Method and apparatus for sensor orientation detection

Abstract

A system determines orientation of a wearable device (100). The system may include at least one processor configured to receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device. The wearable device may have a correct orientation at which the PPG sensor is directed at the user, and an incorrect orientation at which the PPG sensor is directed away from the user. The at least one processor may determine whether the wearable device is in the incorrect or correct orientation. For example, the at least one processor may determine a perfusion measure from the PPG signal. The at least one processor may determine that the wearable device is in the incorrect or correct orientation based on the perfusion measure such as when the perfusion measure falls below a threshold.

Description

METHOD AND APPARATUS FOR SENSOR ORIENTATION DETECTION1 CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional Patent Application No. 63 / 511,326, filed 30 June 2023, the entire content of which is incorporated herein by reference.2 BACKGROUND OF THE TECHNOLOGY2.1 FIELD OF THE TECHNOLOGY

[0002] The present technology relates to determining orientation of a wearable device. In particular, the present technology relates to detecting an incorrect application of a wearable sensor to the user, such as when the sensor is in an incorrect orientation such as a reverse orientation, based on a signal from the sensor, such as a photoplethysmography signal from a photoplethysmography (PPG) sensor.2.2 DESCRIPTION OF THE RELATED ART

[0003] Wearable devices can help assess a user, such as the physiological condition(s) of the user, the state of a user or sensed or determined parameters associated with the user. For instance, wearable PPG devices can monitor pulse rate (PR), oxygen saturation (SpO2), blood pressure and / or blood vessel stiffness, and can detect sleep related events of the user.

[0004] Sometimes, the user may mistakenly wear the PPG device in an incorrect orientation (e.g., a reverse orientation where the PPG device is flipped relative to the correct orientation), preventing proper functioning of the PPG device and / or compromising data signal quality. Such mistakes may result in delays in diagnoses.

[0005] Existing technologies do not timely address the above issue. As such, there is a need to develop a solution that automates detection of incorrect or otherwise unsuitable orientations of the sensor when applied to the user, such as when the sensor is worn in a reverse application, and timely inform the user during or after a measurement session to correct the misapplication of the sensor. Further, to improve the overall accuracy of the evaluation of sensor(s) signals, such as for physiological condition evaluation or determination of user parameters such as pulse rate, blood pressure estimation, SpCh level, etc, there is a need to identify, filter and / or eliminate sensor signals, such as PPG signals, that are affected by the reverse application of the wearable device.3 BRIEF SUMMARY OF THE TECHNOLOGY

[0006] The present technology is directed towards systems and methods for determining orientation of a wearable device, such as determining a correct orientation, in other words a suitable orientation for correct use of the device, or an incorrect orientation (e.g., reversed orientation relative to correct orientation), in other words an unsuitable orientation for correct use of the device, in relation to application of the wearable device to a user.

[0007] A first aspect of the present technology relates to a system for determining orientation of a wearable device.

[0008] A second aspect of the present technology relates to a method for determining orientation of a wearable device.

[0009] Some implementations of the present technology include a system for determining orientation of a wearable device on a user. The system may include at least one processor. The at least one processor may be configured to receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device. The wearable device may have a correct orientation, and an incorrect orientation, such as when the wearable device is being worn by the user and it generates the PPG signal. The at least one processor may be configured to determine whether the wearable device is in the correct orientation or the incorrect orientation, by determining a perfusion measure from the PPG signal; and by determining, based on the perfusion measure, that the wearable device is in the correct orientation or the incorrect orientation.

[0010] In some implementations, the determining that the wearable device may be in the correct orientation or the incorrect orientation may be based on a comparison between the perfusion measure and a threshold. When the perfusion measure is below the threshold, the wearable device may be determined to be in the incorrect orientation. When the perfusion measure is above the threshold, the wearable device may be determined to be in the correct orientation. The incorrect orientation may include the wearable device being mounted on the user with the PPG sensor directed away from the user. The perfusion measure may be determined based on a prominence of a peak of the PPG signal. The at least one processor may be configured to derive a peripheral arterial tonometry signal from the PPG signal to detect an occurrence of a sleep-related event of the user. The PPG signal may be measured at a finger of the user. The at least one processor may be configured to receive the PPG signal from the wearable device via a wireless connection. The PPG sensor may include an infrared sensor and / or a red-light sensor. The system may further include the wearable device.

[0011] In some implementations, the at least one processor may be configured to receive an accelerometer signal from the wearable device to determine whether the user wears the wearable device. The at least one processor may be configured to determine whether the wearable device may be in the correct orientation or the incorrect orientation after determining that the user wears the wearable device. The at least one processor may be configured to identify, from the accelerometer signal, a period of time during which the user wears the wearable device. The at least one processor may be configured to determine, from the PPG signal, whether the wearable device may be in the correct orientation or the incorrect orientation during the identified period of time. The perfusion measure may include a median prominence or an average prominence of a plurality of peaks of the PPG signal. The at least one processor may be configured to generate an output to the user indicating that the wearable device may be in the incorrect orientation. The at least one processor may be configured to receive the PPG signal from the wearable device during or after a measurement session of the user.

[0012] Some implementations of the present technology include a method for determining orientation of a wearable device on a user. The method may include receiving, by one or more processors, a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device. The method may include determining, by the one or more processors, whether the wearable device may be in a correct orientation or an incorrect orientation, such as when the wearable device is being worn by the user and it generates the PPG signal. The determining may include determining a perfusion measure from the PPG signal; and determining, based on the perfusion measure, that the wearable device is in the correct orientation or the incorrect orientation.

[0013] In some implementations, the determining that the wearable device is in the correct orientation or the incorrect orientation may be based on a comparison between the perfusion measure and a threshold. When the perfusion measure is below the threshold, the wearable device may be determined to be in the incorrect orientation. When the perfusion measure is above the threshold, the wearable device may be determined to be in the correct orientation. The incorrect orientation may include the wearable device being mounted on the user with the PPG sensor directed away from the user. The determining the perfusion measure may include determining the perfusion measure based on a prominence of a peak of the PPG signal. The method may include deriving, by the one or more processors, a peripheral arterial tonometry signal from the PPG signal to detect an occurrence of a sleep-related event of the user. ThePPG signal may be measured at a finger of the user. The receiving may include receiving the PPG signal from the wearable device via a wireless connection. The PPG sensor may include an infrared sensor and / or a red-light sensor. The method may include receiving, by the one or more processors, an accelerometer signal from the wearable device to determine whether the user wears the wearable device. The determining whether the wearable device is in the correct orientation or the incorrect orientation may occur after determining that the user wears the wearable device. The method may include identifying, by the one or more processors, from the accelerometer signal, a period of time during which the user wears the wearable device. The method may include determining, by the one or more processors, from the PPG signal, whether the wearable device may be in the correct orientation or the incorrect orientation during the identified period of time. In some implementations, the prominence may include a median prominence or an average prominence of a plurality of peaks of the PPG signal. The method may include generating an output to the user indicating that the wearable device may be in the incorrect orientation.

