User identification via motion and heartbeat waveform data

• US 10,126,830 B2
• Filed: 11/14/2017
• Issued: 11/13/2018
• Est. Priority Date: 08/07/2015
• Status: Active Grant

• Current Assignee: Fitbit, Inc. (Alphabet Inc.)
• Original Assignee: Fitbit, Inc. (Alphabet Inc.)
• Inventors: Yuen, Shelten Gee Jao, Park, James, Ghoreyshi, Atiyeh, Wu, Anjian
• Primary Examiner(s): Schwartz, Darren B
• Application Number:
  US15/812,879
• Publication Number:
  US 20180067565A1
• Time in Patent Office: 364 Days
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0024 for multiple sensor units attached to the patient, e.g. using a body or personal area network
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1032 Determining colour for diagnostic purposes measuring colour in general G01J3/46
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/1112 Global tracking of patients, e.g. by using GPS
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/112 Gait analysis
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/1172 using fingerprinting
• CPC Class Codes: A61B 5/332 Portable devices specially adapted therefor
• CPC Class Codes: A61B 5/441 Skin evaluation, e.g. for skin disorder diagnosis
• CPC Class Codes: A61B 5/6802 Sensor mounted on worn items
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/6844 Monitoring or controlling distance between sensor and tissue
• CPC Class Codes: A61B 5/725 : using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7257 : using Fourier transforms
• CPC Class Codes: A61B 5/7264 : Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 : involving training the classification device
• CPC Class Codes: A61B 5/7271 : Specific aspects of physiological measurement analysis A61B5/316, A61B5/349 and A61B5/374 take precedence
• CPC Class Codes: A61B 5/742 : using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/7475 : User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: A63B 24/0062 : Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
• CPC Class Codes: A63B 69/36 : for golf
• CPC Class Codes: G01C 22/006 : Pedometers
• CPC Class Codes: G01P 1/02 : Housings
• CPC Class Codes: G01P 13/00 : Indicating or recording presence, absence, or direction, of movement electric switches H01H; counting moving objects G06M7/00
• CPC Class Codes: G01S 19/00 : Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
• CPC Class Codes: G01S 19/19 : Sporting applications
• CPC Class Codes: G06F 1/163 : Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 21/32 : using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2218/10 : by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
• CPC Class Codes: G06F 3/017 : Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06Q 50/01 : Social networking
• CPC Class Codes: G06V 40/10 : Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/15 : Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
• CPC Class Codes: G06V 40/20 : Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/23 : Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G09B 5/02 : with visual presentation of the material to be studied, e.g. using film strip
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The disclosure relates to methods, devices, and systems to identify a user of a wearable fitness monitor using data obtained using the wearable fitness monitor. Data obtained from motion sensors of the wearable fitness monitor and data obtained from heartbeat waveform sensors of the wearable fitness monitor may be used to identify the user.

Claims

1. A method, implemented on a wearable fitness monitor comprising one or more motion sensors and one or more processors, the method comprising:

(a) obtaining motion data of a wearer from the one or more motion sensors when the wearable fitness monitor is worn by the wearer, wherein the wearable fitness monitor is configured to be worn by a person;

(b) obtaining, by the one or more processors, a motion signature using the motion data of the wearer, wherein the motion signature characterizes a body movement;

(c) obtaining, by the one or more processors, a test feature vector from the motion signature;

(d) applying, by the one or more processors, a machine learning classifier to the test feature vector, wherein

the machine learning classifier was trained using motion data reflecting motions of one or more non-humans or one or more humans,

the machine learning classifier is configured to receive feature vectors as inputs and provide classifications of the feature vectors as outputs, and

the classifications indicate whether the feature vectors are obtained from non-humans;

(e) obtaining, using the machine learning classifier and by the one or more processors, a classification indicating whether the test feature vector is obtained from a non-human;

(f) determining, based on the classification obtained in (e) and by the one or more processors, the motion signature corresponds to an invalid motion feature, the invalid motion feature characterizing motion likely to be performed by a non-human; and

(g) preventing, based on the determination in (f) and by the one or more processors, the wearable fitness monitor from allowing a transaction.

2. The method of claim 1, wherein the transaction comprises accessing a secure item or providing an award for meeting an activity threshold to a user associated with the wearable fitness monitor.

3. The method of claim 1, further comprising, responsive to determining that the motion signature corresponds to the invalid motion feature, requiring the wearer to authenticate himself or herself.

4. The method of claim 3, wherein requiring the wearer to authenticate comprises requiring the wearer to input a passcode, a fingerprint, an iris image, an ECG, a facial image, a vocal message, or any combination thereof.

5. The method of claim 1, wherein determining the motion signature corresponds to an invalid motion feature in (e) comprises:

obtaining an additional signature using data from one or more additional sensors, and determining that the motion signature, the additional signature, or a combination thereof is inconsistent with at least one human activity.

6. The method of claim 1, wherein the invalid motion feature is a periodic motion having a cycle-to-cycle consistency greater than a threshold.

7. The method of claim 1, wherein the motion signature characterizes a cycle of periodic movement of a person wearing the wearable fitness monitor.

8. The method of claim 7, wherein the periodic movement is selected from the group consisting of running, walking, cycling, swimming, weight lifting, climbing, rowing, a gymnastic exercise, dancing, an aerobic exercise, a yoga routine, golfing, swinging a club, swinging a racquet, striking a ball or another object, swimming, diving, surfing, skating, skiing, skate boarding, exercising on a machine, driving a vehicle, and riding an animal.

9. The method of claim 1, wherein the obtaining the motion signature using the motion data of the wearer further comprises:

obtaining a cycle profile from the motion data.

10. The method of claim 9, wherein the obtaining the test feature vector from the motion signature of (c) comprises:

extracting one or more features from the cycle profile or values derived from the cycle profile, and combining one or more features into the feature vector.

11. The method of claim 10, wherein each feature is selected from the group consisting of:

a slope, an inflection, a zero crossing, a derivative, a moment, a cumulant, and any combination thereof.

12. The method of claim 1, wherein the machine learning classifier comprises a linear discriminant analysis classifier.

13. The method of claim 1, wherein the machine learning classifier comprises a neural network classifier.

14. A system comprising:

a wearable fitness monitor configured to be worn by a person and comprising;

one or more motion sensors, and

a communication interface configured for communicating data from the one or more motion sensors to a device external to the wearable fitness monitor; and

logic configured to;

(a) obtain motion data of a wearer from the one or more motion sensors when the wearable fitness monitor is worn by the wearer, wherein the wearable fitness monitor is configured to be worn by a person;

(b) obtain a motion signature using the motion data of the wearer, wherein the motion signature characterizes a body movement;

(c) obtain a test feature vector from the motion signature;

(d) apply a machine learning classifier to the test feature vector, wherein

the machine learning classifier was trained using motion data reflecting motions of one or more non-humans or one or more humans,

the machine learning classifier is configured to receive feature vectors as inputs and provide classifications of the feature vectors as outputs, and

the classifications indicate whether the feature vectors are obtained from non-humans;

(e) obtain, using the machine learning classifier, a classification indicating whether the test feature vector is obtained from a non-human;

(f) determine, based on the classification obtained in (e), the motion signature corresponds to an invalid motion feature, the invalid motion feature characterizing motion likely to be performed by a non-human; and

(g) prevent, based on the determination in (f), the wearable fitness monitor from allowing a transaction.

15. The system of claim 14, wherein the transaction comprises accessing a secure item or providing an award for meeting an activity threshold to a user associated with the wearable fitness monitor.

16. The system of claim 15, wherein the logic is further configured to:

responsive to determining that the motion signature corresponds to the invalid motion feature, require the wearer to authenticate himself or herself.

17. The system of claim 16, wherein requiring the wearer to authenticate comprises requiring the wearer to input a passcode, a fingerprint, an iris image, an ECG, a facial image, a vocal message, or any combination thereof.

18. The system of claim 14, wherein determining the motion signature corresponds to an invalid motion feature in (e) comprises:

obtaining an additional signature using data from one or more additional sensors, and determining that the motion signature, the additional signature, or a combination thereof is inconsistent with at least one human activity.

19. The system of claim 14, wherein the machine learning classifier comprises a linear discriminant analysis classifier.

20. The system of claim 14, wherein the machine learning classifier comprises a neural network classifier.