A wearable emotion monitoring device trained using fMRI brain scan data.

Abstract

A system for tracking human emotions in real time, comprising a wearable device including multiple sensors, one or more processors, and memory. The system measures multiple physical or chemical parameters of the wearer by one or more sensors, the multiple physical or chemical parameters representing the wearer's autonomic nervous system activity. The system processes the multiple measured parameters using a machine learning-trained algorithm to generate output data, the output data including a display of the wearer's positive emotional activity. The machine learning-trained algorithm is trained and the wearable sensor is configured based on brain scan data and wearable sensor data collected from the subject during the recall of positive emotional experiences.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims the benefit of priority of U.S. Provisional Patent Application No. 63 / 505,900, filed on June 2, 2023, the content of which is hereby incorporated by reference in its entirety.

[0002] The present disclosure generally relates to wearable devices, and more specifically, to wearable biosensor emotion monitoring devices trained using fMRI brain scan data.

Background Art

[0003] According to research, the areas of positive human emotions are shown to include nine different emotion types: enthusiasm, sexual desire, approval / pride, nurturing love / family love, satisfaction, friendship, entertainment, joy, and gratitude. These emotions are generated from various combinations of one or more of the six reward systems: dopamine, testosterone, serotonin, oxytocin, cannabinoid, and opioid. Further, research has studied the ways in which certain emotional reactions in humans correlate with the activity of the autonomic nervous system, such as the patterns demonstrated by the intervals between heartbeats, pre - ejection period of the heart, skin conductance response, respiratory sinus arrhythmia, and mean arterial pressure.

Summary of the Invention

[0004] Despite research on the correlation between human emotional reactions and the activity of the autonomic nervous system, accurately monitoring human emotions (including positive human emotions) in real - time using physical and chemical sensor devices to monitor the activity of the autonomic nervous system and determine the emotional state therefrom has not yet been achieved.

[0005] Commercial fitness trackers use sensors that can detect body temperature, heart rate variability, pulse rate, maximum oxygen saturation (SpO2), respiratory rate, and / or skin conductivity (correlated with sweating). The main focus of these fitness trackers is to identify general fitness indicators and indicators related to sleep quality. However, existing fitness trackers and other existing wearables cannot accurately track emotional responses in real time because they cannot distinguish between various positive emotions or determine the intensity of positive emotional experiences.

[0006] Studies have shown that the nine positive emotions listed above can be accurately and effectively identified, distinguished from each other, and quantified using fMRI brain scan data (3T and 7T). However, relying on fMRI brain scan data to recognize emotional responses limits real-time emotion tracking to situations where the subject is fixed within the fMRI monitoring environment.

[0007] Therefore, there is a need for improved systems and methods for real-time monitoring of human emotional responses that enable accurate and effective real-time differentiation and quantification between different positive emotions. This specification discloses systems and methods that can address this need.

[0008] In some embodiments, a wearable device is provided that includes multiple sensors configured to measure the wearer's physical and chemical parameters, where the measured parameters represent the wearer's autonomic nervous system activity. The measured parameters can be analyzed on the wearable device or remotely (e.g., on an associated device or server) by one or more machine learning-trained algorithms, and information about the wearer's emotions can be determined based on the measured parameters. The determined information may include the identification and quantification of the user's emotional state and / or the user's emotional reward centers (e.g., neurotransmitters). The machine learning-trained algorithms can be trained on labeled training data, which includes (a) sensor data collected from physical and chemical sensors measuring the subject's autonomic nervous system activity, and / or (b) brain scan data collected from an fMRI device on the subject. The training data may be collected while the subject is experiencing and / or recalling an emotional state and may be labeled according to the subjective analysis / experience of the emotional state. One or more sensors on the wearable device may be further configured (e.g., calibrated) based on the training data. The determined information, which identifies and quantifies the wearer's emotions, may be stored, transmitted, used to generate one or more outputs, and / or used to trigger automated system functions.

[0009] In some embodiments, a system is provided for tracking human emotions in real time, the system comprising a wearable device including multiple sensors, one or more processors, and a memory storing instructions, the instructions being configured to cause the system to measure multiple physical or chemical parameters of a wearer by one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and to process the multiple measured parameters using a machine learning trained algorithm to generate output data, wherein the output data is configured to include a representation of the wearer's positive emotional activity.

[0010] In some embodiments, one or more sensors include sensors selected from a set including electrical activity sensors, photoplethysmography sensors, non-contact systems configured to measure arterial pulse, mechanical activity-based sensors, force cardiography sensors, seismocardiography sensors, ECG sensors, impedance cardiography sensors, sensors that detect skin electrical responses, pressure-based mean arterial pulse sensors, and ultrasonic sensors.

[0011] In some embodiments, the multiple measured parameters include parameters selected from a set that includes the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0012] In some embodiments, the display of the wearer's positive emotional activity includes a score that quantifies the user's emotions, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0013] In some embodiments, the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all of a set of emotions, including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0014] In some embodiments, the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0015] In some embodiments, the command is configured to cause the system to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including displayed visualizations, audio outputs, and haptic outputs.

[0016] In some embodiments, the command is configured to cause the system to: receive training data, which includes brain scan data showing the brain activity of one or more training subjects, the training data being labeled with information showing the positive emotional activity of one or more training subjects at or near the time the respective sensor data was collected; and use the training data to train a machine learning trained algorithm.

[0017] In some embodiments, the training data includes sensor data indicating multiple physical or chemical parameters of the training subject, where multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject, and the sensor data and brain scan data of the training data are recorded simultaneously.

[0018] In some embodiments, the command is configured to cause the system to: receive training data, which includes brain scan data showing the brain activity of one or more training subjects, the training data being labeled with information showing the positive emotional activity of one or more training subjects at or near the time the respective sensor data was collected; and configure one or more of the sensors of a wearable device based on the training data.

[0019] In some embodiments, a method is provided for tracking human emotions in real time, the method being performed in a system including a wearable device including a plurality of sensors, one or more processors, and memory, the method comprising: measuring a plurality of physical or chemical parameters of a wearer by one or more sensors, the plurality of physical or chemical parameters indicating the wearer's autonomic nervous system activity; and processing the plurality of measured parameters using a machine learning trained algorithm to generate output data, the output data including a representation of the wearer's positive emotional activity.

[0020] In some embodiments, a non-temporary computer-readable storage medium is provided that stores instructions for tracking human emotions in real time, and the instructions are executed by one or more processors of a system including a wearable device including multiple sensors, causing the system to: measure multiple physical or chemical parameters of the wearer indicating the wearer's autonomic nervous system activity using one or more sensors; and process the multiple measured parameters using a machine learning-trained algorithm to generate output data including a display of the wearer's positive emotional activity.

[0021] In some embodiments, a wearable device is provided for tracking human emotions in real time, the wearable device comprising a plurality of sensors, one or more processors, and memory storing instructions, the instructions being configured to cause the system to: measure a plurality of physical or chemical parameters of the wearer indicating the wearer's autonomic nervous system activity by one or more sensors; process the plurality of measured parameters using a machine learning trained algorithm to generate output data, wherein the output data includes a display of the wearer's positive emotional activity, the machine learning trained algorithm includes brain scan data indicating the brain activity of one or more trained subjects, the training data is labeled with information indicating the positive emotional activity of one or more trained subjects at or near the time the respective sensor data was collected, and provide the wearer with the output indicating the determined positive emotional activity of the wearer.