[0014] Some implementations of the present technology include a processor-readable medium, having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to perform any aspects of the aforementioned methods or described herein.

[0015] Some implementations of the present technology include a processor-readable medium, having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to determine orientation of a wearable device. The processor-executable instructions may include instructions to receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device. The processor-executable instructions may include instructions to determine whether the wearable device may be in a correct orientation or an incorrect orientation, including: instructions to determine a perfusion measure from the PPG signal; and instructions to generate, based on the perfusion measure, an indication that the wearable device may be in the correct orientation or the incorrect orientation.

[0016] Of course, portions of the aspects may form sub-aspects of the present technology. Also, various ones of the sub-aspects and / or aspects may be combined in various manners and also constitute additional aspects or sub-aspects of the present technology.

[0017] Other features of the technology will be apparent from consideration of the information contained in the following detailed description, abstract, drawings and claims.4 BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present technology is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which like reference numerals refer to similar elements including:

[0019] FIG. 1 illustrates an example wearable device, according to one aspect of the present technology.

[0020] FIG. 2 illustrates an example PPG waveform, according to one aspect of the present technology.

[0021] FIG. 3 A illustrates the wearable device at a normal position in a correct orientation relative to a user, according to one aspect of the present technology.

[0022] FIG. 3B illustrates the wearable device in a normal position but in an incorrect orientation (e.g., at a reverse orientation to the user) relative to the user, according to one aspect of the present technology.

[0023] FIG. 4 A illustrates a segment of a PPG signal collected by the wearable device at a correct orientation, according to one aspect of the present technology.

[0024] FIG. 4B illustrates a segment of a PPG signal collected by the wearable device at an incorrect orientation (e.g., a reverse orientation) according to one aspect of the present technology.

[0025] FIG. 5A is a zoomed-out version of sensor signal showing a full night of data in a low resolution view with the segment of the PPG signal from FIG. 4A, which is collected by the wearable device at a correct orientation, according to one aspect of the present technology.

[0026] FIG. 5B is a zoomed-out version of sensor signal showing a full night of data in a low resolution view, including the segment of a PPG signal of FIG. 4B, which is collected by the wearable device at an incorrect orientation, such as a reverse orientation, according to one aspect of the present technology.

[0027] FIG. 6 illustrates example components of the wearable device and a system for determining orientation of the wearable device, according to one aspect of the present technology.

[0028] FIG. 7 illustrates an example process for determining orientation of the wearable device, according to one aspect of the present technology.

[0029] FIG. 8 illustrates an example flow chart for a method for determining orientation of the wearable device, according to one aspect of the present technology.5 DETAILED DESCRIPTION OF EXAMPLES OF THE TECHNOLOGY

[0030] Before the present technology is described in further detail, it is to be understood that the technology is not limited to the particular examples described herein, which may vary. It is also to be understood that the terminology used in this disclosure is for the purpose of describing only the particular examples discussed herein, and is not intended to be limiting.

[0031] The following description is provided in relation to various examples which may share one or more common characteristics and / or features. It is to be understood that one or more features of any one example or any of the examples or implementations, may be combinable with one or more features of another example or other examples or implementations. In addition, any single feature or combination of features in any of the examples or implementations may constitute a further example or implementation.5.1 WEARABLE DEVICE 100

[0032] FIG. 1 illustrates an example wearable device 100 according to the present disclosure. When worn by a user 101, the device 100 may record data associated with the user. In examples, the device 100 may be worn by the user during sleep so as to record sleep-related events.

[0033] The device 100 may include a switch 102 to power on and off the device 100, and a sensor 104 to record data associated with the user. In implementations, both the switch 102 and the sensor 104 may be disposed on a contact surface 106. The contact surface 106 may represent a sensing side of the device 100. Further, the device 100 may include a non-contact surface 108 such as opposite to the contact surface 106. The contact surface 106 and the noncontact surface 108 may face opposite directions. When the device 100 is worn correctly by the user, the contact surface 106 and the sensor 104 may be in direct contact with the user’s skin, such as finger, brachia, nostril, head, forehead, mouth, toe, wrist, ankle, torso, esophageal region, and ear (e.g., in-ear, earlobe, external ear cartilage, superior auricular region), among other possibilities, while the non-contact surface may face away from the user’s skin.

[0034] The sensor 104 may include a PPG sensor. The PPG sensor may include a light source and a detector. The light source may be configured to emit light. The light source may emit light of different wavelengths and intensities, including but not limited to green, red, blue and infrared lights. The light source may include one or more light-emitting diodes (LEDs). The detector or receiver may be configured to detect reflections of light from the user’s tissue,such as to obtain reflectance-based PPG signals. In one example, the amplitude of a PPG signal may change depending on the blood volume of the user’s tissue. The blood volume in arteries may be greater during the systolic phase than the diastolic phase of the cardiac cycle. Changes in the PPG signal amplitude may indicate changes in the blood-flow volume based on the intensity of reflected light.

[0035] In one example implementation, the PPG sensor may include one or more of the following: an infrared sensor and / or a red-light sensor, among other possibilities.5.1.1 Example PPG Waveform

[0036] FIG. 2 illustrates an example PPG waveform of a PPG signal detected by the sensor 104, when the device 100 is correctly oriented on the user. The PPG waveform may include one or more pulses. Each pulse may have a pulse wave duration dl. The pulse wave duration dl may correspond to a cardiac cycle, including a systolic phase pl of the cardiac cycle and a diastolic phases p2 of the cardiac cycle. The pulse may have a systolic peak ml and a diastolic peak m2.

