CSI-based human activity recognition refers to the use of Channel State Information extracted from Wi-Fi signals to identify and classify human physical actions, behaviors, or movements without requiring subjects to carry dedicated sensors or devices. By analyzing how the multipath propagation characteristics of wireless signals are perturbed by human motion, researchers can distinguish activities ranging from coarse gestures and gait patterns to fine-grained actions such as falls, breathing, and sign language, making it a non-intrusive and privacy-preserving alternative to camera- or wearable-based sensing. The field encompasses several key variants organized by methodology, including pattern-based approaches that rely on handcrafted signal features and model-based approaches that exploit physical channel models, as well as learning-driven pipelines spanning traditional machine learning and deep learning architectures, with reproducibility and cross-environment generalization remaining central open challenges.
Source Papers
- A Survey on Human Behavior Recognition Using Channel State Information ↗ — A Survey on Human Behavior Recognition Using Channel State I
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- 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
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition ↗ — Understanding and Modeling of WiFi Signal Based Human Activi
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired