Activity recognition is the problem of automatically identifying and classifying human physical actions or behaviors — such as walking, sitting, falling, or gesturing — from signals captured by a sensing system, in this context channel state information (CSI) extracted from ambient WiFi transmissions without requiring subjects to carry any device. It is a central problem in wireless human sensing research because it enables a wide range of practical applications including smart home automation, elderly care monitoring, rehabilitation, and security surveillance using existing WiFi infrastructure. Key variants include coarse-grained activity recognition, which distinguishes between broad categories of movement such as stationary versus mobile states, and fine-grained recognition, which resolves more subtle or complex actions such as specific gestures or fall detection, with approaches spanning both traditional machine learning pipelines operating on handcrafted CSI features and deep learning methods that learn representations directly from raw or preprocessed CSI data.
Source Papers
- A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels ↗ — A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Cha
- An Overview on IEEE 802.11bf: WLAN Sensing ↗ — An Overview on IEEE 802.11bf: WLAN Sensing
- 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
- Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions ↗ — Occupancy Prediction in IoT-Enabled Smart Buildings: Technol
- Passive WiFi Radar for Human Sensing Using a Stand-Alone Access Point ↗ — Passive WiFi Radar for Human Sensing Using a Stand-Alone Acc
- Towards Environment Independent Device Free Human Activity Recognition ↗ — Towards Environment Independent Device Free Human Activity R
- WiFi CSI-based device-free sensing: from Fresnel zone model to CSI-ratio model ↗ — WiFi CSI-based device-free sensing: from Fresnel zone model
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information