Edge computing refers to a distributed computing paradigm in which data processing and inference tasks are performed locally on or near the devices that collect sensor data, rather than being offloaded to centralized cloud servers. In the context of Wi-Fi CSI sensing, edge computing is significant because it enables low-latency, privacy-preserving, and bandwidth-efficient deployment of activity recognition, occupancy detection, and similar sensing applications in real-world environments such as vehicles, smart buildings, and public spaces. Key variants relevant to the field include on-device inference on embedded Wi-Fi hardware or single-board computers, and multi-node edge architectures in which several receivers collaboratively process CSI and RSSI streams locally before producing a final estimate, as demonstrated in passenger-counting systems that fuse data from multiple access points without relying on remote computation.
Source Papers
- 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
- RSSI-Assisted CSI-Based Passenger Counting with Multiple Wi-Fi Receivers ↗ — RSSI-Assisted CSI-Based Passenger Counting with Multiple Wi-