PPG data to determine the user's heart rate data. The quality of the heart rate data may be based on signal quality from one or more sensors of the wearable device, which may be affected by ring rotation, ring fit (e.g., which may change over time, such as over the course of a day and / or over months, years, etc.), the state of the wearable device and / or the wearable device's sensors (e.g., newer devices may operate differently from older devices), the temperature of the user's skin, the ambient temperature, the user's activity level, etc. Accordingly, the wearable device may analyze the heart rate data by comparing it to a set of criteria (e.g., thresholds). In some cases, the wearable device may determine whether to output the determined heart rate data based on the analysis. For example, if the heart rate data satisfies the set of criteria (e.g., indicates sufficient quality), the device may output the heart rate data to the user. If the heart rate data fails to meet the heart rate criteria (e.g., indicates insufficient quality), the device may refrain from outputting the heart rate data. In such cases, the output heart rate data may be accurate, but gaps may appear in the heart rate data (e.g., heart rate trends) as a result of the wearable device not outputting heart rate data for a period of time. In comparison, in other cases, the wearable device may be configured to output all heart rate data regardless of the quality of the data, which may result in outliers, errors, etc.

[0160] In some cases, to reduce the occurrence of gaps in the output data while maintaining the reliability of the heart rate data, the wearable device may be configured with multiple sets of criteria (e.g., multiple threshold quality metrics), with later criteria being more relaxed than earlier criteria in the sets. In other words, if the collected heart rate data does not satisfy a first criterion or first threshold quality metric, rather than simply discarding the heart rate data (which would result in a “gap” appearing in the user's heart rate data trend), the system may compare the collected heart rate data against additional, less stringent criteria / threshold quality metrics. If the heart rate data satisfies the additional, less stringent criteria / threshold quality metric, the system may output the heart rate data for display to the user, thereby reducing (or preventing) gaps in the user's heart rate data.

[0161] For example, a first set of criteria (e.g., first quality heartbeat criteria, first threshold quality metric at 810-a) can relate to the most stringent criteria, a second set of criteria (second quality heartbeat criteria, second threshold quality metric at 810-b) can be less stringent than the first set but more stringent than a third set (e.g., third quality heartbeat criteria, third threshold quality metric at 810-c), etc. Thus, the wearable device (or other component of system 200) first compares the heartbeat output selection at 805-a to the first set of criteria, and if the output satisfies the first set of criteria (e.g., equal to or lower than a threshold value) (e.g., QHR≧Thresh1), the device can output the heartbeat data. That is, if the heartbeat data satisfies the first threshold quality metric, the heartbeat data can be output for display to the user.

[0162] In comparison, if the output cannot meet the first set of criteria (e.g., QHR < Thresh1), the device may then compare the heartbeat data with a second set of criteria at 805-b. The second heartbeat criteria are not as strict (e.g., looser) than the first set of criteria. That is, if the heartbeat data cannot meet the first threshold quality metric, the system may compare the heartbeat data with a second threshold quality metric that is smaller than (e.g., not as strict as) the first threshold quality metric. The device may perform such a procedure through comparison at 805-c, for example, until the output meets the set of criteria and / or until the device has exhausted the criteria for comparing the output (e.g., until all threshold quality metrics have been exhausted), whichever comes first.

[0163] In some cases, the device may attach a quality label to the output data. For example, heartbeat data that has passed the second set of criteria (e.g., the second threshold quality metric) but not the first set of criteria (e.g., the first threshold quality metric) is less reliable than data that has passed the first set of criteria. So the device may attach a label indicating the quality of the output data to all data, the most reliable data (e.g., data that meets the first quality criteria), or any data that could not pass the first criteria. Thus, the device may provide the heartbeat data to the user without gaps or with minimal gaps within the data.

[0164] If the output cannot meet any of the criteria (e.g., the first, second, or third quality heartbeat criteria), the device may refrain from outputting the data. In some other cases, the device may output the data but supply a label indicating the low reliability of the data.

[0165] Thus, the device may determine a time series of heartbeat data with quality labels indicating the reliability of the corresponding data points. Then, at 465, the device may display the time series in an application (e.g., GUI275), with or without labels.

[0166] 9 illustrates an example GUI 900 supporting techniques for heartbeat detection according to aspects of the present disclosure. GUI 900 may implement or be implemented by aspects of system 100, system 200, heartbeat determination procedures 300 and 400, channel selection procedures 500, 600 and 700, heartbeat determination procedure 800, or any combination thereof. For example, GUI 900 may include an example GUI 275 included within user device 106 illustrated in FIG. 2.

