Human activity classification using radar signal and RNN networks

Conference Paper (2020)
Author(s)

Haoyang Jiang (University of Electronic Science and Technology of China)

Francesco Fioranelli (TU Delft - Microwave Sensing, Signals & Systems)

Shufan Yang (University of Glasgow)

Olivier Romain (CY University)

Julien Le Kernec (University of Electronic Science and Technology of China, CY University, University of Glasgow)

Microwave Sensing, Signals & Systems
DOI related publication
https://doi.org/10.1049/icp.2021.0556
More Info
expand_more
Publication Year
2020
Language
English
Microwave Sensing, Signals & Systems
Volume number
2020
Pages (from-to)
1595-1599
ISBN (electronic)
9781839535406

Abstract

Radar-based human activities recognition is still an open problem and is a key to detect anomalous behaviour for security and health applications. Deep learning networks such as convolutional neural networks (CNN) have been proposed for such tasks and showed better performance than traditional supervised learning paradigm. However, it is hard to deploy CNN networks to embedded systems due to the limited computational power available. From this point of concern, the use of a recurrent neural network (RNN) is proposed in this paper for human activities classification. We also propose an innovative data argumentation method to train the neural network using a limited number of data. The experiment shows that our network can achieve a mean accuracy of 94.3% in human activity classification.

No files available

Metadata only record. There are no files for this record.