Wearable-based behaviour interpolation for semi-supervised human activity recognition

Duan, Haoran; Wang, Shidong; Ojha, Varun; Wang, Shizheng; Huang, Yawen; Long, Yang; Ranjan, Rajiv; Zheng, Yefeng

Abstract

While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-and-error process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learning-based HAR requires a large amount of labelled data and extracting HAR features from unlabelled data for effective deep learning training remains challenging. We, therefore, introduce a deep semi-supervised HAR approach, MixHAR, which concurrently uses labelled and unlabelled activities. Our MixHAR employs a linear interpolation mechanism to blend labelled and unlabelled activities while addressing both inter- and intra-activity variability. A unique challenge identified is the activity-intrusion problem during mixing, for which we propose a mixing calibration mechanism to mitigate it in the feature embedding space. Additionally, we rigorously explored and evaluated the five conventional/popular deep semi-supervised technologies on HAR, acting as the benchmark of deep semi-supervised HAR. Our results demonstrate that MixHAR significantly improves performance, underscoring the potential of deep semi-supervised techniques in HAR.

Citation

Duan, H., Wang, S., Ojha, V., Wang, S., Huang, Y., Long, Y., …Zheng, Y. (2024). Wearable-based behaviour interpolation for semi-supervised human activity recognition. Information Sciences, 665, Article 120393. https://doi.org/10.1016/j.ins.2024.120393

• Journal Article Type: Article
• Acceptance Date: Feb 28, 2024
• Online Publication Date: Mar 5, 2024
• Publication Date: 2024-04
• Deposit Date: May 16, 2024
• Publicly Available Date: May 16, 2024
• Journal: Information Sciences
• Print ISSN: 0020-0255
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 665
• Article Number: 120393
• DOI: https://doi.org/10.1016/j.ins.2024.120393
• Public URL: https://durham-repository.worktribe.com/output/2441901