[0167] GUI 900 represents a series of application pages 905 that may be displayed to a user via GUI 900 (e.g., GUI 275 depicted in FIG. 2 ). Server 110 of system 200 may cause GUI 900 of user device 106 (e.g., a mobile device) to display an indication of heart rate data (e.g., via application page 905-a or 905-b). Thus, upon determining heart rate data (e.g., as described with reference to FIGS. 3 and 8 ), a user may be presented with application page 905-a upon opening wearable application 250. As shown in FIG. 9 , application page 905-a may display a heart rate graph 910-a. Heart rate graph 910-a may include a visual display of how the user's heart rate responded to different events and activities (e.g., exercise, sleep, rest, etc.). In some cases, heart rate graph 910-a may display the user's heart rate over minutes, hours, days, etc. In some cases, the heart rate graph 910-a may display a combination of daytime and nighttime heart rate data (e.g., awake heart rate data and sleep heart rate data). Additionally, in some implementations, the application page 905-a may display one or more scores (e.g., a sleep score, a readiness score 915, an activity score, an inactivity score) of the user for each day (e.g., each sleep day), where one or more scores may be based on the heart rate data. As another example, the heart rate data may be used to update at least a subset of the factors of the readiness score 915 (e.g., a subset of sleep, sleep balance, HRV balance, recovery index, activity, and activity balance). In some cases, the user may select a button 925 to add a workout, a self-guided session, tags, etc.

[0168] Continuing with FIG. 9 , a user can select heart rate graph 910-a on application page 905-a to view details related to their heart rate, as shown on application page 905-b (“Heart Rate Also Shown”). In other words, tapping on heart rate graph 910-a shown on application page 905-a can cause GUI 900 to display application page 905-b, allowing the user to immediately and easily view the user's heart rate over time. Application page 905-b may include a model view with details about the heart rate. Heart rate graphs 901-a and 910-b may display the same or different graphs. For example, the time scales may be the same or different. In some cases, application page 905-b may display a diurnal heart rate graph (e.g., an awake heart rate graph) and a nocturnal heart rate graph (e.g., a sleep heart rate graph) to allow the user to distinguish between the user's heart rate during the day (e.g., when awake and active) and the user's heart rate during the night (e.g., when relaxed or asleep). Application page 905-b may also include a daily heart rate range 920-a, a relaxed heart rate range 920-b, a sleep heart rate range 920-c, and an exercise heart rate range 920-d. Each range may be in hours, for example. In some cases, application page 905-b may display heart rate data as HRV, resting heart rate, etc.

[0169] The system's server may cause the user device's GUI 900 to display a message related to the identified heart rate data on application page 905-a, 905-b, or both. The user device may display suggestions and / or information related to the heart rate data via the message. In some implementations, the user device 106 and / or the server 110 may generate alerts (e.g., messages, insights) related to the heart rate data that may be displayed to the user via the GUI 900 (e.g., application page 905-a or 905-b, or other application pages). In particular, the messages generated and displayed to the user via the GUI 900 may be related to one or more characteristics (e.g., time of day, duration, range) of the heart rate data. For example, a message may alert the user to take a breath, take time to relax, etc., based on the user's heart rate. In some cases, a message may display suggestions on how to adjust lifestyle to achieve a particular heart rate. In this regard, the system may be configured to display messages or insights to the user to promote effective and healthy patterns for the user.

[0170] 10 shows a block diagram 1000 of a device 1005 supporting techniques for heartbeat detection according to aspects of the present disclosure. The device 1005 may include an input module 1010, an output module 1015, and a wearable application 1020. The device 1005 may also include a processor. Each of these components can communicate with each other (e.g., via one or more buses).

[0171] The input module 1010 may provide a means for receiving information, such as packets associated with various information channels (e.g., control channels, data channels, information channels related to disease detection techniques), user devices, control information, or any combination thereof. The information may be sent to other components of the device 1005. The input module 1010 may utilize a single antenna or a set of multiple antennas.

[0172] The output module 1015 may provide a means for transmitting signals generated by other components of the device 1005. For example, the output module 1015 may transmit information such as packets, user data, control information, or any combination thereof, associated with various information channels (e.g., control channels, data channels, information channels related to disease detection techniques). In some examples, the output module 1015 may be co-located with the input module 1010 within a transceiver module. The output module 1015 may utilize a single antenna or a set of multiple antennas.

[0173] For example, the wearable application 1020 may include a physiological data component 1025, a condition quality component 1030, a PPG data component 1035, a heart rate component 1040, or any combination thereof. In some examples, the wearable application 1020 or its various components may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the input module 1010, the output module 1015, or both. For example, the wearable application 1020 may receive information from the input module 1010, transmit information to the output module 1015, or be integrated in combination with the input module 1010, the output module 1015, or both to receive information, transmit information, or perform various other operations described herein.

[0174] The physiological data component 1025 may be configured as or otherwise support a means for receiving physiological data associated with a user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user. The condition quality component 1030 may be configured as or otherwise support a means for determining a condition quality metric associated with the time interval based at least in part on the received motion data and temperature data, the condition quality metric indicating the relative quality of the physiological data collected over the time interval for determining a heart rate measurement. The PPG data component 1035 may be configured as or otherwise support a means for sampling PPG data of the user by the wearable device based at least in part on the condition quality metric satisfying a threshold metric value and the timer satisfying a first threshold duration. The heart rate component 1040 may be configured as or otherwise support a means for determining a heart rate measurement of the user based at least in part on the sampled PPG data.

[0175] 11 shows a block diagram 1100 of a wearable application 1120 supporting techniques for heartbeat detection according to aspects of the present disclosure. Wearable application 1120 may be an example of aspects of the wearable application or wearable application 1020, or both, described herein. Wearable application 1120 or various components thereof may be examples of means for performing various aspects of the techniques for heartbeat detection described herein. For example, the wearable application 1120 may include a physiological data component 1125, a condition quality component 1130, a PPG data component 1135, a heart rate component 1140, a PPG signal component 1145, a PPG signal comparison component 1150, a PPG signal component 1155, a PPG signal quality component 1160, a PPG signal selection component 1165, a PPG sensor activation component 1170, a PPG sensor deactivation component 1175, a PPG signal deactivation component 1180, a PPG signal activation component 1185, or any combination thereof.

