Radar-Based Human Activity Recognition Using Hyperdimensional Computing

Abstract

Aiming at realizing on-chip real-time human activity recognition based on the miniaturized and integrated radar with limited computational resources, hyperdimensional computing (HDC) is a promising method due to its unique advantages including high energy efficiency, excellent robustness, lightweight model, and superfast learning process. This article reports on the first use of HDC in the radar system to recognize human activities. First, we design an image mask method to minimize the impact of interference in original radar micro-Doppler spectrograms and apply a fast envelope extraction method to fully reflect features of different human activities. Subsequently, we select the most applicable representation methods for HDC to encode and recognize these features. To better accelerate the convergence speed, enable subtle adjustments of the HDC model, and improve the recognition accuracy, we propose a new adaptive retraining method, Mask-Retraining. Finally, the accuracy of recognizing six human activities using HDC with Mask-Retraining reaches 92.93%. Experimental results and comparisons between HDC and ten recognition algorithms demonstrate the validity of our methods. In most cases, HDC outperforms other algorithms being compared both in recognition accuracy and computational cost. Especially, HDC becomes the prime and irreplaceable candidate when only small datasets or finite data points are available.