Wearable sensor based system for person identification

• US 9,769,166 B1
• Filed: 10/19/2016
• Issued: 09/19/2017
• Est. Priority Date: 10/19/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lai, Jui-Hsin, Nai, Lifeng, Suzumara, Toyotaro, Xia, Yinglong
• Primary Examiner(s): THIAW, CATHERINE B
• Application Number:
  US15/297,825
• Time in Patent Office: 335 Days
• 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 5/0013 Medical image data A61B1/00011, A61B6/56, A61B8/56 take precedence
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/1118 Determining activity level
• 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 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/6802 Sensor mounted on worn items
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: H04L 63/083 using passwords cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226
• CPC Class Codes: H04L 63/0853 using an additional device, e.g. smartcard, SIM or a different communication terminal cryptographic mechanisms or cryptographic arrangements for entity authentication involving additional secure or trusted devices H04L9/3234
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04W 12/068 using credential vaults, e.g. password manager applications or one time password [OTP] applications
• CPC Class Codes: H04W 12/33 using wearable devices, e.g. using a smartwatch or smart-glasses

Abstract

A system, method and computer program product for real-time recognition of individuals. The method comprises: receiving at a hardware processor, a first sensor data associated with the individual. The first sensor data associated with the individual is processed to determine an activity the individual is currently engaged in. Additionally, a second sensor data associated with the individual is received and processed to determine a feature associated with a muscle of said individual while engaged in activity. Based on the received sensor data and determined activity and muscle features, the method generates a model that correlates determined activities and corresponding muscle features of the individual user with the individual'"'"'s identity. The model is subsequently used to identify the individual. By receiving and inputting real-time, sensor data from an individual into said generated model, the model generates and determines: an activity and a muscle feature for use in identifying the individual.

Claims

1. An identity recognition system comprising:

one or more accelerometer sensor devices and muscle sensor devices attached to and associated with an individual engaged in a physical activity; and

at least one processor and a memory coupled to the at least one processor, wherein the memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to;

receive, in real-time, a first sensor data from said one or more accelerometer devices attached to and associated with the individual;

receive, in real-time, a second sensor data from said muscle sensor devices attached to the individual'"'"'s arm, leg, stomach or chest muscle groups exclusive of the cardiac muscle of the individual;

input said real-time first sensor data from said one or more accelerometer devices to a model trained to correlate said first sensor data to a learned physical activity engaged by the individual;

determine, using said trained model and said real-time first sensor data, the physical activity currently engaged in by the individual;

input said real-time second sensor data from said muscle sensor devices to said trained model;

detect, using said trained model, a muscle feature of the individual based on said real-time second sensor data from said muscle sensor devices and said determined physical activity the individual is currently engaged in,

wherein said model is trained to further correlate the determined physical activity currently engaged in by the individual and corresponding muscle features of the individual with an identity of said individual, and

use the trained model to identify the individual, in real-time based on the determined physical activity the individual is currently engaged in and detected muscle feature of the individual.

2. The identity recognition system of claim 1, wherein said individual is desirous of accessing or opening a device having said at least one processor with which said model is run, wherein responsive to said identifying the individual, said instructions, when executed by the at least one processor, further cause the at least one processor to:

automatically activate the device to permit user access therein.

3. The identity recognition system of claim 1, wherein said individual is desirous of opening an application running on the device having said at least one processor with which said model is run, wherein responsive to said identifying the individual, said instructions, when executed by the at least one processor, further cause the at least one processor to:

automatically activate the application running on the device to permit user access to the application.

4. The identity recognition system of claim 1, wherein said individual is desirous of activating a remote system or device from said individual, wherein responsive to said identifying the individual, said instructions, when executed by the at least one processor, further cause the at least one processor to:

automatically initiate communication of a signal for use in activating and carrying out a function in the remote system or device.

5. The identify recognition system of claim 4, wherein the function carried out in the remote system or device is selected from the group consisting of:

open up a software application on the remote system or device, access a secure web-site or Internet location, control or switch on a remote device, automatically unlock or open a door of the individual'"'"'s residence.

6. The identity recognition system of claim 1, wherein responsive to said identifying the individual, said instructions, when executed by the at least one processor, further cause the at least one processor to:

automatically generate a password associated with that individual for use in opening activating a device or activating an application running on the device.

7. The identity recognition system of claim 1, wherein said instructions, when executed by the at least one processor, further cause the at least one processor to:

generate an activity mode parameter corresponding to the individual'"'"'s determined physical activity; and

use said activity mode parameter for determining said muscle feature of the individual'"'"'s determined physical activity.

8. The identity recognition system of claim 1, wherein said instructions, when executed by the at least one processor, further cause the at least one processor to:

use machine learning to train and update, based on received accelerometer sensor data, said model to classify an individual'"'"'s physical activity, wherein the determined physical activity currently engaged in by the individual is selected from the group consisting of;

walking, running, sitting idle, sleeping, driving a vehicle.

9. A method for recognizing individuals comprising:

receiving, in real-time, at at least one hardware processor, a first sensor data from one or more accelerometer devices attached to and associated with an individual engaged in a physical activity;

receiving, in real-time, at the at least one hardware processor, a second sensor data from one or more muscle sensor devices attached to the individual'"'"'s arm, leg, stomach or chest muscle groups exclusive of the cardiac muscle of the individual;

inputting, using said at least one hardware processor, said real-time first sensor data from said one or more accelerometer devices to a model trained to correlate said first sensor data to a learned physical activity engaged by the individual;

determining, using said trained model and said real-time first sensor data, the physical activity currently engaged in by the individual;

inputting, using said at least one hardware processor, said real-time second sensor data from said muscle sensor devices to said trained model;

detecting, using said trained model, a muscle feature of the individual based on said real-time second sensor data from said muscle sensor devices and said determined physical activity the individual is currently engaged in, wherein said model is trained to further correlate the determined physical activity currently engaged in by the individual and corresponding muscle features of the individual with an identity of said individual, and

using the trained model, at said least one hardware processor, to identify the individual in real-time, based on the determined physical activity the individual is currently engaged in and detected muscle feature of the individual.

10. The method of claim 9, wherein said individual is desirous of accessing or opening a device having said at least one hardware processor with which said model is run, wherein responsive to said identifying the individual, said method further comprises:

automatically activating, using said at least one hardware processor, the device to permit user access therein.

11. The method of claim 9, wherein said individual is desirous of opening an application running on the device having said at least one hardware processor with which said model is run, wherein responsive to said identifying the individual, said method further comprises:

automatically activating the application running on the device to permit user access to the application.

12. The method of claim 9, wherein said individual is desirous of activating a remote system or device from said individual, said method further comprising:

responsive to said identifying the individual, automatically initiating communication of a signal for use in activating and carrying out a function in the remote system or device.

13. The method of claim 12, wherein the function carried out in the remote system or device is selected from the group consisting of:

open up a software application on the remote system or device, access a secure web-site or Internet location, control or switch on a remote device, automatically unlock or open a door of the individual'"'"'s residence.

14. The method of claim 9, further comprising:

generating, using said at least one hardware processor, an activity mode parameter corresponding to the individual'"'"'s determined physical activity; and

using said activity mode parameter for determining said muscle feature of the individual'"'"'s determined physical activity.

15. The method of claim 9, further comprising:

using machine learning to train and update said model, at said at least one hardware processor, based on received accelerometer sensor data, to classify an individual'"'"'s physical activity, wherein the determined physical activity currently engaged in by the individual is selected from the group consisting of;

walking, running, sitting idle, sleeping, driving a vehicle.

16. A computer program product stored in a non-transitory computer-readable storage medium having computer readable program instructions, the computer readable program instructions read and carried out by at least one processor for performing a method for identity recognition, wherein the method comprises:

receiving, in real-time, at at least one processor, a first sensor data from one or more accelerometer devices attached to and associated with an individual engaged in a physical activity;

receiving, in real-time, at the at least one processor, a second sensor data from one or more muscle sensor devices attached to the individual'"'"'s arm, leg, stomach or chest muscle groups exclusive of the cardiac muscle of the individual;

inputting, using said at least one processor, said real-time first sensor data from said one or more accelerometer devices to a model trained to correlate said first sensor data to a learned physical activity engaged by the individual;

determining, using said trained model and said real-time first sensor data, the physical activity currently engaged in by the individual;

inputting, using said at least one processor, said real-time second sensor data from said muscle sensor devices to said trained model;

detecting, using said trained model, a muscle feature of the individual based on said real-time second sensor data from said muscle sensor devices and said determined physical activity the individual is currently engaged in, wherein said model is trained to further correlate the determined physical activity currently engaged in by the individual and corresponding muscle features of the individual with an identity of said individual, and

using the trained model, at said least one processor, to identify the individual in real-time, based on the determined physical activity the individual is currently engaged in and detected muscle feature of the individual.

17. The computer program product of claim 16, wherein said individual is desirous of accessing or opening a device having said at least one processor with which said model is run, or opening an application running on the device, wherein responsive to said identifying the individual, said method further comprises:

automatically activating, using said at least one processor, the device to permit user access therein and/or automatically activating the application running on the device to permit user access to the application.

18. The computer program product of claim 16, wherein said individual is desirous of activating a remote system or device from said individual, said method further comprising:

responsive to said identifying the individual, automatically initiating communication of a signal for use in activating and carrying out a function in the remote system or device.

19. The computer program product of claim 16, wherein said method further comprises:

generating an activity mode parameter corresponding to the individual'"'"'s determined physical activity; and

using said activity mode parameter for determining said muscle feature of the individual'"'"'s determined physical activity.

20. The computer program product of claim 16, wherein said method further comprises:

using machine learning to train and update said model based on received accelerometer sensor data, to classify an individual'"'"'s physical activity, wherein the a determined physical activity currently engaged in by the individual is selected from the group consisting of;

walking, running, sitting idle, sleeping, driving a vehicle.