[0176] The physiological data component 1125 may be configured as or otherwise support a means for receiving physiological data associated with a user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user. The condition quality component 1130 may be configured as or otherwise support a means for determining a condition quality metric associated with a time interval based at least in part on the received motion data and temperature data, the condition quality metric indicating the relative quality of the physiological data collected over the time interval for determining a heart rate measurement. The PPG data component 1135 may be configured as or otherwise support a means for sampling PPG data of the user by the wearable device based at least in part on the condition quality metric satisfying a threshold metric value and the timer satisfying a first threshold duration. The heart rate component 1140 may be configured as or otherwise support a means for determining a heart rate measurement of the user based at least in part on the sampled PPG data.

[0177] In some examples, to support sampling of PPG data, the PPG signal component 1145 can be configured as or otherwise support a means for acquiring a first PPG signal with a first pair of PPG sensors including at least light-emitting diodes configured to emit light in the visible spectrum. In some examples, to support sampling of PPG data, the PPG signal component 1145 can be configured as or otherwise support a means for acquiring a second PPG signal with a second pair of PPG sensors including at least infrared diodes. In some examples, to support sampling of PPG data, the PPG signal comparison component 1150 can be configured as or otherwise support a means for comparing a first PPG quality metric associated with the first PPG signal and a second PPG quality metric associated with the second PPG signal, the first PPG quality metric and the second PPG quality metric indicating the relative quality of the first PPG signal and the second PPG signal, respectively, and determining a heart rate measurement based at least in part on said comparison.

[0178] In some examples, the PPG signal selection component 1165 may be configured as or otherwise support a means for selecting one of the first or second PPG signals based at least in part on the comparison, and the heart rate measurement is determined based at least in part on the selected first or second PPG signal.

[0179] In some examples, the PPG signal deactivation component 1180 may be configured as or otherwise support a means for selectively deactivating the other of the non-selected first or second PPG signal, and determining the heart rate measurement is based at least in part on the selective deactivation of the other of the first or second PPG signal.

[0180] In some examples, the PPG signal component 1155 may be configured as or otherwise support a means for acquiring, based at least in part on the selection, a further PPG signal by one of the first or second pairs of PPG sensors associated with a selected one of the first or second PPG signals, and the heart rate measurement is based at least in part on the further PPG signal.

[0181] In some examples, the PPG signal activation component 1185 may be configured as or otherwise support a means for selectively activating the other of the non-selected first or second PPG signals based at least in part on the failure of the further PPG signal to satisfy a threshold quality metric. In some examples, the PPG signal component 1155 may be configured as or otherwise support a means for acquiring a third PPG signal with the other of the non-selected first or second PPG signals based at least in part on activating the other of the non-selected first or second PPG signals, and the heart rate measurement is based at least in part on the third PPG signal.

[0182] In some examples, to support sampling of the PPG data, the PPG signal component 1155 can be configured as or otherwise support a means for acquiring a first PPG signal with a first pair of PPG sensors including at least infrared diodes. In some examples, to support sampling of the PPG data, the PPG signal comparison component 1150 can be configured as or otherwise support a means for comparing a first PPG quality metric associated with the first PPG signal to a threshold quality metric, the first PPG quality metric including a relative quality of the first PPG signal, and determining a heart rate measurement based at least in part on said comparison.

[0183] In some examples, the PPG signal component 1155 may be configured as or otherwise support a means for acquiring a further PPG signal by a first pair of PPG sensors based at least in part on a first PPG quality metric associated with the first PPG signal satisfying a threshold quality metric, and a heart rate measurement is determined at least in part based on the further PPG signal.

[0184] In some examples, the PPG sensor activation component 1170 may be configured as or otherwise support a means for selectively activating a second pair of PPG sensors including at least a light emitting diode configured to emit light in the visible spectrum based at least in part on the failure of the first PPG quality metric associated with the first PPG signal to satisfy the threshold quality metric. In some examples, the PPG signal component 1155 may be configured as or otherwise support a means for acquiring a second PPG signal with the second pair of PPG sensors based at least in part on the selectively activating the second pair of PPG sensors, and a heart rate measurement is determined based at least on the second PPG signal.

[0185] In some examples, the PPG sensor deactivation component 1175 may be configured as or otherwise support a means for selectively deactivating the first pair of PPG sensors based at least in part on a first PPG quality metric associated with the first PPG signal failing to satisfy a threshold quality metric, and determining the heart rate measurement is based at least in part on selectively deactivating the first pair of PPG sensors.

[0186] In some examples, the state quality component 1130 may be configured as or otherwise support a means for determining the number of heartbeats in a PPG signal, and a PPG quality metric associated with the PPG signal may be based at least in part on the number of heartbeats.

[0187] In some examples, the PPG signal quality component 1160 may be configured as or otherwise support a means for determining the number of heart beats in the PPG signal, and a PPG quality metric associated with the PPG signal may be based at least in part on the number of heart beats.