[0037] As shown in FIG. 2, the PPG signal may have a direct current (DC) component representing a steady part of the PPG signal, and an alternating current (AC) component representing a pulsatile part of the PPG signal. The DC component may correspond to the reflected optical signal from the user’s tissue. The DC component may depend on the structure of the user’s tissue, and may also depend on the average volume of both the arterial and venous blood. The DC component may change slowly with respiration. The AC component may fluctuate according to changes in the blood volume that occur between the systolic and diastolic phases of the cardiac cycle. The fundamental frequency of the AC component may depend on the heart rate (HR) and may be superimposed onto the DC component. The AC value may correspond to a vertical distance between the peak ml and a baseline bl where the troughs tl and t2 reside. The amplitude of the troughs tl, t2 may represent the base value or the DC value of the PPG signal.5.1.2 Correct Orientation vs. Incorrect Orientation

[0038] FIG. 3 A illustrates an application of the device 100 to measure a PPG signal at the user’s finger. The device 100 may be secured to the user via a bandage 109 or other band, belt, strap or sleeve. As shown in FIG. 3 A, when the device 100 is in a correct position andorientation, the contact surface 106 for sensing may be in direct contact with the user, while the non-contact surface 108 may have no contact with the user.

[0039] FIG. 3B illustrates and example of the device 100 in an incorrect orientation (in this example a reverse orientation) but in a correct position, at which the non-contact surface 108 is in direct contact with the user, while the contact surface 106 for sensing has no contact with the user. When the device 100 is in an incorrect orientation, the device 100 may send a sensing signal (e.g., light) to the atmosphere or otherwise away from the user rather than toward the user’s tissue. In examples, the device 100 may be considered to be in the incorrect orientation, such as when an impractical amount (e.g., >50% (greater than 50 percent)) of the sensing signal (e.g., light) is directed to the atmosphere or otherwise away from the user rather than toward the user’s tissue, when the sensor does not reliably perform PPG, even though it may be providing sensor data indictive of at least some physiological sensing since the user may be wearing the sensor, albeit incorrectly. Alternatively put, the device 100 may be considered to be in the incorrect orientation, such as when an insufficient amount (e.g., <50% (less than 50 percent)) of the sensing signal is reflected from the the user’s tissue and sensed by the sensor, when the sensor does not reliably perform PPG, even though it may be providing sensor data indictive of at least some physiological sensing since the user may be wearing the sensor, albeit incorrectly. In some incorrect orientations, the sensing device may be mounted generally towards the user but may still be mounted in a way that the result sensing signal is unsuitably directed at the user’s skin. For example, a mounted sensor may be directed at the user’s finger at an unsuitable angle, or directed at a user’s finger (or other body part) in the vicinity of the device other than the intended finger to which the device is applied, or it may be directed at a user’ s intended finger which may be fully / partially obstructed such as by the user’ s clothing, etc. Similarly, in some instances it may be in an incorrect orientation because it is not in an optimal sensing location such that all or part of the sensor is sensing on a location that is away from the optimal sensing location. As a result, when the device 100 is in the incorrect orientation (e.g., reverse position), PPG morphology may distinctly differ from that detected at the correct orientation. Such incorrect orientation may cause the sensing signal to be characterizable as, or have, a signal with an insufficient signal-to-noise content for a determination or evaluation as described herein. That is, when in suboptimal or incorrect orientation, the physiological component from the user in the sensor signal may be low but the sensor signal would otherwise be dominated by noise. The noise may mainly be attributable to the reflected light on a possible set of surfaces that do not cause an optimal physiological (e.g.,PPG) signal. For example, slight movements by the patient, or indeed even movement in the patient’s skin due to blood pulses, can result in small fluctuations in this noise signal.

[0040] For example, FIGS. 4A-B illustrate a comparison between the PPG waveforms detected by the device 100 at the correct orientation and an incorrect orientation that is a reverse orientation. FIG. 4A illustrates the PPG waveform detected at the correct orientation, while FIG. 4B illustrates the PPG waveform detected at the reverse orientation. Both figures may have similar scale in time and amplitude. When the device 100 is in the incorrect, e.g., reverse, orientation, any detected PPG signal may be regarded as, or dominated by, noise. Such noise may be attributed to slight movement in the user’s tissue as caused by blood pulse. Such movement may alter the reflected light slightly, which, in turn, may result in a PPG signal with a low amplitude as shown in FIG. 4B. As shown in FIG. 4B, when the device 100 is incorrectly, e.g., reversely, applied, physiological PPG pulse waveforms are not likely to be detected, and any detected PPG signal may exhibit a much lower amplitude in comparison to that of the typical PPG signal when the sensor is appropriately mounted. An example of such a noisy signal from incorrect orientation is shown in FIG. 4B.

[0041] FIGS. 5A-B illustrate zoomed-out views of the PPG waveforms detected by the device 100 at the correct orientation and the example reverse orientation, when the user is moving. FIGS. 5A-B have different amplitude scales. FIG. 5A illustrates the PPG waveform detected at the correct orientation, while FIG. 5B illustrates the PPG waveform detected at the reverse orientation. When the device is in the reverse orientation, the sensor 104 may not be in contact with the user. As a result, the sensor 104 may be much more sensitive to changes in light reflection when the patient is moving, resulting in large swings in DC values as shown in FIG. 5B.

[0042] In some implementations, any PPG signal collected by the device 100 in an incorrect orientation such as a reverse orientation, may be marked or deemed as invalid.

[0043] In some implementations, a processor 114 of the device 100 may perform an orientation determination of the wearing of the device 100 and activate a signal of the device such as an incorrect orientation indicator light or a correct orientation indicator light on the device 100 based on the determination, to provide the user with an indication of proper or correct orientation or improper or incorrect orientation such as to suggest a need for change in orientation. Optionally, such an indication (e.g., by a light and / or on a display) may be on an output component or user interface of the system 200 or other external system, based on a determination of any of the processors described herein, such as the processor 214. Thus, anelectronic message may be generated by a processor described herein and provided to the user based on an orientation detection described herein to advise the user to adjust the orientation of the sensor to improve the screening process with the sensor.5.1.3 Components of Wearable Device

[0044] Referring to FIG. 6, aside from the sensor 104 mentioned earlier and one or more optional indicators, the device 100 may include one or more of the following: an accelerometer 110 configured to generate an accelerometer signal, memory 112, one or more processors 114 and a network interface 116.

