Research Article
Elderly Care - Human Activity Recognition Using Radar with an Open Dataset and Hybrid Maps
@INPROCEEDINGS{10.1007/978-3-030-95593-9_4, author={Xinyu Zhang and Qammer H. Abbasi and Francesco Fioranelli and Olivier Romain and Julien Le Kernec}, title={Elderly Care - Human Activity Recognition Using Radar with an Open Dataset and Hybrid Maps}, proceedings={Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. 16th EAI International Conference, BODYNETS 2021, Virtual Event, October 25-26, 2021, Proceedings}, proceedings_a={BODYNETS}, year={2022}, month={2}, keywords={Human activity recognition Convolutional neural network Transfer learning Radar Micro-Doppler Hybrid maps}, doi={10.1007/978-3-030-95593-9_4} }- Xinyu Zhang
Qammer H. Abbasi
Francesco Fioranelli
Olivier Romain
Julien Le Kernec
Year: 2022
Elderly Care - Human Activity Recognition Using Radar with an Open Dataset and Hybrid Maps
BODYNETS
Springer
DOI: 10.1007/978-3-030-95593-9_4
Abstract
Population ageing has become a severe problem worldwide. Human activity recognition (HAR) can play an important role to provide the elders with in-time healthcare. With the advantages of environmental insensitivity, contactless sensing and privacy protection, radar has been widely used for human activity detection. The micro-Doppler signatures (spectrograms) contain much information about human motion and are often applied in HAR. However, spectrograms only interpret magnitude information, resulting in suboptimal performances. We propose a radar-based HAR system using deep learning techniques. The data applied came from the open dataset “Radar signatures of human activities” created by the University of Glasgow. A new type of hybrid map was proposed, which concatenated the spectrograms amplitude and phase. After cropping the hybrid maps to focus on useful information, a convolutional neural network (CNN) based on LeNet-5 was designed for feature extraction and classification. In addition, the idea of transfer learning was applied for radar-based HAR to evaluate the classification performance of a pre-trained network. For this, GoogLeNet was taken and trained on the newly-produced hybrid maps. These initial results showed that the LeNet-5 CNN using only the spectrograms obtained an accuracy of 80.5%, while using the hybrid maps reached an accuracy of 84.3%, increasing by 3.8%. The classification result of transfer learning using GoogLeNet was 86.0%.