[0022] In some embodiments, a method is provided for tracking human emotions in real time, the method being performed by a wearable device including multiple sensors, one or more processors, and memory, the method including: measuring multiple physical or chemical parameters of a wearer by one or more sensors, the multiple physical or chemical parameters representing the wearer's autonomic nervous system activity; processing the multiple measured parameters using a machine learning trained algorithm to generate output data, the output data including a representation of the wearer's positive emotional activity, the machine learning trained algorithm being trained using training data including brain scan data representing the brain activity of one or more trained subjects, the training data being labeled with information indicating the positive emotional activity of one or more trained subjects at or near the time the respective sensor data was collected; and providing the wearer with an output indicating the determined positive emotional activity of the wearer.

[0023] In some embodiments, a non - transient computer - readable storage medium storing instructions for tracking human emotions in real - time, the instructions, when executed by one or more processors of a wearable device including a plurality of sensors, cause the wearable device to: measure, by one or more sensors, a plurality of physical or chemical parameters of a wearer, wherein the plurality of physical or chemical parameters indicate the wearer's autonomic nervous system activity; process the plurality of measured parameters using a machine - learned trained algorithm to generate output data, wherein the output data includes an indication of the wearer's positive emotional activity, and the machine - learned trained algorithm is trained using training data including brain scan data indicating the brain activity of one or more training subjects, and the training data is labeled with information indicating the positive emotional activity of one or more training subjects at or near the time when the respective sensor data was collected; and provide an output indicating the determined positive emotional activity of the wearer to the wearer. A non - transient computer - readable storage medium configured as such.

[0024] Any of the embodiments disclosed herein may be combined, in whole or in part, with any other embodiment disclosed herein.

Brief Description of the Drawings

[0025] [Figure 1] A diagram showing an example of a system for tracking human emotions in real - time using a wearable device according to some embodiments. [Figure 2] A diagram showing an example of a positive emotion - neurotransmitter (PE - NT) matrix according to some embodiments. [Figure 3] A diagram showing an exemplary method for tracking human emotions in real - time using a wearable device according to some embodiments. [Figure 4] A diagram showing an example of a computer according to some embodiments.

Best Mode for Carrying Out the Invention

[0026] In the following detailed description and embodiments of the present disclosure, reference is made to the accompanying drawings, which illustrate, by way of example, specific embodiments that can be implemented. It should be understood that other embodiments and examples can be implemented and changes can be made without departing from the scope of the present disclosure.

[0027] Furthermore, as used in the following description, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. As used herein, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items and is to be understood as including them. The terms "includes", "including", "comprises", and / or "comprising", when used herein, specify the presence of the described features, integers, steps, operations, elements, components, and / or units, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, units, and / or groups thereof.

[0028] Unless otherwise specified, as will be apparent from the following discussion, throughout the description, discussions using terms such as "processing", "calculating", "computing", "determining", "displaying", etc. refer to the operations and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (electronic) quantities within the memory or registers of the computer system, or other information storage, transmission, or display device.

[0029] Certain aspects of this disclosure include process steps and instructions described herein in the form of algorithms. Note that the process steps and instructions of this disclosure can be implemented in software, firmware, or hardware, and if implemented in software, they can be downloaded, reside on different platforms used by various operating systems, and operated from there.

[0030] As used throughout this disclosure, the term “machine learning” is understood to include artificial intelligence (AI) systems that learn to perform tasks based on training data. This includes machine learning-based generative AI, neural networks (e.g., convolutional neural networks (CNNs), recurrent neural networks (RNNs), etc.), generative adversarial networks (GANs), deep learning, computer vision, and / or other variations thereof. Models trained using a machine learning training process may be referred to herein as machine learning trained models or machine learning trained algorithms.

[0031] This disclosure also relates to a device for performing the operations described herein. This device may be specifically constructed for the required purpose, or it may include a general-purpose computer that is selectively invoked or reconfigured by a computer program stored in the computer. Such computer programs may be stored in any type of disk, including floppy disks, optical disks, CD-ROMs, magneto-optical disks, read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic or optical cards, application-specific integrated circuits (ASICs), or any type of medium suitable for storing electronic instructions, each coupled to a computer system bus. Furthermore, the computers referred to herein may include a single processor or be architectures that utilize multiple processor designs to enhance computing power.

[0032] The methods, devices, and systems described herein are not inherently related to any particular computer or other device. Furthermore, various general-purpose systems may be used with the programs in accordance with the teachings herein, or it may be more convenient to construct a more specialized device to perform the required method steps. The structures required for these various systems will become apparent from the following description. Moreover, this disclosure does not describe any particular programming language. It will be understood that various programming languages ​​may be used to carry out the teachings of this disclosure described herein.

[0033] Where used herein, the terms “real time” or “real-time” as used interchangeably herein generally refer to events (e.g., actions, processes, methods, techniques, calculations, computations, analyses, visualizations, optimizations, etc.) performed using recently acquired (e.g., collected or received) data. In some cases, real-time events may occur almost instantly or within a sufficiently short time span, for example, within at least 1 millisecond (ms), 5 ms, 0.01 seconds, 0.05 seconds, 0.1 seconds, 0.5 seconds, 1 second, 0.1 minutes, 0.5 minutes, 1 minute, or longer. In some cases, real-time events may occur almost instantly or within a sufficiently short time span, for example, within a maximum of 1 second, 0.5 seconds, 0.1 seconds, 0.05 seconds, 0.01 seconds, 5 ms, 1 ms, or less.

[0034] This specification describes a system and method that enables real-time monitoring of human emotional responses and accurate and effective real-time differentiation and quantification of various positive emotions.

[0035] Systems and Devices In some embodiments, a system 100 is provided for monitoring human emotional responses. The system 100 may include a wearable device 102 and optionally a remote system 110. The wearable device 102 may include a number of physical and / or chemical sensors 104 for monitoring bioresponses indicating the wearer's autonomic nervous system activity. For example, the wearable device may include one or more sensors for measuring one or more parameters, including but not limited to:

[0036] For example, the interval between each heartbeat (CBI or IBI) (ms) measured by (1) electrical activity (such as an electrocardiogram based on wet, dry, or capacitive electrodes), (2) sensors that detect arterial pulsations using photoplethysmography (PPG), or non-contact systems such as PhysioCam (PhyC) that can measure arterial pulsations with sufficient accuracy to derive HRV even between different tasks, (3) sensors based on mechanical activity (e.g., hydraulic sensors, EMFi film sensors, cardiograms (BCG) using accelerometers), radio frequencies, or seismocardiograms (SCG) using accelerometers, laser Doppler vibrometers, laser speckle vibrometers, or airborne ultrasound, or gyrocardiograms (GCG) using gyroscopes or laser speckle vibrometers) and / or (4) force cardiography:

[0037] For example, pre-ejection time (PEP) (ms) measured by one or more of the same or similar sensor types as those described above for IBI (optionally, force cardiography and / or seismocardiography is preferred). PEP can be measured by simultaneously acquiring both ECG and impedance cardiography as described above;

[0038] For example, the number of valid skin conductance reactions (SCRs) measured by sensors that detect galvanic skin reactions, such as Ag / AgCl, stainless steel, silver, brass, and gold electrodes, Flexcomp Infiniti physiological monitoring and data acquisition unit, Empatica E4 and Refa System, Microsoft Band 2, Empatica E4, Health Sensor Platform, BITalino, Polar H6, Wearable Zephyr BioHarness 3, and / or Obimon EDA;

[0039] For example, respiratory sinus arrhythmia (RSA) (ms2) measured by one or more of the above-mentioned electrocardiogram sensors; and / or

[0040] For example, this may include mean arterial pressure (MAP) (mmHg) measured by (1) pressure-based methods (e.g., vascular unloading techniques, arterial pressure tonometry), (2) ultrasound-based methods, and / or (3) deep learning-based methods using data from PPG or ECG.

[0041] The measured parameters may be stored in a local data storage 107 provided as part of device 102 for local analysis by one or more processors 106 provided as part of device 102. Additionally or alternatively, the measured parameters may be transmitted to a remote system 110 via a network communication device 108 for, for example, remote storage, remote display, and / or remote data processing.

[0042] In Figure 1, the remote system 110 may include a network communication device 118 configured to receive and / or transmit data from one or more wearable devices, such as the wearable device 102. In the example of system 100, the remote system 100 may receive measured parameters transmitted from the wearable device 102 and store the parameters in storage 114. Optionally, one or more processors 112 of the remote system 110 may process the received parameters.

[0043] In some embodiments, one or more measured parameters are processed either locally in the wearable device 102 by one or more processors 106, or remotely in a remote system 110 by one or more processors 112. This allows for the determination of the wearer's emotional state and / or the activated emotional reward system in the wearer based on the measured parameters. The emotional reward system may include one or more of dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids. Processing may be performed in real time or near real time. One or more of the measured parameters are processed, for example, using one or more algorithms, rules, and / or trained models to identify the presence of one or more emotional responses (and / or emotional reward systems) and to quantify one or more of the individual emotional responses (and / or reward systems). In some embodiments, one or more of the nine positive human emotional responses (enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, gratitude) can be identified, and a quantification can be generated for each of the one or more emotional responses of an individual human. In some embodiments, a score can be generated that quantifies the strength of each identified emotional response. In some embodiments, one or more of the emotional reward centers described above can be identified, and a quantification can be generated for each of the one or more individual emotional reward centers. In some embodiments, a score can be generated that quantifies the strength of each identified emotional reward center.

[0044] In some embodiments, the system may be configured to apply one or more algorithms (including, for example, one or more algorithms applied together with and / or as part of the machine learning trained algorithms described herein) to identify and / or quantify the aforementioned emotional responses and / or emotional reward systems and convert them into neurotransmitters (and associated neurotransmitter levels). For example, the algorithms described above may use a positive emotion-neurotransmitter (PE-NT) matrix, as illustrated in Figure 2, which can convert positive emotions quantified for different emotional reward systems into amounts of one or more neurotransmitters. An exemplary PE-NT matrix is ​​described, for example, in U.S. Patent Application No. 17 / 389,023, which is incorporated herein by reference in its entirety.

[0045] The rows in the PE-NT matrix represent categories of positive emotions such as enthusiasm, sexual desire, pride / recognition, nurturing love, satisfaction, amusement, joy, and gratitude. These correspond to emotional states entered by the user and / or identified by the system. The columns in the PE-NT matrix may represent neurotransmitters associated with positive emotions (dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids). A "1" in the matrix may indicate that a particular neurotransmitter is associated with a particular emotion. A "0" in the matrix may indicate that a particular neurotransmitter is not associated with a particular emotion.

[0046] The PE-NT matrix can be used to calculate the amount of neurotransmitters associated with a media content object. In one or more examples, the calculation may include a column for positive emotions ("PE") ratings, indicating the emotional state(s) provided by the user with respect to a particular media content object. Optionally, the calculation may also include a representation of the intensity of the emotional state experienced by the user. For example, in one embodiment, the user may indicate that their enthusiasm while consuming a particular media content is mild (below average but present), resulting in a PE rating of 3. In the same example, the user may rate their satisfaction while consuming the media content as an average of 5 (e.g., on a scale of 0-10) in the PE rating column. To calculate the amount of neurotransmitters associated with a media content object, the calculation may involve multiplying the PE rating by a number in the PE-NT matrix to generate a number associated with the activity of a particular neurotransmitter. For example, enthusiasm may be associated with dopamine release, as shown in the PE-NT matrix. The PE rating for enthusiasm (provided by the user as associated with a particular media content) is 3. The value is multiplied by 1 in the dopamine column to obtain a value of 3. Thus, with respect to enthusiasm felt by the user as expressed in the PE assessment, the dopamine level associated with enthusiasm for media content is quantified as 3. In one or more cases, the remaining columns are left at 0 because those neurotransmitters are not associated with enthusiasm.

[0047] In some embodiments, an identified emotional state may correspond to the activity of two or more neurotransmitters, and the value of each neurotransmitter is obtained by multiplying the PE-NT matrix value of each neurotransmitter by its PE rating. For example, if satisfaction is rated 5 by the user and associated with dopamine, oxytocin, and cannabinoids, then each of those neurotransmitters can be multiplied by 5 (multiply by 5 × 1) to determine the level of neurotransmitter activity corresponding to that positive emotion. Once the calculation for each neurotransmitter has been performed for each emotional state experienced by the user, the calculation can be summed up, and the total neurotransmitter can be associated with a media content object.

[0048] In some embodiments, processing one or more measured parameters to determine (e.g., identify and / or quantify) emotional responses and / or reward systems may be performed by one or more algorithms trained using machine learning with functional magnetic resonance imaging (fMRI) brain scan data and data from one or more wearable sensors, such as sensor 104 contained in a wearable device 102. In some embodiments, in addition to or instead of utilizing machine learning (ML) training procedures that train on brain scan data, one or more deterministic algorithms or other computations may process brain scan data and / or wearable sensor data to determine correlations between emotional responses and / or reward systems, build deterministic models of relationships between wearable sensor data and emotional responses and / or reward systems, and / or deterministically process and analyze wearable sensor data to determine and quantify emotional responses and / or reward systems.

[0049] As shown in Figure 1, the storage 114 of the remote system 110 may store fMRI data 116 and / or historical sensor data 117. The historical sensor data 117 may be received from the sensor 104 of the wearable device 102 and / or from one or more similar sensors. The fMRI data 116 may be received from one or more MRI devices. In some embodiments, the historical sensor data 117 may include data received from the sensor 104 of the wearable device 102, which is currently and / or previously stored in the local data storage 107 of the device 102 and transmitted from the device 102 to the remote system 110. In some embodiments, the fMRI data 116 and historical sensor data 117 may be acquired simultaneously from the same subject so that specific data points from two different data sources correspond to each other. In some embodiments, the fMRI data 116 and historical sensor data 117 may be acquired at different times. The historical sensor data 117 and / or fMRI data 116 may be acquired from a single subject or multiple subjects. Some or all of the historical sensor data 117 and / or fMRI data 116 may be unlabeled, and / or may be labeled with, for example, one or more labels indicating the subject to which the data corresponds, the time of collection, the sensor used for collection, other associated (e.g., simultaneous) data points, and / or one or more associated memories or emotions that were experienced or recalled at the time (or immediately before) the data was collected.

[0050] In some embodiments, the historical sensor data 117 and / or fMRI data 116 may be used as training data for training one or more algorithms configured to identify and quantify human emotional responses (and / or emotional reward centers) based on parameters indicating autonomic nervous system responses measured by sensors (such as sensor 104), for example, using machine learning. One or more sensors used to measure the historical sensor data 117 are configured to operate within an operating MRI machine, thereby allowing simultaneous collection of brain scan (fMRI) training data and wearable sensor training data. In some embodiments, the wearable device 102 may similarly be configured to operate within an operating MRI machine. In some embodiments, one or more algorithms are trained using machine learning that is partially based on fMRI data, but may not require (or necessarily accept) fMRI data as input once deployed. Instead, one or more machine learning-trained algorithms may actually be trained to determine and quantify human emotional responses (and / or emotional reward centers) based solely on parameters indicating autonomic nervous system responses.

[0051] The collection of fMRI data 116 and historical sensor data 117 may be carried out as follows: During memory retrieval, a brain scanner (e.g., 3 Tesla (T) fMRI or 7 Tesla (T) fMRI) is used to determine the three-dimensional location of brain activity and to detect the intensity of brain activity in the brain regions. Based on the characteristic brain regions / nuclei in which activity is detected based on the fMRI data, one or more of the nine positive emotions may be identified. The intensity of brain activity in separate nuclei may correspond to the intensity of the emotion subjectively experienced by the individual. These two datasets collected from fMRI, namely the three-dimensional location of brain activity identifying a distinct positive emotion and the brain activity identifying the respective emotion intensity, may be correlated with one or more peripheral data (e.g., autonomic nervous system responses) recorded by various wearable sensors (recorded as historical sensor data 117) while inside the brain scanner. In some embodiments, the wearable sensors may measure skin conductivity, respiration, and cardiac data.

