Privacy-Preserving Cross-Environment Human Activity Recognition
- 24 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (3) , 1765-1775
Abstract
Recent studies have demonstrated the success of using the channel state information (CSI) from the WiFi signal to analyze human activities in a fixed and well-controlled environment. Those systems usually degrade when being deployed in new environments. A straightforward solution to solve this limitation is to collect and annotate data samples from different environments with advanced learning strategies. Although workable as reported, those methods are often privacy sensitive because the training algorithms need to access the data from different environments, which may be owned by different organizations. We present a practical method for the WiFi-based privacy-preserving cross-environment human activity recognition (HAR). It collects and shares information from different environments, while maintaining the privacy of individual person being involved. At the core of our approach is the utilization of the Johnson–Lindenstrauss transform, which is theoretically shown to be differentially private. Based on that, we further design an adversarial learning strategy to generate environment-invariant representations for HAR. We demonstrate the effectiveness of the proposed method with different data modalities from two real-life environments. More specifically, on the raw CSI dataset, it shows 2.18% and 1.24% improvements over challenging baselines for two environments, respectively. Moreover, with the discrete wavelet transform features, it further yields 5.71% and 1.55% improvements, respectively.Keywords
Funding Information
- National Natural Science Foundation of China (61903231)
This publication has 54 references indexed in Scilit:
- Keystroke Recognition Using WiFi Signals2015
- Tracking Keystrokes Using Wireless Signals2015
- Non-Invasive Detection of Moving and Stationary Human With WiFiIEEE Journal on Selected Areas in Communications, 2015
- Robust Extreme Learning Machine With its Application to Indoor PositioningIEEE Transactions on Cybernetics, 2015
- Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural LearningIEEE Transactions on Cybernetics, 2014
- Omnidirectional Coverage for Device-Free Passive Human DetectionIEEE Transactions on Parallel and Distributed Systems, 2013
- Multilevel Depth and Image Fusion for Human Activity DetectionIEEE Transactions on Cybernetics, 2013
- Tool releaseACM SIGCOMM Computer Communication Review, 2011
- Wireless Location Privacy Protection in Vehicular Ad-Hoc NetworksMobile Networks and Applications, 2009
- Extensions of Lipschitz mappings into a Hilbert space1984