TCN-MAML: A TCN-Based Model with Model-Agnostic Meta-Learning for Cross-Subject Human Activity Recognition

• Published in: Sensors (Basel, Switzerland) Vol. 25; no. 13; p. 4216
• Main Authors: Lin, Chih-Yang, Lin, Chia-Yu, Liu, Yu-Tso, Chen, Yi-Wei, Ng, Hui-Fuang, Shih, Timothy K.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 06.07.2025; MDPI
• Subjects: Accuracy; Adaptability; Adaptation; Algorithms; Datasets; Deep learning; Elder care; Embedded systems; Human Activities; human activity recognition; Human acts; Human behavior; Humans; Machine Learning; MAML; Neural networks; Neural Networks, Computer; Sensors; TCN; Wearable Electronic Devices; Wi-Fi; wireless sensor networks; Wireless Technology; MAML; wireless sensor networks; human activity recognition; TCN
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s25134216

Human activity recognition (HAR) using Wi-Fi-based sensing has emerged as a powerful, non-intrusive solution for monitoring human behavior in smart environments. Unlike wearable sensor systems that require user compliance, Wi-Fi channel state information (CSI) enables device-free recognition by capturing variations in signal propagation caused by human motion. This makes Wi-Fi sensing highly attractive for ambient healthcare, security, and elderly care applications. However, real-world deployment faces two major challenges: (1) significant cross-subject signal variability due to physical and behavioral differences among individuals, and (2) limited labeled data, which restricts model generalization. To address these sensor-related challenges, we propose TCN-MAML, a novel framework that integrates temporal convolutional networks (TCN) with model-agnostic meta-learning (MAML) for efficient cross-subject adaptation in data-scarce conditions. We evaluate our approach on a public Wi-Fi CSI dataset using a strict cross-subject protocol, where training and testing subjects do not overlap. The proposed TCN-MAML achieves 99.6% accuracy, demonstrating superior generalization and efficiency over baseline methods. Experimental results confirm the framework’s suitability for low-power, real-time HAR systems embedded in IoT sensor networks.