[0052] Conventional systems have been unable to identify clear signals of positive emotions based solely on wearable sensor data due to the low signal-to-noise ratio of wearable sensor data. However, as described herein, by using high-sensitivity fMRI data in real time to first interpret and then optimize the wearable sensor data, it is possible to significantly improve the signal-to-noise ratio. Based on this correlation, in some embodiments, the signal-to-noise ratio can be further optimized by recording real-life experiences that evoke positive emotions using a wearable device and then re-evaluating them with fMRI (artificially reducing noise). Since emotions are a universal property for all human beings, wearable devices trained with fMRI data from 20-30 subjects are widely available and do not require individual training with the individual's brain (e.g., fMRI) and wearable sensor data.

[0053] In some embodiments, training data (e.g., fMRI data 116 and / or historical sensor data 117) may be collected while the subject is stationary (e.g., lying still in a brain scanner). This prevents other electrophysiological signals, such as signals related to muscle movement, from generating noise that would impair data acquisition capabilities.

[0054] In some embodiments, algorithms(s) trained to identify and quantify emotional responses and / or emotional reward systems based on fMRI data and wearable sensor data may be stored in a remote system 110 (e.g., on storage 114), local data storage 107 on the wearable device 102, elsewhere within system 100, or in a system separate from system 100.

[0055] In some embodiments, one or more of the sensors 104 of the wearable device 102 may be optimized for sensitivity and / or accuracy based on fMRI brain data and / or personal subjective data. For example, system 100 can simultaneously collect sensor data from sensor 104, fMRI brain scan data (e.g., using a brain scanner) from the same subject, and personal subjective data from the subject. Personal subjective data may include audio data, text data, etc., describing the emotional aspects of the subject's experiences or memories. Based on this collected data, system 100 can calibrate, configure, and / or otherwise optimize the sensitivity and / or accuracy of sensor 104.

[0056] In some embodiments, one or more sensors 104 may be configured (e.g., calibrated, optimized), and / or algorithms may be trained using machine learning. This allows the sensors 104 and / or machine learning-trained algorithms to be deployed for use by the general public without requiring individualized training or individualized calibration. In some embodiments, individualized training and / or individualized calibration may be used to optimize performance for individual users. Individualized training and / or calibration may include one or more aspects of the training and calibration processes described above, written for the general public.

[0057] After the algorithm has been trained and / or after the sensor has been configured (e.g., calibrated, optimized), the machine learning trained algorithm may be applied (e.g., deployed) to process new (e.g., unlabeled) sensor data collected from the sensor 104 of the wearable device 102. Because the new sensor data is unlabeled, it may not explicitly indicate any association with memory, experience, human emotion, or emotional reward centers. By processing the unlabeled sensor data using the machine learning trained algorithm, the system may generate output data that includes (a) a representation of one or more human emotions (e.g., one or more of the positive human emotions described above) and a quantification for one or more of the identified human emotions, and / or (b) a representation of one or more emotional reward systems (e.g., one or more of the emotional reward systems described above) and a quantification for one or more of the identified emotional reward systems. The output data may include scores indicating the quantification of a given human emotion or reward system, and / or confidence levels associated with the determination of a given human emotion and / or reward system.

[0058] The output score may be stored locally and / or remotely (e.g., on storage 107 and / or on storage 114), transmitted to one or more other system components and / or one or more other systems, used to generate one or more visualizations and / or one or more other outputs (e.g., auditory output and / or haptic feedback), and / or used to invoke one or more automated system functions.

[0059] As described above, training data (e.g., fMRI data and / or wearable sensor data) can be collected while the subject is stationary. However, once the device is deployed, sensor data (e.g., autonomic nervous system data) can be collected at any time, including when the wearer is moving. Therefore, other electrophysiological signals generated by the wearer, such as signals related to muscle movement, may affect the ability of the wearable sensor to effectively collect data (due to the low signal-to-noise ratio of autonomic nervous system data). Training data collected using the methods described above may not be suitable for training algorithms using machine learning, as fMRI data may not be available while the subject is moving, thus needing to account for the variability of this data.

[0060] Despite this issue, the systems and devices described herein may be configured to effectively identify and quantify emotional responses and / or reward systems based on wearable sensor data collected at any time, including during wearer movement, and analyzed using algorithms trained at least partially on brain scan (e.g., fMRI) data using machine learning. For example, the systems and devices described herein may be configured to take electrophysiological signals into account using a “stepwise” training plan for the algorithm(s). The training plan may include several steps that progressively introduce wearer movement so that the machine learning-trained algorithm(s) configured to identify and quantify emotional responses and / or reward systems during use can do so regardless of wearer movement. At each step of training, the subject may be presented with the same positive memory trigger.

[0061] In some embodiments, the first stage of training may include collecting wearable sensor training data along with brain scan training data, as described above. During this stage of training, the subject may maintain a static posture within an fMRI brain scanner. The first stage of training may also include a post-hoc emotional assessment in which the wearer provides a subjective assessment of their own emotions, which may be used to calibrate and / or optimize the wearable device.

[0062] In some embodiments, the second stage of machine learning training of the algorithm may include collecting additional wearable sensor data while the subject is in a stationary, standing position outside the fMRI brain scanning environment. Any noise detected from the subject's basic muscle contractions due to standing is measured and removed from the measured wearable data. In some embodiments, during the second stage of training, the subject may again complete a post-emotional assessment to subjectively evaluate their emotions.

[0063] In some embodiments, the third stage of machine learning training of the algorithm may include collecting additional wearable sensor training data while the subject walks on a treadmill. Any noise detected by active muscle contractions during walking is measured and removed from the measured wearable data. In some embodiments, during the second stage of training, the subject may again complete a post-emotional assessment to subjectively evaluate their emotions.

[0064] In some embodiments, following the three training stages described above, the wearable device may be further trained using a continuous, inductive machine learning training process. This may include the wearable device's sensors ad-hoc detecting signals above a noise baseline and, based on that detection, prompting the wearer of the device via an input device to confirm the detected event. Based on the subject's input (e.g., confirming the detected event), the input device may prompt the subject for additional information about the event, such as a display of the type of emotion experienced. In some embodiments, the input device may prompt the user for an assessment that quantifies the intensity of the emotion experienced. Based on the subject's input, the machine learning-trained algorithm configured to identify and quantify emotional responses and / or reward centers may be refined. In some embodiments, the wearable device may be configured to detect signals indicating positive events. If a negative event is detected, the system may further refine the machine learning-trained algorithm(s) using user input indicating that a negative event has been detected. The continuous ML training process may take place over a period of time, such as approximately two to three weeks.

[0065] method Figure 3 shows an exemplary method 300 for tracking human emotional activity using a wearable device. Method 300 may be performed by a system for tracking human emotional activity, such as system 100 described herein.

[0066] In block 302, the system may receive training data. As described herein, the training data may include (a) sensor data from sensors measuring physical and / or chemical activity indicating autonomic nervous system activity, and / or (b) brain scan (e.g., fMRI) data. The training data may be labeled to indicate information about the subject's emotional activity at the time the training data was measured (e.g., subjectively reported emotional state and / or neurotransmitter levels). In some embodiments, the first round of training data may be collected while the subject is wearing wearable sensors and in an fMRI machine, thereby allowing simultaneous collection of wearable sensor data and brain scan data. The data (sensor data and brain scan data) may be collected while the subject is recalling one or more positive emotions and positive memories subjectively characterized as being associated with the intensity of the emotion, respectively. The training data collected may be labeled using subjective emotional characterization by the subject.