[0188] In some examples, to support sampling of the PPG data, the PPG signal component 1155 can be configured as or otherwise support a means for acquiring a first PPG signal over a time interval. In some examples, to support sampling of the PPG data, the PPG signal quality component 1160 can be configured as or otherwise support a means for determining that a first PPG quality metric associated with the first PPG signal satisfies a first threshold quality metric, and determining the heart rate measurement is based at least in part on the first PPG quality metric satisfying the threshold quality metric.

[0189] In some examples, the PPG signal component 1155 may be configured or otherwise support a means for obtaining a second PPG signal over a second time interval after the first time interval. In some examples, the PPG signal quality component 1160 may be configured or otherwise support a means for determining that a second PPG quality metric associated with the second PPG signal fails to satisfy a first threshold quality metric. In some examples, the heart rate component 1040 may be configured or otherwise support a means for determining a second heart rate measurement of the user for a second time interval based at least in part on the second PPG quality metric satisfying a second threshold quality metric that is less than the first threshold quality metric.

[0190] In some examples, the wearable device comprises a wearable ring device. In some examples, the wearable device collects physiological data from the user based on arterial blood flow.

[0191] 12 shows a diagram of a system 1200 including a device 1205 supporting techniques for heartbeat detection according to aspects of the present disclosure. The device 1205 may be or include examples of components of the device 1005 described herein. The device 1205 may include examples of the user device 106, as previously described herein. The device 1205 may include components for bidirectional communication, including components for sending and receiving communications with the wearable device 104 and the server 110, such as a wearable application 1220, a communication module 1210, an antenna 1215, a user interface component 1225, a database (application data) 1230, a memory 1235, and a processor 1240. These components may be in electronic communication or may be otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1245).

[0192] The communications module 1210 may manage input and output signals for the device 1205 via the antenna 1215. The communications module 1210 may include an example of the communications module 220-b of the user device 106 described and illustrated in FIG. 2. In this regard, the communications module 1210 may manage communications with the ring 104 and the server 110, as depicted in FIG. 2. The communications module 1210 may also manage peripherals not built into the device 1205. In some cases, the communications module 1210 may represent a physical connection or port to an external peripheral. In some cases, the communications module 1210 may utilize an operating system such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or other known operating systems. In other cases, the communications module 1210 may represent or interact with a wearable device (e.g., ring 104), a modem, a keyboard, a mouse, a touchscreen, or similar devices. In some cases, the communications module 1210 may be implemented as part of the processor 1240. In some examples, a user may interact with the device 1205 via the communications module 1210, a user interface component 1225, or a hardware component controlled by the communications module 1210.

[0193] In some cases, the device 1205 may include a single antenna 1215. However, in some other cases, the device 1205 may be equipped with more than one antenna 1215, which may be capable of simultaneously transmitting or receiving multiple wireless transmissions. The communications module 1210 may perform bidirectional communications via one or more antennas 1215, wired or wireless links, as described herein. For example, the communications module 1210 may represent a wireless transceiver and may communicate bidirectionally with other wireless transceivers. The communications module 1210 may also include a module that modulates packets, provides the modulated packets to one or more antennas 1215 for transmission, and demodulates packets received from one or more antennas 1215.

[0194] The user interface component 1225 may manage the storage and processing of data in the database 1230. In some cases, a user may interact with the user interface component 1225. In other cases, the user interface component 1225 may operate automatically without user interaction. The database 1230 may be an example of a single database, a distributed database, multiple distributed databases, a data store, a data lake, or an emergency backup database.

[0195] The memory 1235 may include RAM and ROM. The memory 1235 may store computer-readable computer-executable software that, when executed, causes the processor 1240 to perform various functions described herein. In some cases, the memory 1235 may include a BIOS that may, among other things, control basic hardware or software operations such as interaction with peripheral components or devices.

[0196] The processor 1240 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 1240 may be configured to operate a memory array using a memory controller. In other cases, the memory controller may be incorporated into the processor 1240. The processor 1240 may be configured to execute computer-readable instructions stored in the memory 1235 to perform various functions (e.g., functions or tasks that support the methods and systems for sleep stage algorithms).

[0197] For example, wearable application 1220 may be configured or otherwise support a means for receiving physiological data associated with a user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user. Wearable application 1220 may be configured or otherwise support a means for determining a state quality metric associated with the time interval based at least in part on the received motion data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement. Wearable application 1220 may be configured or otherwise support a means for sampling PPG data of the user by the wearable device based at least in part on the state quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration. Wearable application 1220 may be configured or otherwise support a means for determining a heart rate measurement of the user based at least in part on the sampled PPG data.

[0198] By including or configuring the wearable application 1220 according to the examples described herein, the device 1205 may support techniques for improved heart rate data determination and output procedures.

[0199] The wearable applications 1220 may include applications (e.g., “APPs”), programs, software, or other components configured to facilitate communication with the ring 104, the server 110, other user devices 106, etc. For example, the wearable applications 1220 may include applications executable on the user device 106 configured to receive data (e.g., physiological data) from the ring 104, perform processing operations on the received data, send and receive data from the server 110, and cause presentation of the data to the user 102.

