Democratizing Federated WiFi-based Human Activity Recognition Using Hypothesis Transfer

Page view(s)
13
Checked on Feb 07, 2025
Democratizing Federated WiFi-based Human Activity Recognition Using Hypothesis Transfer
Title:
Democratizing Federated WiFi-based Human Activity Recognition Using Hypothesis Transfer
Journal Title:
IEEE Transactions on Mobile Computing
Keywords:
Publication Date:
10 September 2024
Citation:
Li, B., Cui, W., Zhang, L., Yang, Q., Wu, M., & Zhou, J. T. (2024). Democratizing Federated WiFi-based Human Activity Recognition Using Hypothesis Transfer. IEEE Transactions on Mobile Computing, 1–17. https://doi.org/10.1109/tmc.2024.3457788
Abstract:
Human activity recognition (HAR) is a crucial task in IoT systems with applications ranging from surveillance and intruder detection to home automation and more. Recently, non-invasive HAR utilizing WiFi signals has gained considerable attention due to advancements in ubiquitous WiFi technologies. However, recent studies have revealed significant privacy risks associated with WiFi signals, raising concerns about bio-information leakage. To address these concerns, the decentralized paradigm, particularly federated learning (FL), has emerged as a promising approach for training HAR models while preserving data privacy. Nevertheless, FL models may struggle in end-user environments due to substantial domain discrepancies between the source training data and the target end-user environment. This discrepancy arises from the sensitivity of WiFi signals to environmental changes, resulting in notable domain shifts. As a consequence, FL-based HAR approaches often face challenges when deployed in real-world WiFi environments. Albeit there are pioneer attempts on federated domain adaptation, they typically require non-trivial communication and computation cost, which is prohibitively expensive especially considering edge-based hardware equipment of end-user environment. In this paper, we propose a model to democratize the WiFi-based HAR system by enhancing recognition accuracy in unannotated end-user environments while prioritizing data privacy. Our model leverages the hypothesis transfer and a lightweight hypothesis ensemble to mitigate negative transfer. We prove a tighter theoretical upper bound compared to existing multi-source federated domain adaptation models. Extensive experiments shows our model improves the average accuracy by approximately 10 absolute percentage points in both cross-person and cross-environment settings comparing several state-of-the-art baselines.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Natural Science Foundation of China - N/A
Grant Reference no. : 62476053

This research / project is supported by the Key Program for International Cooperation of Ministry of Science and Technology, China - N/A
Grant Reference no. : 2024YFE0100700
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1536-1233
1558-0660
2161-9875
Files uploaded:

File Size Format Action
federated-wifi-har-camera-ready-1.pdf 3.36 MB PDF Open