[0067] In block 304, the system can train an algorithm using machine learning based on received training data. As described herein, a machine learning-trained algorithm may be trained based on labeled sensor training data and / or labeled brain scan training data, thereby configured to accept unlabeled wearable sensor data (indicating the wearer's autonomic nervous system activity) and to generate output data that identifies and quantifies the user's emotional activity. The identified and quantified emotional activity may include the identification and quantification of one or more emotional states and / or one or more emotional reward centers (e.g., neurotransmitters) as described above.

[0068] In block 306, the system may configure a wearable sensor based on received training data. As described herein, one or more sensors of a wearable device may be calibrated, optimized, and / or otherwise configured based on labeled training data. When brain scan data and sensor data (e.g., autonomic nervous system data) are collected simultaneously, the wearable sensor may be calibrated based on the relationship between the brain scan data and the sensor data (e.g., autonomic nervous system data). Calibration may utilize a peak memory for a given emotional state (e.g., a memory with a maximum intensity score (e.g., 8) and maximum brain activity in the region of interest) and a control memory that is rated as 0 for that emotional state (e.g., a memory with a maximum intensity score and minimum or baseline brain activity in the region of interest).

[0069] In block 308, the system may receive sensor data from the configured wearable sensors. As described herein, a calibrated and deployed wearable device can measure sensor data indicating the wearer's autonomic nervous system activity (for example, using the same or similar sensor types as those used to collect training data). In some embodiments, the data collected from the wearable device may not be collected together with corresponding brain scan data, and in some embodiments, it may not be labeled with an explicit indication of associated emotional activity.

[0070] In block 310, the system can apply a machine learning-trained algorithm to process the received sensor data to identify and quantify the emotional activity of the wearer of the wearable sensor. The machine learning-trained algorithm may generate output data that includes the identification and quantification of one or more emotional states and / or one or more emotional reward centers (e.g., neurotransmitters) as described above. The generated output data may be stored, transmitted, and used to generate one or more outputs (e.g., on a wearable device) and / or to trigger one or more automated system functions.

[0071] Referring to blocks 302-310, the methods described above may be validated, repeated, and / or repeated one or more times. For example, after the wearable sensor is configured, deployed, and used in blocks 308-310 to identify and quantify the wearer's positive emotional activity, the experience associated with the positive emotional activity may be recorded for later recall by the subject during subsequent fMRI training data recording sessions. In subsequent fMRI training data recording sessions, the subject may recall positive memories associated with experiences in which the wearable sensor previously identified and quantified the subject's positive emotional activity in real time. During recall, brain scan data may be collected, and optionally, additional wearable sensor data may be collected. The system may compare wearable sensor data from actual experiences with wearable sensor data from the recall of those experiences in order to further calibrate and / or validate the sensor configuration. Furthermore, the system may use newly recorded brain scan data, newly recorded wearable sensor data during recall, and / or real-time sensor data recorded during actual experience to update machine learning trained algorithms (e.g., retrain the algorithms) and / or update the calibration or other configuration of one or more sensors of the wearable device.

[0072] Computing devices Figure 4 shows examples of computers according to several embodiments. Device 400 may be a host computer connected to a network. Device 400 may be a client computer or a server. As shown in Figure 4, device 400 may be any suitable type of microprocessor-based device, such as a personal computer, workstation, server, or handheld computing device (portable electronic device) such as a telephone or tablet. The device may include, for example, one or more of a processor 410, an input device 420, an output device 430, storage 440, and a communication device 460. The input device 420 and the output device 430 can generally correspond to those described above and can either be connected to or integrated with the computer.

[0073] The input device 420 may be any suitable device that provides input, such as a touchscreen, keyboard or keypad, mouse, or voice recognition device. The output device 430 may be any suitable device that provides output, such as a touchscreen, haptic device, or speaker.

[0074] Storage 440 may be any suitable device that provides storage, such as electrical, magnetic, or optical memory including RAM, cache, hard drive, or removable storage disk. Communication device 460 may include any suitable device capable of sending and receiving signals over a network, such as a network interface chip or device. Computer components can be connected in any suitable manner, such as via a physical bus or wirelessly.

[0075] The software 450 stored in the storage 440 and executable by the processor 410 may include, for example, programming that embodies the functions of the present disclosure (for example, embodied in the device described above).

[0076] The software 450 may also be stored and / or transported in any non-temporary computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as those described above, which can fetch instructions associated with the software from such instruction execution systems, apparatus, or devices and execute those instructions. In the context of this disclosure, a computer-readable storage medium may be any medium, such as storage 440, that contains or can store programming and is used by or connected to an instruction execution system, instruction execution apparatus, or instruction execution device.

[0077] The software 450 can also be propagated in any transport medium for use by or in connection with an instruction execution system, apparatus, or device, such as those described above, which can fetch instructions associated with the software from such instruction execution systems, apparatus, or devices and execute those instructions. In the context of this disclosure, the transport medium may be any medium on which programming can be communicated, propagated, or transported for use by or in connection with an instruction execution system, instruction execution apparatus, or instruction execution device. Transport-readable mediums include, but are not limited to, wired or wireless propagation media of electronic, magnetic, optical, electromagnetic, or infrared.

[0078] Device 400 may be connected to a network which may be any preferred type of interconnected communication system. The network may implement any suitable communication protocol and be protected by any suitable security protocol. The network may include any suitable configuration of network links capable of transmitting and receiving network signals, such as wireless network connections, T1 or T3 lines, cable networks, DSL, or telephone lines.

[0079] Device 400 can implement any operating system suitable for operation over a network. Software 450 can be written in any preferred programming language such as C, C++, Java, or Python. In various embodiments, application software embodying the functionality of this disclosure can be deployed in different configurations, for example, in a client / server configuration, or via a web browser as a web-based application or web service.

[0080] Exemplary Embodiments The following embodiments are illustrative and are not intended to limit the scope of any invention described herein.

[0081] Embodiment 1. It is a system for tracking human emotions in real time. A wearable device containing multiple sensors, One or more processors, Includes a memory for storing instructions, and the instructions are stored in the system. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The system is configured to process the plurality of measured parameters using a machine learning-trained algorithm to generate output data, wherein the output data includes a representation of the wearer's positive emotional activity.

[0082] Embodiment 2. The system according to Embodiment 1, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0083] Embodiment 3. The system according to any one of Embodiments 1 to 2, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0084] Embodiment 4. The system according to any one of Embodiments 1 to 3, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0085] Embodiment 5. The system according to any one of Embodiments 1 to 4, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0086] Embodiment 6. The system according to any one of Embodiments 1 to 5, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0087] Embodiment 7. The system according to any one of Embodiments 1 to 6, wherein the command is configured to cause the system to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including a displayed visualization, an audio output, and a haptic output.

[0088] Embodiment 8. The command is to receive training data in the system, which includes brain scan data showing the brain activity of one or more training subjects, wherein the training data is labeled with information showing the positive emotional activity of one or more of the training subjects at or near the time when the respective sensor data was collected, and the receiving The system according to any one of embodiments 1 to 7, configured to train the machine learning trained algorithm using the aforementioned training data.

[0089] Embodiment 9. The training data includes sensor data indicating multiple physical or chemical parameters of the training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The system according to Embodiment 8, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0090] Embodiment 10. The command is to receive training data in the system, which includes brain scan data showing the brain activity of one or more of the training subjects, wherein the training data is labeled with information showing the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected, and the receiving The system according to any one of embodiments 1 to 9, configured to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0091] Embodiment 11. A method for tracking human emotions in real time, which is implemented in a system including a wearable device that includes multiple sensors, one or more processors, and memory. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The method comprising processing the plurality of measured parameters using a machine learning-trained algorithm to generate output data, wherein the output data includes a representation of the wearer's positive emotional activity.

