Lightweight Biometric Sensing for Walker Classification Using Narrowband RF Links

Radar-Based Non-Contact Continuous Identity Authentication

Non-contact vital signs monitoring using microwave Doppler radar has shown great promise in healthcare applications. Recently, this unobtrusive form of physiological sensing has also been gaining attention for its potential for continuous identity authentication, which can reduce the vulnerability of traditional one-pass validation authentication systems. Physiological Doppler radar is an attractive approach for continuous identity authentication as it requires neither contact nor line-of-sight and does not give rise to privacy concerns associated with video imaging. This paper presents a review of recent advances in radar-based identity authentication systems. It includes an evaluation of the applicability of different research efforts in authentication using respiratory patterns and heart-based dynamics. It also identifies aspects of future research required to address remaining challenges in applying unobtrusive respiration-based or heart-based identity authentication to practical systems. With the advancement of machine learning and artificial intelligence, radar-based continuous authentication can grow to serve a wide range of valuable functions in society.

Support Vector Machine-Based Classifier for the Assessment of Finger Movement of Stroke Patients Undergoing Rehabilitation

Purpose

Traditionally, clinical evaluation of motor paralysis following stroke has been of value to physicians and therapists because it allows for immediate pathophysiological assessment without the need for specialized tools. However, current clinical methods do not provide objective quantification of movement; therefore, they are of limited use to physicians and therapists when assessing responses to rehabilitation. The present study aimed to create a support vector machine (SVM)-based classifier to analyze and validate finger kinematics using the leap motion controller. Results were compared with those of 24 stroke patients assessed by therapists.

Methods

A non-linear SVM was used to classify data according to the Brunnstrom recovery stages of finger movements by focusing on peak angle and peak velocity patterns during finger flexion and extension. One thousand bootstrap data values were generated by randomly drawing a series of sample data from the actual normalized kinematics-related data. Bootstrap data values were randomly classified into training (940) and testing (60) datasets. After establishing an SVM classification model by training with the normalized kinematics-related parameters of peak angle and peak velocity, the testing dataset was assigned to predict classification of paralytic movements.

Results

High separation accuracy was obtained (mean 0.863; 95% confidence interval 0.857–0.869; p = 0.006).

Conclusion

This study highlights the ability of artificial intelligence to assist physicians and therapists evaluating hand movement recovery of stroke patients.