Hierarchical feature recovery for robust human activity recognition in body Sensor networks

Oishi, Nobuyuki, Lago, Paula, Birch, Philip and Roggen, Daniel (2022) Hierarchical feature recovery for robust human activity recognition in body Sensor networks. 10th International Workshop on Human Activity Sensing Corpus and its Application, Cambridge, September 11-15 2022. Published in: Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp/ISWC '22 Adjunct). ACM ISBN 978-1-4503-9423-9 (Accepted)

[img] PDF - Submitted Version
Download (882kB)
[img] PDF - Accepted Version
Download (879kB)

Abstract

With the advances in Body Sensor Networks (BSNs) and textile-integrated sensing, more sensor data becomes available from which human activities are recognised. However, some sensors may become unavailable unexpectedly in practice. Previous work proposed to complement the features of a missing sensor with regression-based methods but considered only up to one sensor missing and thus lacked a mechanism for selecting relevant sensors when multiple sensors were missing. The number of unique combinations of missing sensors increases exponentially when multiple sensors may be missing. To handle this, we propose a Hierarchical Feature Recovery (HFR) approach. We first assess the dependencies between sensors by comparing the feature mapping accuracy between each sensor and then evaluate the HFR approach on a dataset of activities of daily living with 17 gestures using 14 motion sensors. Our HFR method can alleviate classification performance drop by up to 8.3 pp compared to a baseline method.

Item Type: Conference Proceedings
Keywords: Sensor-based Human Activity Recognition, Body Sensor Network, Fault-tolerance
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Research Centres and Groups: Sensor Technology Research Centre
Related URLs:
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 27 Sep 2022 10:48
Last Modified: 27 Sep 2022 10:48
URI: http://sro.sussex.ac.uk/id/eprint/108153

View download statistics for this item

📧 Request an update