[0200] FIG. 13 shows a flowchart illustrating a method 1300 supporting techniques for heartbeat detection according to aspects of the present disclosure. The operations of method 1300 may be implemented by a user device or components thereof described herein. For example, the operations of method 1300 may be performed by a user device as described with reference to FIGS. 1-12 . In some examples, the user device may execute a set of instructions to control functional elements of the user device to perform the described functions. Additionally or alternatively, the user device may perform aspects of the described functions using dedicated hardware.

[0201] At 1305, the method may include receiving physiological data associated with the user, including motion data and temperature data collected over a time interval by a wearable device associated with the user. The operations of 1305 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1305 may be performed by physiological data component 1125 as described with reference to FIG. 11 .

[0202] At 1310, the method may include determining a condition quality metric associated with the time interval based at least in part on the received motion data and temperature data. The condition quality metric indicates a relative quality of the physiological data collected over the time interval for determining the heart rate measurement measurement. The operations of 1310 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1310 may be performed by condition quality component 1130 as described with reference to FIG. 11 .

[0203] At 1315, the method may include sampling, by the wearable device, PPG data of the user based at least in part on the state quality metric satisfying the threshold metric value and the timer satisfying the first threshold duration. The operations of 1315 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1315 may be performed by the PPG data component 1135 as described with reference to FIG. 11 .

[0204] At 1320, the method may include determining a heart rate measurement of the user based at least in part on the sampled PPG data. The operations of 1320 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1320 may be performed by heart rate component 1040 as described with reference to FIG. 11 .

[0205] FIG. 14 shows a flowchart illustrating a method 1400 supporting techniques for heartbeat detection according to aspects of the present disclosure. The operations of method 1400 may be implemented by a user device or components thereof described herein. For example, the operations of method 1400 may be performed by a user device described with reference to FIGS. 1-12. In some examples, the user device may execute a set of instructions to control functional elements of the user device to perform the described functions. Additionally or alternatively, the user device may perform aspects of the described functions using dedicated hardware.

[0206] At 1405, the method may include receiving physiological data associated with the user, including motion data and temperature data collected over a time interval by a wearable device associated with the user. The operations of 1405 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1405 may be performed by physiological data component 1125 as described with reference to FIG. 11 .

[0207] At 1410, the method may include determining a condition quality metric associated with the time interval based at least in part on the received motion data and temperature data. The condition quality metric indicates a relative quality of the physiological data collected over the time interval for determining the heart rate measurement measurement. The operations of 1410 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1410 may be performed by condition quality component 1130 as described with reference to FIG. 11 .

[0208] At 1415, the method may include sampling, by the wearable device, PPG data of the user based at least in part on the state quality metric satisfying the threshold metric value and the timer satisfying the first threshold duration. The operations of 1415 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1415 may be performed by PPG data component 1135 as described with reference to FIG. 11 .

[0209] At 1420, the method may include acquiring a first PPG signal with a first pair of PPG sensors including at least a light emitting diode configured to emit light in the visible spectrum. The operations of 1420 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1420 may be performed by a PPG signal component 1145 described with reference to FIG. 11.

[0210] At 1425, the method may include acquiring a second PPG signal with a second pair of PPG sensors including at least an infrared diode. The operations of 1425 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1425 may be performed by PPG signal component 1145 described with reference to FIG. 11.

[0211] At 1430, the method may include comparing a first PPG quality metric associated with the first PPG signal and a second PPG quality metric associated with the second PPG signal. The first PPG quality metric and the second PPG quality metric indicate relative quality of the first PPG signal and the second PPG signal, respectively. The operations of 1430 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1430 may be performed by PPG signal comparison component 1150 described with reference to FIG. 11 .

[0212] At 1435, the method may include determining a heart rate measurement of the user based at least in part on the sampled PPG data. Determining the heart rate measurement is based at least in part on the comparison. The operations of 1435 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1435 may be performed by heart rate component 1040 as described with reference to FIG. 11 .

[0213] FIG. 15 shows a flowchart illustrating a method 1500 supporting techniques for heartbeat detection according to aspects of the present disclosure. The operations of method 1500 may be implemented by a user device or components thereof described herein. For example, the operations of method 1500 may be performed by a user device described with reference to FIGS. 1-12. In some examples, the user device may execute a set of instructions to control functional elements of the user device to perform the described functions. Additionally or alternatively, the user device may perform aspects of the described functions using dedicated hardware.

[0214] At 1505, the method may include receiving physiological data associated with the user, including motion data and temperature data collected over a time interval by a wearable device associated with the user. The operations of 1505 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1505 may be performed by physiological data component 1125 as described with reference to FIG. 11 .

[0215] At 1510, the method may include determining a condition quality metric associated with the time interval based at least in part on the received motion data and temperature data. The condition quality metric indicates a relative quality of the physiological data collected over the time interval for determining the heart rate measurement measurement. The operations of 1510 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1510 may be performed by condition quality component 1130 as described with reference to FIG. 11 .

[0216] At 1515, the method may include sampling, by the wearable device, PPG data of the user based at least in part on the state quality metric satisfying the threshold metric value and the timer satisfying the first threshold duration. The operations of 1515 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1515 may be performed by PPG data component 1135 as described with reference to FIG. 11 .