[0045] The network interface 116 may transmit data, such as data recorded by the sensor 104 and the accelerometer 110, to a system 200 for further analysis. Detailed discussion of the system 200 is provided below.5.2 SYSTEM 200

[0046] The system 200 may determine orientation of the device 100. For example, the system 200 may detect whether the device 100 is in the correct orientation or an incorrect orientation such as a reverse orientation, based on data provided by the device 100.

[0047] The system 200 may include memory 212, one or more processors 214 and a network interface 216. The memory 212 may store data received from the device 100, including but not limited to, the PPG signal, and the accelerometer signal. The memory 212 may also store data derived from the PPG and / or accelerometer signals. Such derived data may include, for example, artifacts and activity data. The memory 212 may include computer program code configured to cause the processor(s) 214 to perform any one or more functions such as any one or more of a physiological condition evaluation 220, a correct / incorrect sensor orientation detection 222, and an attachment determination 224. Detailed discussion of each function is described in more detail herein.

[0048] Although such functions are generally described herein in relation to particular processors of either the device 100 or the system 200, it will be understood that in some implementations, any or each of the functions described herein may be performed in any one or more of these processors such as when a memory associated with such a processor includes the program code for such a processor to perform the function(s). For example, any or all of the operations / steps of the functions performed by the processor(s) 214 as described herein may be performed by the processor(s) 114 and vice versa.5.2.1 Physiological Condition Evaluation 220

[0049] In some implementations, the processor(s) 214 may process the PPG signal to evaluate the physiological condition of the user 101. From the PPG signal, the processor(s) 214 may derive SpCh, pulse rate (PR), and changes in peripheral arterial tone. The processor may analyze the concurrence of drops in SpCh, surges in pulse rate, and increases in peripheral arterial tone. Based on the peripheral arterial tone, the processor(s) 214 may detect an occurrence of a sleep-related event of the user. The sleep-related event may include, but not limited to, a sleep-disordered breathing event such as an apnea and / or hypopnea event, snoring, or a limb movement.

[0050] Before using the PPG signal to evaluate the physiological condition of the user 101, the processor(s) 214 may determine whether the PPG signal is valid. Such determination may include determining whether the PPG signal, as a whole or one or more portions thereof, is valid. If the PPG signal is collected when the device 100 is in an incorrect orientation such as the reverse orientation, the PPG signal, or portion thereof, may be marked or deemed as invalid for purposes of elevating the physiological conditions of the user 101.

[0051] In some implementations, the system 200 and / or the processor(s) 214 may not perform evaluation of the physiological condition of the user 101. Rather, an external system may perform such evaluation. The system 200 may provide determination of orientation of the device 100 to the external system. If the system 200 informs the external system that the device 100 is in the incorrect orientation, e.g., reverse, orientation at the time when the PPG signal is detected by the device 100, the external system may discard such PPG signal when evaluating the physiological condition of the user 101.5.2.2 Incorrect Orientation Application Determination 222

[0052] To determine whether the device 100 is in an incorrect orientation such as the reverse orientation illustrated in FIG. 3B, the processor(s) 214 may determine a perfusion measure from the PPG signal. The perfusion measure may be compared to one or more thresholds. For example, if the perfusion measure falls below one or more thresholds, such as a predetermined threshold, the device 100 may be deemed in an incorrect orientation such as the reverse orientation. Such a threshold(s) may be determined empirically, such as from user population studies (optionally matched demographically with the user), and may optionally be chosen to represent an unrealistic perfusion level such that it may be attributed to an incorrect sensor orientation. Such evaluations of perfusion in the PPG signal may be based on different evaluation periods (e.g., different quantities of PPG signal data). For example, an evaluationmay be based on a period of time of the data on the order of minutes or hours, such as ten minutes, twenty minutes or other time periods. Some such evaluations may be based on shorter or longer time periods of data such as to provide more contemporaneous indications of the orientation of the sensor for more immediate adjustment / correction of sensor orientation before a relatively long sensing / screening / diagnostic session and / or for a more complete indication after a sensing / screening / diagnostic session with the sensor.

[0053] In some implementations, the perfusion measure may be determined or derived from other measures such as a perfusion measure that is based on an indication of prominence, such as the prominence of a peak of the PPG signal. The prominence of the peak may indicate how much a peak stands out from the surrounding baseline of the PPG signal due to its intrinsic height and its location relative to other peaks. The prominence of the peak may be defined as the vertical distance between the peak and its lowest contour line. The lower the prominence of a peak, the lower the perfusion. Low values for such prominences may indicate that peaks are less pronounced, signalling incorrect or reverse application of the device 100. On the other hand, high values for such prominences may indicate that the device 100 is in the correct orientation for normal use. Other indicators of prominence, which may serve as a suggestion of perfusion, may include any of the following: a peak amplitude of the PPG signal, an AC value of the peak of the PPG signal, a peak-to-base ratio of the PPG signal, a ratio between AC and DC values of the peak of the PPG signal. As such, the perfusion measure may be determined based on calculating one or more of the following: a peak amplitude of the PPG signal, an AC value of the peak of the PPG signal, a peak-to-base ratio of the PPG signal, and a ratio between AC and DC values of the peak of the PPG signal. Moreover, a perfusion measure may be an average or median of other perfusion measures.

[0054] In some implementations, the perfusion measure may refer to a median prominence of a plurality of peaks of the PPG signal determined from one or more of the following: a median peak amplitude of the PPG signal, a median AC value of the PPG signal, a median peak-to-base ratio of the PPG signal, and a median ratio between AC and DC values of the PPG signal. As described herein, a median may be a median of instantaneous measures (e.g., perfusion or prominence) from the PPG signal from an entire recording session or from measures of a portion of the recording session that includes a plurality of peaks of the signal. A median may be a moving median derived from a plurality of peaks of a fixed time window size that moves along of samples of the signal from a recording session.

[0055] In some implementations, the processor(s) may receive the PPG signal after a measurement session (such as sleep and / or screening and / or diagnostic session) of the user with the device 100, the processor(s) may determine the median prominence (or median perfusion) from the PPG signal collected during the entire session of the user. If the median prominence (or median perfusion) is below the predetermined threshold, the device 100 may be deemed in the incorrect orientation during the user’s measurement session, e.g., sleep and / or screening / diagnostic session. As such, the PPG signal collected during the session, in which the median prominence is below the predetermined threshold, may be marked or deemed as invalid, and may not be relied on for evaluating physiological conditions of the user.