[0092] Embodiment 12. The method according to Embodiment 11, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0093] Embodiment 13. The method according to any one of Embodiments 11 to 12, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0094] Embodiment 14. The method according to any one of Embodiments 11 to 13, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0095] Embodiment 15. The method according to any one of Embodiments 11 to 14, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0096] Embodiment 16. The method according to any one of Embodiments 11 to 15, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0097] Embodiment 17. The method according to any one of embodiments 11 to 16, comprising providing the wearer with an output indicating the determined positive emotional activity of the wearer, wherein the output is selected from a set including a displayed visualization, an audio output, and a haptic output.

[0098] Embodiment 18. Receiving training data, which includes brain scan data showing the brain activity of one or more training subjects, wherein the training data is labeled with information indicating the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected, The method according to any one of embodiments 11 to 17, wherein the method is configured to train the machine learning trained algorithm using the aforementioned training data.

[0099] Embodiment 19. The training data includes sensor data indicating multiple physical or chemical parameters of the training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The method according to Embodiment 18, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0100] Embodiment 20. Receiving training data, which includes brain scan data showing the brain activity of one or more of the training subjects, wherein the training data is labeled with information indicating the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected, The method according to any one of embodiments 11 to 19, wherein the method is configured to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0101] Embodiment 21. A non-temporary, computer-readable storage medium for storing instructions for tracking human emotions in real time, wherein the instructions are configured to be executed by one or more processors of a system including a wearable device including multiple sensors, and the system, Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, A non-temporary computer-readable storage medium configured to process the plurality of measured parameters using a machine learning-trained algorithm to generate output data, wherein the output data includes a representation of the wearer's positive emotional activity.

[0102] Embodiment 22. A non-temporary computer-readable storage medium according to Embodiment 21, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0103] Embodiment 23. A non-temporary computer-readable storage medium according to any one of embodiments 21 to 22, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0104] Embodiment 24. A non-temporary, computer-readable storage medium according to any one of embodiments 21 to 23, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotions, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0105] Embodiment 25. A non-temporary, computer-readable storage medium according to any one of embodiments 21 to 24, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0106] Embodiment 26. A non-temporary computer-readable storage medium according to any one of embodiments 21 to 25, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0107] Embodiment 27. The command is configured to cause the system to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including a displayed visualization, an audio output, and a haptic output, in a non-temporary computer-readable storage medium according to any one of embodiments 21 to 26.

[0108] Embodiment 28. The command is to receive training data in the system, which includes brain scan data showing the brain activity of one or more training subjects, wherein the training data is labeled with information showing the positive emotional activity of one or more of the training subjects at or near the time when the respective sensor data was collected, and the receiving A non-temporary computer-readable storage medium according to any one of embodiments 21 to 27, configured to train the machine learning trained algorithm using the aforementioned training data.

[0109] Embodiment 29. The training data includes sensor data indicating multiple physical or chemical parameters of the training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. A non-temporary computer-readable storage medium according to Embodiment 28, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0110] Embodiment 30. The command is to receive training data in the system, which includes brain scan data showing the brain activity of one or more of the training subjects, wherein the training data is labeled with information showing the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected, and the receiving A non-temporary computer-readable storage medium according to any one of embodiments 21 to 29, configured to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0111] Embodiment 31. A wearable device for tracking human emotions in real time, Multiple sensors, One or more processors, Includes a memory for storing instructions, and the instructions are transmitted to the device. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more of the training subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected. The wearable device is configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

[0112] Embodiment 32. The device according to Embodiment 31, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0113] Embodiment 33. The device according to Embodiment 31 or 32, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0114] Embodiment 34. The device according to any one of Embodiments 31 to 33, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0115] Embodiment 35. The device according to any one of Embodiments 31 to 34, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0116] Embodiment 36. The device according to any one of Embodiments 31 to 35, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0117] Embodiment 37. The device according to any one of embodiments 31 to 36, wherein the command is configured to cause the device to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including a displayed visualization, an audio output, and a haptic output.

[0118] Embodiment 38. The training data includes sensor data indicating multiple physical or chemical parameters of a training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The device according to any one of embodiments 31 to 37, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0119] Embodiment 39. The device according to any one of embodiments 31 to 38, wherein the instruction is configured to cause the system to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0120] Embodiment 40. A method for tracking human emotions in real time, which is performed by a wearable device including multiple sensors, one or more processors, and memory. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more trained subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the trained subjects at or near the time the respective sensor data was collected. The method is configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

[0121] Embodiment 41. The method according to Embodiment 40, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0122] Embodiment 42. The method according to Embodiment 40 or 41, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0123] Embodiment 43. The method according to any one of Embodiments 40 to 42, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0124] Embodiment 44. The method according to any one of Embodiments 40 to 43, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0125] Embodiment 45. The method according to any one of Embodiments 40 to 44, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0126] Embodiment 46. The method according to any one of embodiments 40 to 45, comprising providing the wearer with an output indicating the determined positive emotional activity of the wearer, wherein the output is selected from a set including a displayed visualization, an audio output, and a haptic output.

[0127] Embodiment 47. The training data includes sensor data indicating multiple physical or chemical parameters of a training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The method according to any one of embodiments 40 to 46, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0128] Embodiment 48. The method according to any one of embodiments 40 to 47, wherein the method is configured to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0129] Embodiment 49. A non-temporary, computer-readable storage medium for storing instructions for tracking human emotions in real time, wherein the instructions are configured to be executed by one or more processors of a system including a wearable device including multiple sensors, and the wearable device, Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more trained subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the trained subjects at or near the time the respective sensor data was collected. A non-temporary computer-readable storage medium configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

[0130] Embodiment 50. A non-temporary computer-readable storage medium according to Embodiment 49, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

[0131] Embodiment 51. A non-temporary computer-readable storage medium according to Embodiment 49 or 50, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

[0132] Embodiment 52. A non-temporary computer-readable storage medium according to any one of embodiments 49 to 51, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotions, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0133] Embodiment 53. A non-temporary, computer-readable storage medium according to any one of embodiments 49 to 52, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

[0134] Embodiment 54. A non-temporary, computer-readable storage medium according to any one of embodiments 49 to 53, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

[0135] Embodiment 55. The instruction is configured to cause the device to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including displayed visualizations, audio outputs, and haptic outputs, in a non-temporary computer-readable storage medium according to any one of embodiments 49 to 54.

[0136] Embodiment 56. The training data includes sensor data indicating multiple physical or chemical parameters of a training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. A non-temporary computer-readable storage medium according to any one of embodiments 49 to 55, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

[0137] Embodiment 57. A non-temporary computer-readable storage medium according to any one of embodiments 49 to 56, wherein the instruction is configured to cause the system to configure one or more of the plurality of sensors of the wearable device based on the training data.

[0138] [Examples] Virtual Example 1 In a hypothetical embodiment, peripheral signals from autonomic nervous system responses are measured using multiple sensors provided as part of a sensor patch. The sensors are configured to measure the following parameters, which represent skin conductivity, respiration, and cardiac data. Specifically, the sensors are used to measure the interval between each heartbeat (IBI), ms; pre-ejection time (PEP), ms; the number of effective skin conductance responses (SCRs); respiratory sinus arrhythmia (RSA), ms2; and mean arterial pressure (MAP), mmHg.

[0139] Parameters are measured while subjects are recalling personal, positive memories (e.g., while recalling the above memories and / or viewing images related to those memories). Parameters are measured over one or more runs for each subject, with each run consisting of four different sessions, each session covering 18 different memories. Measured parameter data are labeled according to the positive human emotions associated with the above personal, positive memories.

[0140] Labeled parameter data is analyzed manually and / or using machine learning training algorithms to determine the correlation between different parameter levels and various individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is configured (e.g., trained using ML) to process unlabeled measured parameter data and, based on it, determine relevant individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions.

[0141] Next, the configured algorithm is applied to unlabeled measurement parameter data collected using the sensors on the sensor patch, thereby identifying and quantifying individual positive human emotions.

[0142] Virtual Example 2 In the hypothetical embodiment, peripheral signals from autonomic nervous system responses are measured using multiple sensors provided as part of a sensor patch. The sensors include the same sensors as described above with reference to hypothetical embodiment 1, and the parameters measured are the same as those described above with reference to hypothetical embodiment 1. In addition to measuring the above parameters indicating autonomic nervous system responses, fMRI brain scan data (3T rt-fMRI) is simultaneously collected.

[0143] Parameter and brain scan data are measured while subjects are recalling personal, positive memories (e.g., while recalling the above memories and / or viewing images related to those memories). Parameters are measured for each subject over 21 days, averaging 2 to 5 positive experiences per day, for a total of 60 to 80 positive experiences. The measured parameter and brain scan data are labeled according to the positive human emotions associated with the above personal, positive memories, for example, as indicated by the user when user input is entered.

[0144] Labeled parameter data and brain scan data are analyzed manually and / or using machine learning training algorithms to determine correlations between different parameter levels, brain scan data, and features with various individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is configured (e.g., trained using ML) to process unlabeled measured parameter data collected from the patch sensors described above and, based on this, determine relevant individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is trained, at least in part, on the collected brain scan data described above, but is trained to make determinations based solely on the patch sensor data (without referring to the corresponding brain scan data).

[0145] Next, the configured algorithm is applied to unlabeled measurement parameter data collected using the sensors on the sensor patch, thereby identifying and quantifying individual positive human emotions.

[0146] Virtual Example 3 In the hypothetical embodiment, peripheral signals from autonomic nervous system responses are measured using multiple sensors provided as part of a sensor patch. The sensors include the same sensors as described above with reference to hypothetical embodiment 1, and the parameters measured are the same as those described above with reference to hypothetical embodiment 1.

[0147] Parameters are measured and recorded within a time window in which the subject indicates that a positive experience is in progress or has recently been completed. For example, the subject uses an input device, such as an input device with a graphical user interface (e.g., a smartphone application), to indicate that a positive experience is in progress or has recently been completed. User input causes the parameters measured by the sensor patch to be recorded and / or analyzed. For example, user input causes the sensor patch to start measuring. In another example, user input causes the system to start recording measurements from the sensor patch. In yet another example, user input causes the system to permanently store and / or analyze parameters that were recorded and temporarily stored by the system at the time indicated by the user input, in order to associate them with a positive experience. Parameters are measured over one or more runs for a single subject, with each run consisting of four different sessions, each session covering 18 different memories. The measured parameter data is labeled according to the positive human emotions associated with the personal positive memories described above.

[0148] Labeled parameter data is analyzed manually and / or using machine learning training algorithms to determine the correlation between different parameter levels and various individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is configured (e.g., trained using ML) to process unlabeled measured parameter data collected from the patch sensors described above and, based on this, determine the relevant individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions.

[0149] Next, the configured algorithm is applied to unlabeled measurement parameter data collected using the sensors on the sensor patch, thereby identifying and quantifying individual positive human emotions.

[0150] Virtual Embodiment 4 In the hypothetical embodiment, peripheral signals from autonomic nervous system responses are measured using multiple sensors provided as part of a sensor patch. The sensors include the same sensors as described above with reference to hypothetical embodiment 1, and the parameters measured are the same as those described above with reference to hypothetical embodiment 1.

[0151] Parameters are measured and recorded within a time window in which a subject indicates that a positive experience is in progress or has recently been completed. For example, a subject uses an input device, such as an input device with a graphical user interface (e.g., a smartphone application), to indicate that a positive experience is in progress or has recently been completed, as described above with reference to Hypothetical Example 3. Parameters are measured for 20-24 subjects (50:50 male-female ratio, 18-35 years old, no neurological or psychiatric disorders). For each subject, data for a total of 84 positive experiences are recorded over a 6-week period. The measured parameter data are labeled to indicate the subject and the positive human emotion associated with the personal positive memory described above, as indicated by the user when user input is entered, for example.

[0152] In addition to collecting sensor data during real-life experiences, parameters are measured using patch sensors, and brain scan data is collected using 3T fMRI during one or more brain scan sessions. During each session, data for each subject is measured while the subject is recalling a peak memory ("best memory of my life"). The data patterns between real-time emotional experience and emotional experience during memory recall in MRI are very similar. The measured parameter data and brain scan data from the above sessions are labeled to indicate the subject and the positive human emotions associated with the peak memory, as indicated by the subject, for example.

[0153] Labeled parameter data and brain scan data are analyzed manually and / or using machine learning training algorithms to determine correlations between different parameter levels, brain scan data, and features with various individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is configured (e.g., trained using ML) to process unlabeled measured parameter data collected from the patch sensors described above and, based on this, determine relevant individual positive human emotions (as described above), along with the intensity (quantification) of these individual positive human emotions. The algorithm is trained, at least in part, on the collected brain scan data described above, but is trained to make determinations based solely on the patch sensor data (without referring to the corresponding brain scan data).

[0154] Next, the configured algorithm is applied to unlabeled measurement parameter data collected using the sensors on the sensor patch, thereby identifying and quantifying individual positive human emotions.

[0155] Follow-up scans are performed at 3 and 6 months. Structural changes in cortical thickness and rGMV are consistent with emotional and overall well-being assessments.

[0156] Virtual Example 5 In a hypothetical embodiment, a stepwise manner of collecting wearable sensor training data is performed to address the influence of electrophysiological signals, such as those generated by muscle contractions, on autonomic nervous system data.

[0157] First, subjects are placed in a 7T MRI while wearing one or more research-grade wearables and one or more consumer-grade wearables containing the necessary sensors. Upon presentation of positive memory triggers (e.g., photos, videos, music, text, audio), real-time changes measured from the emotional centers in the brain via fMRI are matched with outputs from the research-grade wearable(s) and consumer-grade wearables. The research-grade wearables serve as controls with higher sensitivity compared to the consumer-grade wearables. This data matching is enhanced using machine learning (e.g., generative AI). Improved consumer-grade wearables are manufactured to identify and quantify nine emotions. After the MRI scan, subjects complete a post-hoc emotional assessment to evaluate their subjective emotions. The post-hoc assessment matches subjective emotions with objective brain activity measurements and objective wearable measurements for further calibration and / or optimization of the wearable devices.

[0158] Following the MRI scan, the algorithmic training is repeated outside the MRI, with the subject standing still in front of a screen projecting the same positive memory triggers. Any additional noise present in the case of basic muscle contractions in an upright standing position is measured. Post-hoc subjective emotional assessments by the subject are repeated. Any noise from the standing position is subtracted from the measured wearable data.

[0159] Next, the algorithmic training is repeated on a treadmill while the subject walks, with the same positive memory trigger projected onto a screen. Any noise added when there is active muscle contraction during walking is measured. Post-hoc subjective sentiment assessments are repeated. Then, any noise from walking is subtracted from the measured wearable data.

[0160] Next, the algorithm's sequential machine learning training process is carried out as follows: Whenever a wearable sensor(s) detects a signal above a noise baseline, the wearable device prompts the subject to confirm, modify, or reject the measured emotion determined based on the detected signal. Over time, the subject trains the wearable device to recognize sensor data patterns above the noise baseline. For example, the wearable device detects an increase in arousal (indicated by changes in skin conductivity and / or heart rate variability, i.e., HRV, shown by changes) and, in response, prompts the subject using the input device's graphical user interface to ask the following question(s): "Did something positive happen?" If the subject confirms via the input device that, yes, something positive happened, the wearable device then prompts the subject to indicate whether the positive event was accompanied by an emotion such as excitement, sexual desire, amusement, or pleasure. By selecting one or more emotions, the underlying sensor data patterns are refined and prioritized for future use. If a subject does not confirm that something positive happened because the arousal was ultimately triggered by a negative experience (e.g., anxiety, panic, stress), the ML-trained algorithm uses this information to lower the priority of the underlying sensor data patterns. In some embodiments, post-event sentiment assessment involves a wearable device prompting the subject to quantify emotion intensity on a scale such as 0-8. Over time (e.g., 2-3 weeks later), the wearable device is fine-tuned to efficiently detect and quantify nine individual emotions.

[0161] conclusion The above description has been based on reference to specific embodiments for illustrative purposes. However, the above exemplary considerations are not intended to be exhaustive, nor are they intended to limit this disclosure to the exact form disclosed. Many modifications and variations are possible in light of the above teachings. The multiple embodiments have been selected and described to best illustrate the principles of the art and its practical applications. Thereafter, those skilled in the art will be able to best utilize the art and its various embodiments with various modifications suitable for specific uses that may be conceived.

[0162] While this disclosure and examples have been adequately described with reference to the accompanying drawings, it should be noted that various changes and modifications will be apparent to those skilled in the art. Such changes and modifications should be understood to be included within the scope of the disclosure and examples as defined by the claims.

[0163] With respect to the numerical ranges disclosed in the text and drawings, the disclosed numerical ranges are applicable across the entire disclosed numerical range, and therefore, even though the specification does not verbatim specify precise range limitations, they essentially support any range or value within the disclosed numerical range, including endpoints.

[0164] The above description is provided to enable those skilled in the art to prepare or use this disclosure and is provided in relation to a particular use and its requirements. Various modifications to preferred embodiments will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments and uses without departing from the spirit and scope of the disclosure. Thus, this disclosure is not intended to be limited to the embodiments shown, but rather to be given the broadest scope of the principles and features disclosed herein. Finally, all disclosures of patents and publications referenced in this application are incorporated herein by reference.

Claims

1. It is a system for tracking human emotions in real time. A wearable device containing multiple sensors, One or more processors, Includes a memory for storing instructions, and the instructions are stored in the system. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The system is configured to generate output data, which includes a display of the wearer's positive emotional activity, by processing the plurality of measured parameters using a machine learning-trained algorithm.

2. The system according to claim 1, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

3. The system according to any one of claims 1 to 2, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

4. The system according to any one of claims 1 to 3, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

5. The system according to any one of claims 1 to 4, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

6. The system according to any one of claims 1 to 5, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

7. The system according to any one of claims 1 to 6, wherein the command is configured to cause the system to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including a displayed visualization, an audio output, and a haptic output.

8. The instruction is given to the system, Receiving training data, which includes brain scan data showing the brain activity of one or more training subjects, wherein the training data is labeled with information indicating the positive emotional activity of one or more of the training subjects at or near the time when each sensor data was collected, The system according to any one of claims 1 to 7, configured to train the machine learning trained algorithm using the aforementioned training data.

9. The training data includes sensor data indicating multiple physical or chemical parameters of a training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The system according to claim 8, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

10. The instruction is given to the system, Receiving training data including brain scan data showing the brain activity of one or more of the training subjects, wherein the training data is labeled with information showing the positive emotional activity of one or more of the training subjects at or near the time the respective sensor data was collected, The system according to any one of claims 1 to 9, configured to configure one or more of the plurality of sensors of the wearable device based on the training data.

11. A method for tracking human emotions in real time, which is performed in a system including a wearable device that includes multiple sensors, one or more processors, and memory. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The method comprising processing the plurality of measured parameters using a machine learning-trained algorithm to generate output data, wherein the output data includes a representation of the wearer's positive emotional activity.

12. A non-temporary, computer-readable storage medium for storing instructions for tracking human emotions in real time, wherein the instructions are configured to be executed by one or more processors of a system including a wearable device including multiple sensors, and the system, Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, A non-temporary computer-readable storage medium configured to process the plurality of measured parameters using a machine learning-trained algorithm to generate output data, wherein the output data includes a representation of the wearer's positive emotional activity.

13. A wearable device for tracking human emotions in real time, Multiple sensors, One or more processors, Includes a memory for storing instructions, and the instructions are transmitted to the device. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more trained subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the trained subjects at or near the time the respective sensor data was collected. The wearable device is configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

14. The device according to claim 13, wherein the one or more sensors include a sensor selected from a set including an electrical activity sensor, a photoplethysmography sensor, a non-contact system configured to measure arterial pulse, a mechanical activity-based sensor, a force cardiography sensor, a seismocardiography sensor, an ECG sensor, an impedance cardiography sensor, a sensor for detecting skin electrical responses, a pressure-based mean arterial pulse sensor, and an ultrasonic sensor.

15. The device according to claim 13 or 14, wherein the plurality of measured parameters include parameters selected from a set including the interval between each heartbeat, pre-ejection time, number of skin conductance responses, respiratory sinus arrhythmia, and mean arterial pressure.

16. The device according to any one of claims 13 to 15, wherein the display of the wearer's positive emotional activity includes a score that quantifies the user's emotion, selected from a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

17. The device according to any one of claims 13 to 16, wherein the display of the wearer's positive emotional activity includes a score that quantifies each of the user's emotions for all emotions in a set including enthusiasm, sexual desire, recognition / pride, nurturing / familial love, satisfaction, friendship, amusement, joy, and gratitude.

18. The device according to any one of claims 13 to 17, wherein the display of positive emotional activity includes a score that quantifies the user's active emotional reward center, selected from a set including dopamine, testosterone, serotonin, oxytocin, cannabinoids, and opioids.

19. The device according to any one of claims 13 to 18, wherein the command is configured to cause the device to provide the wearer with an output indicating the wearer's determined positive emotional activity, the output being selected from a set including a displayed visualization, an audio output, and a haptic output.

20. The training data includes sensor data indicating multiple physical or chemical parameters of a training subject, wherein the multiple physical or chemical parameters of one or more training subjects indicate the autonomic nervous system activity of the training subject. The device according to any one of claims 13 to 19, wherein the sensor data of the training data and the brain scan data of the training data are recorded simultaneously.

21. The device according to any one of claims 13 to 20, wherein the instruction is configured to cause the system to configure one or more of the plurality of sensors of the wearable device based on the training data.

22. A method for tracking human emotions in real time, which is performed by a wearable device including multiple sensors, one or more processors, and memory. Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more trained subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the trained subjects at or near the time the respective sensor data was collected. The method is configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

23. A non-temporary, computer-readable storage medium for storing instructions for tracking human emotions in real time, wherein the instructions are configured to be executed by one or more processors of a system including a wearable device including multiple sensors, and the wearable device, Measuring multiple physical or chemical parameters of the wearer using one or more sensors, wherein the multiple physical or chemical parameters indicate the wearer's autonomic nervous system activity, and the measurement of these parameters, The process involves using a machine learning-trained algorithm to process the multiple measured parameters and generate output data, wherein the output data includes a representation of the wearer's positive emotional activity, the machine learning-trained algorithm is trained using training data which includes brain scan data showing the brain activity of one or more trained subjects, and the training data is labeled with information indicating the positive emotional activity of one or more of the trained subjects at or near the time the respective sensor data was collected. A non-temporary computer-readable storage medium configured to provide the wearer with an output indicating the positive emotional activity of the wearer as determined above.

Images