No Cover Image

Journal article 233 views 41 downloads

Unsupervised Doppler Radar Based Activity Recognition for e-Healthcare

Yordanka Karayaneva Orcid Logo, Sara Sharifzadeh Orcid Logo, Wenda Li Orcid Logo, Yanguo Jing, Bo Tan Orcid Logo

IEEE Access, Volume: 9, Pages: 62984 - 63001

Swansea University Author: Sara Sharifzadeh Orcid Logo

  • 65599.VOR.pdf

    PDF | Version of Record

    This work is licensed under a Creative Commons Attribution 4.0 License.

    Download (1.98MB)

Check full text

DOI (Published version): 10.1109/access.2021.3074088

Abstract

Passive radio frequency (RF) sensing and monitoring of human daily activities in elderly care homes is an emerging topic. Micro-Doppler radars are an appealing solution considering their non-intrusiveness, deep penetration, and high-distance range. Unsupervised activity recognition using Doppler rad...

Full description

Published in: IEEE Access
ISSN: 2169-3536
Published: Institute of Electrical and Electronics Engineers (IEEE) 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65599
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Passive radio frequency (RF) sensing and monitoring of human daily activities in elderly care homes is an emerging topic. Micro-Doppler radars are an appealing solution considering their non-intrusiveness, deep penetration, and high-distance range. Unsupervised activity recognition using Doppler radar data has not received attention, in spite of its importance in case of unlabelled or poorly labelled activities in real scenarios. This study proposes two unsupervised feature extraction methods for the purpose of human activity monitoring using Doppler-streams. These include a local Discrete Cosine Transform (DCT)-based feature extraction method and a local entropy-based feature extraction method. In addition, a novel application of Convolutional Variational Autoencoder (CVAE) feature extraction is employed for the first time for Doppler radar data. The three feature extraction architectures are compared with the previously used Convolutional Autoencoder (CAE) and linear feature extraction based on Principal Component Analysis (PCA) and 2DPCA. Unsupervised clustering is performed using K-Means and K-Medoids. The results show the superiority of DCT-based method, entropy-based method, and CVAE features compared to CAE, PCA, and 2DPCA, with more than 5%-20% average accuracy. In regards to computation time, the two proposed methods are noticeably much faster than the existing CVAE. Furthermore, for high-dimensional data visualisation, three manifold learning techniques are considered. The methods are compared for the projection of raw data as well as the encoded CVAE features. All three methods show an improved visualisation ability when applied to the encoded CVAE features.
College: Faculty of Science and Engineering
Funders: DataDriven Research Innovation DDRI Coventry University
Start Page: 62984
End Page: 63001

Similar Items