Biometric user authentication system and a method therefor

摘要

The present disclosure relates to a method and a system for authenticating a user. In one embodiment, one or more input and target data samples extracted from a plurality of physiological and movement signals of the user are processed to train one or more regression models. In real time authentication, the input and target data samples are extracted from the plurality of physiological and activity signals and mapped with trained regression models to determine a regression error. Based on the regression error, an appropriate authentication signal is then generated and transmitted to the user. Using dynamically selected multiple input and target data samples for user authentication increases the accuracy of authentication, thereby reducing possibilities of invalid authentication. Further, the power consumed by the sensors and computation load is reduced by dynamically powering up and powering down of the one or more sensors based on their usage during the authentication process.

主权项

1. A method of authenticating a subject, the method comprising:
receiving in real time, by a processor of a wearable device, at least a plurality of physiological and movement signals of the subject from one or more physiological and activity sensors of the wearable device; deriving, by the processor, one or more input and target data samples associated with the plurality of received physiological and movement signals; determining, by the processor, a regression error value based on the derived input and target data samples; transmitting, by the processor, a signal authenticating the subject based on the comparison of the determined regression error value with a predetermined threshold regression error value; receiving at least a plurality of physiological and movement signals of the subject from the one or more physiological and activity sensors; deriving one or more input and target data samples associated with the plurality of received physiological and movement signals; generating one or more combinations of input and target data samples by randomly selecting input and target data sample from the corresponding derived input and target data samples; and training one or more regression models based on the one or more generated combinations of the input and target data samples to generate one or more trained regression models associated with the subject; determining a model regression error value for each of the trained regression models; calculating a training progress value at a time based on the determined model regression error value and a predetermined training threshold value; and displaying the determined training progress value.