A knowledge-light approach to personalised and open-ended human activity recognition.

Wijekoon, Anjana; Wiratunga, Nirmalie; Sani, Sadiq; Cooper, Kay

Abstract

Human Activity Recognition (HAR) is a core component of clinical decision support systems that rely on activity monitoring for self-management of chronic conditions such as Musculoskeletal Disorders. Deployment success of such applications in part depend on their ability to adapt to individual variations in human movement and to facilitate a range of human activity classes. Research in personalised HAR aims to learn models that are sensitive to the subtle nuances in human movement whilst Open-ended HAR learns models that can recognise activity classes out of the pre-defined set available at training. Current approaches to personalised HAR impose a data collection burden on the end user; whilst Open-ended HAR algorithms are heavily reliant on intermediary-level class descriptions. Instead of these 'knowledge-intensive' HAR algorithms; in this article, we propose a 'knowledge-light' method. Specifically, we show how by using a few seconds of raw sensor data, obtained through micro-interactions with the end-user, we can effectively personalise HAR models and transfer recognition functionality to new activities with zero re-training of the model after deployment. We introduce a Personalised Open-ended HAR algorithm, MNZ, a user context aware Matching Network architecture and evaluate on 3 HAR data sources. Performance results show up to 48.9% improvement with personalisation and up to 18.3% improvement compared to the most common 'knowledge-intensive' Open-ended HAR algorithms.

Citation

WIJEKOON, A., WIRATUNGA, N., SANI, S. and COOPER, K. 2020. A knowledge-light approach to personalised and open-ended human activity recognition. Knowledge-based systems [online], 192, article ID 105651. Available from: https://doi.org/10.1016/j.knosys.2020.105651

• Journal Article Type: Article
• Acceptance Date: Feb 9, 2020
• Online Publication Date: Feb 13, 2020
• Publication Date: Mar 15, 2020
• Deposit Date: Feb 11, 2020
• Publicly Available Date: Feb 14, 2021
• Journal: Knowledge-based systems
• Print ISSN: 0950-7051
• Electronic ISSN: 1872-7409
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 192
• Article Number: 105651
• DOI: https://doi.org/10.1016/j.knosys.2020.105651
• Keywords: Human activity recognition; Personalised HAR; Open-ended HAR; Zero-shot learning; Matching networks
• Public URL: https://rgu-repository.worktribe.com/output/854277