SenseFi is a large-scale, publicly available benchmark dataset designed specifically for WiFi CSI-based human sensing tasks, providing standardized CSI measurements collected across multiple environments, subjects, and activities to support the development and fair evaluation of deep learning models. It matters for the field because it addresses the longstanding scarcity of labeled, reproducible CSI data, enabling systematic comparison of sensing algorithms for tasks such as activity recognition, gesture detection, and human identification without requiring researchers to collect their own domain-specific data. The dataset is notably associated with a unified benchmark framework that supports multiple deep learning architectures and cross-domain evaluation scenarios, making it a foundational resource for advancing both supervised and transfer learning approaches in WiFi sensing research.
Source Papers
- A Survey on Green Wireless Sensing: Energy-Efficient Sensing via WiFi CSI and Lightweight Learning ↗ — A Survey on Green Wireless Sensing: Energy-Efficient Sensing
- WiFi-Based Human Sensing With Deep Learning: Recent Advances, Challenges, and Opportunities ↗ — WiFi-Based Human Sensing With Deep Learning: Recent Advances