[0056] Similarly, a portion of the PPG signal less than an entire recording session, with some plurality of peaks collected during that particular portion of the session, may be marked or deemed as invalid when its median perfusion or median prominence is below a predetermined threshold. Still further, in some cases, a portion of the PPG signal with one peak may be marked or deemed as invalid, if an instantaneous perfusion measure or instantaneous prominence measure determined for the one peak of that portion of the PPG signal is below a predetermined threshold. When a sufficient number of such portions (e.g., either single peak portions or multi-peak portions) of the signal relative to the total number of portions forming the whole signal of the session (e.g., greater than 50 percent, 60 percent, 70 percent, etc.) are determined to be invalid, the device 100 may be deemed in the incorrect orientation during the user’s measurement session. In such event, the entire recording session may not be relied on for evaluating physiological conditions of the user. Alternatively, in some implementations, the particular portions marked as invalid may not be relied on for evaluating physiological conditions of the user and the remaining portions not marked invalid may be relied upon for evaluating physiological conditions of the user.

[0057] Optionally, the aforementioned implementations using median measures (e.g., median perfusion or median prominence) may instead, or additionally, be implemented with average measures. For example, in yet further implementations, the perfusion measure may refer to an average prominence of a plurality of peaks of the PPG signal determined from one or more of the following: an average peak amplitude of the PPG signal, an average AC value of the PPG signal, an average peak-to-base ratio of the PPG signal, and an average ratio between AC and DC values of the PPG signal.

[0058] In some implementations, the predetermined threshold(s) may have a suitable numerical value in relation to the implemented range of the signal, and which may be determined empirically.

[0059] In some implementations, the processor(s) 214 may identify a period of time, from the PPG signal, that the device 100 is in an incorrect, e.g., reverse, orientation. The processor(s) 214 may exclude the PPG signal within the identified period of time from physiological condition evaluation 220.

[0060] In some implementations, after determining orientation of the device, the processor may generate an output to the user or an external system indicating the orientation of the device. For example, the output may indicate that the device 100, at the time when the PPG signal is detected by the device 100, is in a correct orientation or an incorrect orientation such as a reverse orientation. As previously noted, such output may be generated by any of the processors such as with a light indicator, display or electronic message.

[0061] In some implementations, the system 200 and / or the processor(s) 214 may not perform physiological condition evaluation 220 of the user 101. Rather, an external system may perform such evaluation. The system 200 may provide determination of orientation of the device 100 to the external system. If the system 200 informs the external system that the device 100 is in an incorrect orientation at the time when the PPG signal is detected by the device 100, the external system may discard such PPG signal, or portion thereof, when performing physiological condition evaluation.5.2.3 Attachment Determination 224

[0062] In some implementations, the processor(s) 214 may process the accelerometer signal measured by the device 100 to determine whether the user is or was wearing the device 100 or whether the device 100 or the sensor 104 of the device 100 is physically attached to the user 101. The accelerometer may record activity signal in a time period during which a PPG signal is also recorded.

[0063] The accelerometer signal may indicate an activity of the user 101, such as body movements. When the accelerometer signal indicates no activity, the processor(s) 214 may determine that the device 100 is not attached to or worn by the user. The processor(s) 214 may identify, from the accelerometer signal, a period of time that has no activity, and may generate an output indicating that the PPG signal corresponding to that period of time is invalid. As such, an accelerometer signal may be implemented for discarding PPG sensor signals. One ormore thresholds may be compared with the accelerometer signal for such evaluations. Such thresholds may be empirically determined. In some implementations, an accelerometer signal with high or excessive indications of movement or activity may serve as a basis to discard sensor signals, such as for avoiding performing a reverse orientation detection which may be unpractical in light of expected noisiness of the PPG signal when there is excessive motion activity. Moreover, an accelerometer signal may be combined with other signals, such as a measure of perfusion as previously discussed, to discard sensor signals where such signals suggest, such as by comparison with one or more thresholds, an incorrect orientation (e.g., no or low perfusion and no or low movement).

[0064] On the other hand, in some implementations, when the accelerometer signal indicates positive activity, the device 100 may be deemed attached to or worn by the user. In such cases, such a signal can serve as a basis to justify an assessment for incorrect orientation detection when normal activity is detected, since the normal activity suggests that the sensor is at least worn by a user, even if incorrectly. Normal activity may be detected when, for example, an activity measure, such as a count or total for a recording session or a median or average of counts from a plurality of discrete epochs of a session, etc., for the accelerometer signal is in an expected or suitable range determined by assessment of the measure with one or more thresholds. Such threshold(s) may be empirically derived.

[0065] Thus, n some implementations, the processor(s) 214 may perform the correct / incorrect sensor orientation detection 222 after determining that the user is or was wearing the device 100. Alternatively, a complete absence of movement in the activity signal can be taken as an indication that the sensor is not attached to the user and therefore serve as a basis to determine that the sensor is improperly attached, such as not attached at all.

[0066] In some implementations, the processor(s) 214 may identify, from the accelerometer signal, a period of time during which the user wears the wearable device. The processor(s) 214 may then determine, from the PPG signal, whether the device 100 is in a correct or incorrect orientation (e.g., a reverse orientation) during the identified period of time. In some implementations, the processor(s) 214 may then determine, from the PPG signal, that the device 100 is in an incorrect orientation during the identified period of time. The processor may then exclude the PPG signal within the identified period of time from physiological condition evaluation 220 and / or generate the output indicate to the user the detected incorrect sensor orientation. Otherwise, if the processor 214 determines that the sensor is not in the incorrect orientation or in the correct orientation, the processor 214 may then proceed toevaluate the PPG signal, such as for a screening session, to detect sleep disordered breathing events from the PPG signal.

[0067] In the case that the processor 114 of the device 100 performs the attachment determination and / or the incorrect / correct sensor orientation detection, the processor 114 may first determine that the user is wearing the device from the activity signal. If so, the processor(s) 114 may then determine, from the PPG signal, whether the device 100 is in a correct or incorrect sensing orientation (e.g., a reverse orientation). Such a determination may be repeatedly performed. When the processor(s) 114 determines, from the PPG signal, that the device 100 is in an incorrect orientation, the processor may then exclude the PPG signal from physiological condition evaluation 220 and / or generate the output as previously described to indicate to the user the detected incorrect sensor orientation. Otherwise, if the processor 114 determines that the sensor is not in the incorrect orientation or is in the correct orientation, the processor 114 may then proceed to, or continue to, record the PPG signal in a session and / or employ the PPG signal for further analysis post-session as described herein. In some such implementations, the incorrect / correct sensor orientation determination may be repeatedly performed during such a session. Optionally, the processor 114 may thereafter evaluate the PPG signal for sleep disordered breathing events or transmit the PPG signal for such as for an evaluation of the signal by another one or more of the processors described herein when correct orientation is determined or repeatedly determined.