[0217] At 1520, the method may include acquiring a first PPG signal with a first pair of PPG sensors including at least an infrared diode. The operations of 1520 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1520 may be performed by a PPG signal component 1155 described with reference to FIG. 11 .

[0218] At 1525, the method may include comparing a first PPG quality metric associated with the first PPG signal to a threshold quality metric. The first PPG quality metric indicates a relative quality of the first PPG signal. The operations of 1525 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1525 may be performed by PPG signal comparison component 1150 described with reference to FIG. 11 .

[0219] At 1530, the method may include determining a heart rate measurement of the user based at least in part on the sampled PPG data. Determining the heart rate measurement is based at least in part on the comparison. The operations of 1530 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1530 may be performed by heart rate component 1040 as described with reference to FIG. 11 .

[0220] It should be noted that the above methods describe possible implementations, and that acts and steps may be rearranged or otherwise modified, and other implementations are possible. Additionally, aspects from two or more methods may be combined.

[0221] A method is described that may include receiving physiological data associated with a user, the physiological data including athletic data and temperature data collected over a time interval by a wearable device associated with the user, determining a state quality metric associated with the time interval based at least in part on the received athletic data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement, sampling PPG data by the wearable device based at least in part on the state quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration, and determining a heart rate measurement of the user based at least in part on the sampled PPG data.

[0222] An apparatus is described that may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to: receive physiological data associated with a user, including athletic data and temperature data collected over a time interval by a wearable device associated with the user; determine a state quality metric associated with the time interval based at least in part on the received athletic data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement; sample PPG data with the wearable device based at least in part on the state quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration; and determine a heart rate measurement of the user based at least in part on the sampled PPG data.

[0223] Another apparatus is described that may include means for receiving physiological data associated with a user, including athletic data and temperature data collected over a time interval by a wearable device associated with the user, means for determining a state quality metric associated with the time interval based at least in part on the received athletic data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement, means for sampling PPG data by the wearable device based at least in part on the state quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration, and means for determining a heart rate measurement of the user based at least in part on the sampled PPG data.

[0224] A non-transitory computer-readable medium having code stored thereon is described. The code may include instructions executable by a processor to: receive physiological data associated with a user, including athletic data and temperature data collected over a time interval by a wearable device associated with the user; determine a state quality metric associated with the time interval based at least in part on the received athletic data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement; sample PPG data with the wearable device based at least in part on the state quality metric satisfying a threshold metric value and a timer satisfying a first threshold duration; and determine a heart rate measurement of the user based at least in part on the sampled PPG data.

[0225] In some examples of the methods, devices, and non-transitory computer-readable media described herein, sampling the PPG data may include operations, features, means, or instructions for acquiring a first PPG signal with a first pair of PPG sensors including at least a light-emitting diode configured to emit light in the visible spectrum, acquiring a second PPG signal with a second pair of PPG sensors including at least an infrared diode, comparing a first PPG quality metric associated with the first PPG signal and a second PPG quality metric associated with the second PPG signal, wherein the first PPG quality metric and the second PPG quality metric indicate relative quality of the first PPG signal and the second PPG signal, respectively, and determining a heart rate measurement may be based at least in part on said comparison.

[0226] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for selecting one of the first or second PPG signals based at least in part on the comparison, and a heart rate measurement may be determined based at least in part on the selected first or second PPG signal.

[0227] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include an operation, feature, means, or instruction for selectively deactivating the other of the non-selected first or second PPG signals, and determining the heart rate measurement may be based at least in part on selectively deactivating the other of the first or second PPG signals.

[0228] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include an operation, feature, means, or instruction for acquiring a further PPG signal by one of the first or second pair of PPG sensors associated with the selected one of the first or second PPG signals based at least in part on the selection, and the heart rate measurement may be based at least in part on the further PPG signal.

[0229] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include an operation, feature, means, or instruction of selectively activating the other of the non-selected first or second PPG signals based at least in part on the failure of the further PPG signal to satisfy a threshold quality metric, and acquiring a third PPG signal from the other of the non-selected first or second PPG signals based at least in part on activating the other of the non-selected first or second PPG signals, and the heart rate measurement may be based at least in part on the third PPG signal.

[0230] In some examples of the methods, devices, and non-transitory computer-readable media described herein, sampling the PPG data may include operations, features, means, or instructions for acquiring a first PPG signal with a first pair of PPG sensors including at least an infrared diode, comparing a first PPG quality metric associated with the first PPG signal to a threshold quality metric, the first PPG quality metric indicating a relative quality of the first PPG signal, and determining a heart rate measurement may be based at least in part on the comparison.

[0231] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include an operation, feature, means, or instruction for acquiring a further PPG signal with the first pair of PPG sensors based at least in part on a first PPG quality metric associated with the first PPG signal satisfying a threshold quality metric, and a heart rate measurement may be determined based at least in part on the further PPG signal.

[0232] Some examples of the methods, devices, and non-transitory computer-readable media described herein may include operations, features, means, or instructions for selectively activating a second pair of PPG sensors including at least a light-emitting diode configured to emit light in the visible spectrum based at least in part on a failure of a first PPG quality metric associated with the first PPG signal to satisfy a threshold quality metric, and acquiring a second PPG signal by the second pair of PPG sensors based at least in part on selectively activating the second pair of PPG sensors.

