WiAR is a publicly available CSI-based dataset designed to support wireless human activity recognition research, capturing channel state information across multiple subjects performing a defined set of human activities or gestures in indoor environments. It matters to the field because it provides a standardized benchmark for developing and evaluating CSI-based sensing models, enabling reproducibility and fair comparison across different algorithmic approaches. The dataset is notably referenced in reproducibility-focused surveys as an example of openly accessible resources that facilitate systematic evaluation of Wi-Fi sensing methods, and it may include variants across different environmental conditions, antenna configurations, or activity subsets to support diverse experimental protocols.
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
- 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
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- Exposing the CSI: A Systematic Investigation of CSI-based Wi-Fi Sensing Capabilities and Limitations ↗ — Exposing the CSI: A Systematic Investigation of CSI-based Wi
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing ↗ — WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activi