Wearable sensor based system for person identification
First Claim
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, anduse 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 Assignments
0 Petitions
Accused Products
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.
-
Citations
20 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
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. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
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. - View Dependent Claims (17, 18, 19, 20)
-
Specification