[0233] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include an operation, feature, means, or instruction for selectively deactivating the first pair of PPG sensors based at least in part on a failure of a first PPG quality metric associated with the first PPG signal to satisfy a threshold quality metric, and determining the heart rate measurement may be based at least in part on selectively deactivating the first pair of PPG sensors.

[0234] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for determining the number of heartbeats in a PPG signal, and a PPG quality metric associated with the PPG signal may be based at least in part on the number of heartbeats.

[0235] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for determining the number of heartbeats in a PPG signal, and a PPG quality metric associated with the PPG signal may be based at least in part on the number of heartbeats.

[0236] In some examples of the methods, devices, and non-transitory computer-readable media described herein, sampling the PPG data may further include an operation, feature, means, or instruction of acquiring a first PPG signal over a time interval and determining that a first PPG quality metric associated with the first PPG signal satisfies a first threshold quality metric, and determining the heart rate measurement may be based at least in part on the first PPG quality metric satisfying the threshold quality metric.

[0237] Some examples of the methods, devices, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for acquiring a second PPG signal over a second time interval after the first time interval, determining that a second PPG quality metric associated with the second PPG signal fails to satisfy a first threshold quality metric, and determining a second heart rate measurement of the user for the second time interval based at least in part on the second PPG quality metric satisfying a second threshold quality metric, which may be lower than the first threshold quality metric.

[0238] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the wearable device comprises a wearable ring device.

[0239] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, a wearable device collects physiological data from a user based on the aneurysm.

[0240] The description set forth herein, in conjunction with the accompanying drawings, describes exemplary configurations and does not represent every example that may be implemented or that is within the scope of the claims. As used herein, the term "exemplary" means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous over other examples." The detailed description includes specific details for the purpose of facilitating an understanding of the described technology. However, these technologies may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described examples.

[0241] In the accompanying figures, similar components or features may be labeled with the same reference label. Additionally, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes among the similar components. If only the first reference label is used in the specification, the description applies to any of the similar components with the same first reference label, regardless of the second reference label.

[0242] The information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0243] The various example blocks and modules described in connection with the disclosure herein may be implemented or performed using a general purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in combination with a DSP core, or any other such configuration).

[0244] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored or transmitted as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. Features implementing the functions may be physically located in various locations, including being distributed such that portions of the functions are implemented in different physical locations. Also, as used herein, including in the claims, "or" used in a list of items (e.g., a list of items followed by a phrase such as "at least one of" or "one or more of") indicates an inclusive list, such as, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase "based on" should not be construed as referring to a closed set of conditions. For example, an example step described as "based on condition A" can be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted the same as the phrase "based at least in part on."

[0245] Computer-readable media includes both non-transitory computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Non-transitory storage media may be any available medium that can be accessed by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media include RAM, ROM, Electrically Erasable Programmable Read Only Memory (EEPROM), Compact Disc (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio waves, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio waves, and microwaves are included in the definition of media. As used herein, disk and disc include CDs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of the above are also included within the scope of computer-readable media.

[0246] The description herein is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0247] [Cross reference] This application claims priority to commonly assigned U.S. Provisional Patent Application No. 63 / 315,602, filed March 2, 2022, entitled "TECHNIQUES FOR HEART RATE DETECTION," and to commonly assigned U.S. Provisional Patent Application No. 63 / 251,086, filed October 1, 2021, entitled "TECHNIQUES FOR HEART RATE DETECTION," which in turn claims priority to commonly assigned U.S. Provisional Patent Application No. 17 / 957,345, filed September 20, 2022, entitled "TECHNIQUES FOR HEART RATE DETECTION," both of which are incorporated herein by reference.

Claims

1. 1. A method for measuring a user's heart rate, comprising: receiving physiological data associated with the user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user; determining a state quality metric associated with the time interval based at least in part on the received motion data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement; and initiating sampling of photoplethysmogram (PPG) data of the user by the wearable device based at least in part on whether the state quality metric satisfies a threshold metric value and whether an elapsed time since a previous sampling of PPG data satisfies a first threshold duration or a second threshold duration that is longer than the first threshold duration, wherein whether the elapsed time is compared to the first threshold duration or the second threshold duration is based on whether the state quality metric satisfies or does not satisfy the threshold metric value; determining a heart rate measurement of the user based at least in part on the sampled PPG data; A method having the following.

2. Initiating the sampling of the PPG data comprises: acquiring a first PPG signal with a first pair of PPG sensors including at least a light emitting diode configured to emit light in the visible spectrum; acquiring a second PPG signal with a second pair of PPG sensors including at least an infrared diode; comparing a first PPG quality metric associated with the first PPG signal and a second PPG quality metric associated with the second PPG signal, the first PPG quality metric and the second PPG quality metric indicating relative quality of the first PPG signal and the second PPG signal, respectively; and determining the heart rate measurement based at least in part on the comparison; The method of claim 1.

3. selecting one of the first PPG signal or the second PPG signal based at least in part on the comparison; the heart rate measurement is determined based at least in part on the selected first PPG signal or the selected second PPG signal. The method of claim 2.

4. selectively deactivating the other of the first PPG signal or the second PPG signal that is not selected; determining the heart rate measurement is based at least in part on selectively deactivating the other of the first PPG signal or the second PPG signal. The method of claim 3.

