FallDeFi is a publicly available CSI-based Wi-Fi sensing dataset specifically designed for fall detection research, capturing channel state information corresponding to human fall events and other activities in indoor environments. It is significant to the field because it provides a standardized benchmark that enables reproducible evaluation and comparison of fall detection algorithms across different studies, contributing to the broader effort of validating CSI-based passive human sensing systems. The dataset has been referenced alongside other benchmark collections in surveys examining reproducibility and generalizability of deep learning models for WiFi-based sensing, and it serves as a foundational resource for researchers developing and testing activity recognition and anomaly detection pipelines where distinguishing falls from routine movements is a critical challenge.
Source Papers
- 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
- WiFi-Based Human Sensing With Deep Learning: Recent Advances, Challenges, and Opportunities ↗ — WiFi-Based Human Sensing With Deep Learning: Recent Advances
- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing ↗ — WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activi