[0068] In some implementations, one or more additional sensors, such as in the device 100 or providing signals to a processor for evaluating an incorrect or correct orientation, may be utilized for the sensor orientation and / or attachment evaluation. For example, a signal from a temperature sensor, such as one measuring user temperature from a housing of the device 100, may provide an indication that the device is mounted, or correctly mounted, on user based on an evaluation of the temperature signal. For example, if a temperature sensor on an intended user contact surface side of the sensor provides a temperature signal corresponding to human contact over time, such a signal can provide an indication of correct sensor orientation, which may optionally be combined with any of the other detection criteria described herein (e.g., accelerometer signal and / or perfusion measure evaluation). Otherwise, a low temperature relative to human body temperature, may be taken as an indication of incorrect sensor orientation, such as when there is also a determination of a low perfusion measure. A detected change in temperature from such a temperature sensor, or a change or drop in temperature froman average temperature from a period of time, may be taken as an indication of detachment. A similar evaluation may be implemented with a signal from a galvanic skin response sensor.5.2.4 Other Example implementations

[0069] In some implementations, the system may include any one or more of the following: a smart phone, a server, a base station, a laptop, and a tablet, among other possibilities, any of which may have a processor 214 of the system.

[0070] For example, the system 200 may include a smart phone. After a measurement session of a user, the device 100 may transmit the recorded data to the smart phone via, for example, Bluetooth. The smart phone may perform any one or more of the functions including: physiological condition evaluation 220, correct / incorrect sensor orientation detection 222, and attachment determination 224. Thereafter, the smart phone may display any result or output described herein to the user such as through its graphical user interface.

[0071] In some implementations, the system may include a smart phone and a server. After a measurement session of a user, the device 100 may transmit the recorded data to the smart phone via, for example, Bluetooth. The smart phone may then transmit the received data to the server via a wireless connection. The server may perform any one or more of the functions including: physiological condition evaluation 220, correct / incorrect sensor orientation detection 222 and attachment determination 224. Thereafter, the server may send any result back to the smart phone for display to the user 101.

[0072] In some implementations, the device 100 may be part of the system 200.

[0073] In some implementations, as the device 100 records the PPG signal and the accelerometer signal, the device 100 may transmit the recorded data to the system 200 in real time or quasi-real time, or during a setup session prior to sleep. The system 200 may perform any one or more of following: physiological condition evaluation 220 correct / incorrect sensor orientation detection 222, and attachment determination 224. For example, as the user sets up the device 100 before sleep, the system 200 may determine whether the device 100 is positioned correctly on the user. In the event that the device is in a reverse position, the system may provide timely notification to the user 101 through a graphical user interface, such as the graphical user interface of a smart phone.

[0074] In some implementations, the processor(s) 214 may receive recorded data from the device after a measurement session of the user. The system 200 may in turn perform any one or more of the following: physiological condition evaluation 220, correct / incorrect sensororientation detection 222, and attachment determination 224, based on the PPG signal and the accelerometer signal recorded during the session. For example, after the session, the system 100 may determine whether the device 100 is correctly positioned for the session. In the event that the system 100 detects correct / correct orientation, the system 100 may output a message to the user advising the user that the PPG signal collected during the session is invalid due to incorrect orientation, and recommend the user to conduct one more sessions with the correct orientation of the device.5.2.5 Flow Chart5.2.5.1 Example Process Flow

[0075] FIG. 7 illustrates an example process performed by the processor(s) 214 such as for performing correct / incorrect sensor orientation detection 222. At 702, the processor(s) 214 may optionally identify the user’s activity from the accelerometer signal provided by the device 100, such as when excessive activity is likely to introduce noise into the PPG signal, or when the user’s activity indicates that the user is wearing the device 100, etc. Based on such user’s activity, at 704, the processor(s) 214 may identify one or more active regions 705 in the PPG signal that correspond in time with the detected activity regions of the accelerometer signal so that the corresponding regions of the PPG signal may be disregarded from further orientation evaluation if excessive activity is detected, or include the corresponding regions of the PPG signal for further orientation evaluation the user’s activity indicates that the user is wearing the device 100. At 706, the processor(s) 214 may calculate one or more perfusion measures of one or more peaks of the PPG signal. At 708, the processor(s) 214 may discard perfusion measures that correspond with the excessively active region(s) 705 of the PPG signal. At 710, the processor(s) 214 may determine a median perfusion 712 from the remaining perfusion measures 709. At 714, the processor(s) 214 may compare the median perfusion 712 to a threshold. In one example, the threshold may have a numerical value, such as 250. At 716, if the median perfusion 712 is less than the threshold, the processor(s) 214 may output an indicator indicating that the device 100 is in an incorrect orientation such as a reverse orientation at the time when the PPG signal is recorded by the device 100. On the other hand, at 718, if the median perfusion 712 is equal to or greater than the threshold, the processor(s) 214 may output an indicator indicating that the device 100 is in a correct or correct orientation at the time when the PPG signal is recorded by the device 100.5.2.5.1 Another Example Process Flow Chart

[0076] FIG. 8 illustrates another example flow chart for a method for determining orientation of a wearable device. At 802, at least one processor may receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device. The wearable device may have a correct orientation or position at which the PPG sensor touches the user, and one or more incorrect orientations such as a reverse orientation at which the PPG sensor faces away from the user. At 804, the at least one processor may determine whether the wearable device is in a correct or an incorrect orientation. For example, the at least one processor may determine a perfusion measure from the PPG signal. The at least one processor may determine that the wearable device is not in a correct orientation or is in an incorrect orientation when the perfusion measure falls below a threshold.

[0077] In examples, the at least one processor may determine the perfusion measure based on a prominence of a peak of the PPG signal.

[0078] In examples, the at least one processor may derive a peripheral arterial tonometry signal from the PPG signal to detect an occurrence of a sleep-related event of the user.

[0079] In examples, the PPG signal may be measured at a finger of the user.

[0080] In examples, the receiving step may include receiving the PPG signal from the wearable device via a wireless connection.

[0081] In examples, the PPG sensor may include an infrared sensor and / or a red-light sensor.

[0082] In examples, the at least one processor may receive an accelerometer signal from the wearable device to determine whether the user wears the wearable device.

[0083] In examples, the step of determining whether the wearable device is in an incorrect position comprises a reverse orientation determination and may occur after determining that the user wears the wearable device.

[0084] In examples, the at least one processor may identify, from the accelerometer signal, a period of time during which the user wears the wearable device. The at least one processor may determine, from the PPG signal, whether the wearable device is in the abcorrect orientation during the identified period of time.

[0085] In examples, the prominence may include a median prominence or an average prominence of a plurality of peaks of the PPG signal.

[0086] In examples, the at least one processor may generate an output to the user indicating that the wearable device is in the reverse position.5.3 COMPONENTS

[0087] The memory 112 and / or the memory 212 may be a non-transitory computer- readable medium configured to store one or more algorithms and / or methods described herein in the form of computer program instructions and / or information / data described herein. Thus, the memory 112 and / or 212 may include one or more of the following: non-volatile memory, battery powered static random-access memory (RAM), and volatile RAM. The memory 112 and / or 212 may be in the form of electrically erasable programmable read-only memory (EEPROM) or NAND flash and / or any other secondary data storage device(s). Such memory may also include, for example one or more databases, which may be remote or collocated with the processor(s) 114 and / or 214. Thus, such memory or databases may optionally be remotely accessible, for example, via the network interface 116 and / or 216.

[0088] The processor(s) 114 and / or the processor(s) 214 may be a dedicated electronic circuit or an application-specific integrated circuit. The processor(s) 114 and / or 214 may be formed with discrete electronic components. The processor(s) 114 and / or 214 may include a dedicated motor control integrated circuit. The processor(s) 114 and / or 214 may include one or more processors or microprocessors, configured to execute one or more computer programs stored in the memory 112 and / or 212.

[0089] The network interface 116 and / or the network interface 216 may include a wired and / or wireless communication interface(s). The wired communication interface may include a wired protocol, to allow, for example, communication via a network, such as an internet or the Internet via Ethernet or optical fibre. The wireless communication interface may include one or more transceivers using wireless protocols such as infrared protocol, cellular, Bluetooth, WIFI, Bluetooth LE, and Bluetooth BLE (5.0) with GATT profile, among other possibilities. The wireless communication interface may be a low power communication interface, e.g., a Bluetooth Low Energy, BLE, wireless interface. In one example, the network interface may allow wireless transmission between the device 100 and the system 200. For instance, the processor(s) 214 may receive the PPG signal and / or the accelerometer signal measured by the sensor 104 and / or the accelerometer 110 of the device 100 via a wireless connection.5.4 TECHNICAL ADVANTAGES

[0090] The present technology may detect incorrect orientation of the wearable device, and timely inform the user to adjust the wearable device. The present technology may improve overall accuracy of evaluating physiological conditions of users, by identifying, filtering and / oreliminating sensing signals such as PPG signals that are affected by the improper application of the wearable device onto a user.5.5 GLOSSARY

[0091] For the purposes of the present technology disclosure, in certain forms of the present technology, one or more of the following definitions may apply. In other forms of the present technology, alternative definitions may apply.

[0092] Apnea. According to some definitions, an apnea is said to have occurred when flow falls below a predetermined threshold for a duration, e.g. 10 seconds. An obstructive apnea will be said to have occurred when, despite patient effort, some obstruction of the airway does not allow air to flow. A central apnea will be said to have occurred when an apnea is detected that is due to a reduction in breathing effort, or the absence of breathing effort, despite the airway being patent. A mixed apnea occurs when a reduction or absence of breathing effort coincides with an obstructed airway.

[0093] Hypopnea. According to some definitions, a hypopnea is taken to be a reduction in flow, but not a cessation of flow. In one form, a hypopnea may be said to have occurred when there is a reduction in flow below a threshold rate for a duration. A central hypopnea will be said to have occurred when a hypopnea is detected that is due to a reduction in breathing effort. In one form in adults, either of the following may be regarded as being hypopneas:(i) a 30% reduction in patient breathing for at least 10 seconds plus an associated 4% desaturation; or(ii) a reduction in patient breathing (but less than 50%) for at least 10 seconds, with an associated desaturation of at least 3% or an arousal.5.6 OTHER REMARKS

[0094] A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in Patent Office patent files or records, but otherwise reserves all copyright rights whatsoever.

[0095] Unless the context clearly dictates otherwise and where a range of values is provided, it is understood that each intervening value, to the tenth of the unit of the lower limit, between the upper and lower limit of that range, and any other stated or intervening value in that stated range is encompassed within the technology. The upper and lower limits of theseintervening ranges, which may be independently included in the intervening ranges, are also encompassed within the technology, subject to any specifically excluded limit in the stated range. Where the stated range includes one or both of the limits, ranges excluding either or both of those included limits are also included in the technology.

[0096] Furthermore, where a value or values are stated herein as being implemented as part of the technology, it is understood that such values may be approximated, unless otherwise stated, and such values may be utilized to any suitable significant digit to the extent that a practical technical implementation may permit or require it.

[0097] Furthermore, “approximately”, “substantially”, “about”, or any similar term used herein means + / - 5-10% of the recited value.

[0098] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this technology belongs. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present technology, a limited number of the exemplary methods and materials are described herein.

[0099] When a particular material is identified as being used to construct a component, obvious alternative materials with similar properties may be used as a substitute. Furthermore, unless specified to the contrary, any and all components herein described are understood to be capable of being manufactured and, as such, may be manufactured together or separately.

[0100] It must be noted that as used herein and in the appended claims, the singular forms "a", "an", and "the" include their plural equivalents, unless the context clearly dictates otherwise.

[0101] All publications mentioned herein are incorporated herein by reference in their entirety to disclose and describe the methods and / or materials which are the subject of those publications. The publications discussed herein are provided solely for their disclosure prior to the filing date of the present application. Nothing herein is to be construed as an admission that the present technology is not entitled to antedate such publication by virtue of prior disclosure. Further, the dates of publication provided may be different from the actual publication dates, which may need to be independently confirmed.

[0102] The terms "comprises" and "comprising" should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced.

[0103] The subject headings used in the detailed description are included only for the ease of reference of the reader and should not be used to limit the subject matter found throughout the disclosure or the claims. The subject headings should not be used in construing the scope of the claims or the claim limitations.

[0104] Although the technology herein has been described with reference to particular examples, it is to be understood that these examples are merely illustrative of the principles and applications of the technology. In some instances, the terminology and symbols may imply specific details that are not required to practice the technology. For example, although the terms "first" and "second" may be used, unless otherwise specified, they are not intended to indicate any order but may be utilised to distinguish between distinct elements. Furthermore, although process steps in the methodologies may be described or illustrated in an order, such an ordering is not required. Those skilled in the art will recognize that such ordering may be modified and / or aspects thereof may be conducted concurrently or even synchronously.

[0105] It is therefore to be understood that numerous modifications may be made to the illustrative examples and that other arrangements may be devised without departing from the spirit and scope of the technology.

Claims

6 CLAIMS1. A system for determining orientation of a wearable device on a user, comprising: at least one processor configured to: receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device, the wearable device having a correct orientation, and an incorrect orientation; and determine whether the wearable device is in the correct orientation or the incorrect orientation, including: determining a perfusion measure from the PPG signal; and determining, based on the perfusion measure, that the wearable device is in the correct orientation or the incorrect orientation.

2. The system of claim 1 wherein the determining that the wearable device is in the correct orientation or the incorrect orientation is based on a comparison between the perfusion measure and a threshold.

3. The system of claim 2 wherein, when the perfusion measure is below the threshold, the wearable device is determined to be in the incorrect orientation.

4. The system of claim 2 wherein, when the perfusion measure is above the threshold, the wearable device is determined to be in the correct orientation.

5. The system of any one of claims 1 to 4, wherein the incorrect orientation comprises the wearable device being mounted on the user with the PPG sensor directed away from the user.

6. The system of any one of claims 1 to 5, wherein the perfusion measure is determined based on a prominence of a peak of the PPG signal.

7. The system of any one of the preceding claims, wherein the at least one processor is configured to derive a peripheral arterial tonometry signal from the PPG signal to detect an occurrence of a sleep-related event of the user.

8. The system of any one of the preceding claims, wherein the PPG signal is measured at a finger of the user.

9. The system of any one of the preceding claims, wherein the at least one processor is configured to receive the PPG signal from the wearable device via a wireless connection.

10. The system of any one of the preceding claims, wherein the PPG sensor includes an infrared sensor and / or a red-light sensor.

11. The system of any one of the preceding claims, further comprising the wearable device.

12. The system of any one of the preceding claims, wherein the at least one processor is configured to receive an accelerometer signal from the wearable device to determine whether the user wears the wearable device.

13. The system of claim 12, wherein the at least one processor is configured to determine whether the wearable device is in the correct orientation or the incorrect orientation after determining that the user wears the wearable device.

14. The system of either claim 12 or 13, wherein the at least one processor is configured to: identify, from the accelerometer signal, a period of time during which the user wears the wearable device; and determine, from the PPG signal, whether the wearable device is in the correct orientation or the incorrect orientation during the identified period of time.

15. The system of any one of the preceding claims, wherein the perfusion measure includes a median prominence or an average prominence of a plurality of peaks of the PPG signal.

16. The system of any one of the preceding claims, wherein the at least one processor is configured to generate an output to the user indicating that the wearable device is in the incorrect orientation.

17. The system of any one of the preceding claims, wherein the at least one processor is configured to receive the PPG signal from the wearable device during or after a measurement session of the user.

18. A method for determining orientation of a wearable device on a user, comprising: receiving, by one or more processors, a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device; and determining, by the one or more processors, whether the wearable device is in a correct orientation or an incorrect orientation, including: determining a perfusion measure from the PPG signal; and determining, based on the perfusion measure, that the wearable device is in the correct orientation or the incorrect orientation.

19. The method of claim 18 wherein the determining that the wearable device is in the correct orientation or the incorrect orientation is based on a comparison between the perfusion measure and a threshold.

20. The method of claim 19 wherein, when the perfusion measure is below the threshold, the wearable device is determined to be in the incorrect orientation.

21. The method of claim 19, wherein, when the perfusion measure is above the threshold, the wearable device is determined to be in the correct orientation.

22. The method of any one of claims 18 to 21, wherein the incorrect orientation comprises the wearable device being mounted on the user with the PPG sensor directed away from the user.

23. The method of any one of claims 18 to 22, wherein the determining the perfusion measure includes determining the perfusion measure based on a prominence of a peak of the PPG signal.

24. The method of any one of claims 18 to 23, further comprising: deriving, by the one or more processors, a peripheral arterial tonometry signal from the PPG signal to detect an occurrence of a sleep-related event of the user.

25. The method of any of claims 18 to 24, wherein the PPG signal is measured at a finger of the user.

26. The method of any one of claims 18 to 25, wherein the receiving includes: receiving the PPG signal from the wearable device via a wireless connection.

27. The method of any one of claims 18 to 26, wherein the PPG sensor includes an infrared sensor and / or a red-light sensor.

28. The method of any one of claims 18 to 27, further comprising: receiving, by the one or more processors, an accelerometer signal from the wearable device to determine whether the user wears the wearable device.

29. The method of claim 28, wherein the determining whether the wearable device is in the correct orientation or the incorrect orientation occurs after determining that the user wears the wearable device.

30. The method of claims 28 or 29, further comprising: identifying, by the one or more processors, from the accelerometer signal, a period of time during which the user wears the wearable device; and determining, by the one or more processors, from the PPG signal, whether the wearable device is in the correct orientation or the incorrect orientation during the identified period of time.

31. The method of any one of claims 18 to 30, wherein the prominence includes a median prominence or an average prominence of a plurality of peaks of the PPG signal.

32. The method of any one of claims 18 to 31, further comprising: generating an output to the user indicating that the wearable device is in the incorrect orientation.

33. A processor-readable medium, having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 18 to 32.

34. A processor-readable medium, having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to determine orientation of a wearable device, the processor-executable instructions comprising: instructions to receive a photoplethysmography (PPG) signal measured by a PPG sensor of the wearable device; and instructions to determine whether the wearable device is in a correct orientation or an incorrect orientation, including: instructions to determine a perfusion measure from the PPG signal; and instructions to generate, based on the perfusion measure, an indication that the wearable device is in the correct orientation or the incorrect orientation.

Images