5. acquiring a further PPG signal with one of the first pair of PPG sensors or the second pair of PPG sensors associated with the selected one of the first PPG signal or the second PPG signal based at least in part on the selection; the heart rate measurement is based at least in part on the further PPG signal. The method of claim 3.

6. selectively activating the other of the first or second PPG signal that was not selected based at least in part on the failure of the additional PPG signal to meet a threshold quality metric; obtaining a third PPG signal by the non-selected other of the first PPG signal or the second PPG signal based at least in part on activating the other of the non-selected first PPG signal or the second PPG signal; and the heart rate measurement is based at least in part on the third PPG signal. The method of claim 5.

7. Initiating the sampling of the PPG data comprises: acquiring a first PPG signal with a first pair of PPG sensors including at least an infrared diode; comparing a first PPG quality metric associated with the first PPG signal to a threshold quality metric; and the first PPG quality metric indicates a relative quality of the first PPG signal; determining the heart rate measurement based at least in part on the comparison; The method of claim 1.

8. acquiring a further PPG signal with the first pair of PPG sensors based at least in part on the first PPG quality metric associated with the first PPG signal satisfying the threshold quality metric; the heart rate measurement is determined at least in part based on the further PPG signal. The method of claim 7.

9. selectively activating a second pair of PPG sensors including at least a light emitting diode configured to emit light within the visible spectrum based at least in part on a failure of the first PPG quality metric associated with the first PPG signal to satisfy the threshold quality metric; acquiring a second PPG signal with the second pair of PPG sensors based at least in part on selectively activating the second pair of PPG sensors; and the heart rate measurement is determined based at least in part on the second PPG signal. The method of claim 7.

10. selectively deactivating the first pair of PPG sensors based at least in part on a failure of the first PPG quality metric associated with the first PPG signal to satisfy the threshold quality metric; determining the heart rate measurement is based at least in part on selectively deactivating the first pair of PPG sensors; The method of claim 7.

11. determining a number of heartbeats in the first PPG signal; the first PPG quality metric associated with the first PPG signal is based at least in part on the number of heartbeats; The method of claim 7.

12. determining a number of heartbeats in the first PPG signal; the first PPG quality metric associated with the first PPG signal is based at least in part on the number of heartbeats; The method of claim 7.

13. Initiating the sampling of the PPG data comprises: acquiring a first PPG signal over the time interval; determining that a first PPG quality metric associated with the first PPG signal satisfies a first threshold quality metric; and determining the heart rate measurement is based at least in part on the first PPG quality metric satisfying the first threshold quality metric; The method of claim 1.

14. acquiring a second PPG signal over a second time interval that is later than the time interval; determining that a second PPG quality metric associated with the second PPG signal fails to satisfy the first threshold quality metric; determining a second heart rate measurement of the user for the second time interval based at least in part on the second PPG quality metric satisfying a second threshold quality metric that is less than the first threshold quality metric; Further comprising: The method of claim 13.

15. the wearable device comprises a wearable ring device; The method of claim 1.

16. the wearable device collects the physiological data from the user based on arterial blood flow; The method of claim 1.

17. 1. A device for measuring a user's heart rate, comprising: a processor; a memory coupled to the processor; stored in the memory, and receiving physiological data associated with the user, the physiological data including motion data and temperature data collected over a time interval by a wearable device associated with the user; determining a state quality metric associated with the time interval based at least in part on the received motion data and temperature data, the state quality metric indicating a relative quality of the physiological data collected over the time interval for determining a heart rate measurement; and initiating sampling of photoplethysmogram (PPG) data of the user by the wearable device based at least in part on whether the state quality metric satisfies a threshold metric value and whether an elapsed time since a previous sampling of PPG data satisfies a first threshold duration or a second threshold duration that is longer than the first threshold duration, wherein whether the elapsed time is compared to the first threshold duration or the second threshold duration is based on whether the state quality metric satisfies or does not satisfy the threshold metric value; determining a heart rate measurement of the user based at least in part on the sampled PPG data; instructions executable by the processor to cause the processor to execute A device having:

18. To begin sampling the PPG data, the instructions may cause the device to: acquiring a first PPG signal with a first pair of PPG sensors including at least a light emitting diode configured to emit light in the visible spectrum; acquiring a second PPG signal with a second pair of PPG sensors including at least an infrared diode; comparing a first PPG quality metric associated with the first PPG signal and a second PPG quality metric associated with the second PPG signal, the first PPG quality metric and the second PPG quality metric indicating relative quality of the first PPG signal and the second PPG signal, respectively; and determining the heart rate measurement based at least in part on the comparison; 18. The apparatus of claim 17.

19. The instructions may cause the device to: selecting one of the first PPG signal or the second PPG signal based at least in part on the comparison; and further executed by the processor to execute the heart rate measurement is determined based at least in part on the selected first PPG signal or the selected second PPG signal.

20. The apparatus of claim 18.

20. The instructions may cause the device to: Selectively deactivating the other of the first PPG signal or the second PPG signal that is not selected. and further executed by the processor to execute determining the heart rate measurement is based at least in part on selectively deactivating the other of the first PPG signal or the second PPG signal.

20. The apparatus of claim 19.

Images