Human Activity Recognition (HAR) is the problem of automatically identifying and classifying physical actions or movements performed by individuals — such as walking, sitting, falling, or gesturing — from sensor-collected data, in this context Channel State Information (CSI) captured via commodity WiFi hardware. HAR is a central benchmark task in WiFi CSI sensing research because it demonstrates the practical utility of passive, contactless sensing systems for applications in healthcare monitoring, smart home automation, and security. Key variants within the field include gesture recognition (fine-grained, short-duration hand or body movements), fall detection (a safety-critical binary or multi-class subset), and gait recognition, with research further distinguished by whether labeled data is used in supervised settings or whether self-supervised and representation learning approaches are employed to reduce annotation burden.
Source Papers
- CSI-Chain: A Complete End-to-End Framework for WiFi CSI Sensing ↗ — CSI-Chain: A Complete End-to-End Framework for WiFi CSI Sens
- Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing ↗ — Context-Aware Predictive Coding: A Representation Learning F
- Efficient machine learning for Wi-Fi CSI-based human activity recognition using fast Monte Carlo based feature extraction ↗ — Efficient machine learning for Wi-Fi CSI-based human activit
- Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning ↗ — Human Activity Recognition via Wi-Fi and Inertial Sensors Wi
- OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors ↗ — OPERAnet, a multimodal activity recognition dataset acquired
- Towards Environment Independent Device Free Human Activity Recognition ↗ — Towards Environment Independent Device Free Human Activity R
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired