LIBSVM is an open-source library for Support Vector Machines (SVM) that provides efficient implementations of SVM-based classification and regression algorithms, including variants such as C-SVC, nu-SVC, and epsilon-SVR. In WiFi/CSI sensing research, it is widely used to train and deploy classifiers that map extracted CSI features to occupancy states or crowd counts, enabling device-free sensing systems to distinguish between different numbers of occupants or presence conditions. Its importance to the field lies in its accessibility, computational efficiency, and support for multi-class classification, making it a practical baseline and production tool for translating raw channel state information into actionable occupancy estimates in smart building and residential environments.
Source Papers
- Device-Free Passive Identity Identification via WiFi Signals ↗ — Device-Free Passive Identity Identification via WiFi Signals
- Device-free occupancy detection and crowd counting in smart buildings with WiFi-enabled IoT ↗ — Device-free occupancy detection and crowd counting in smart
- Implementing Wi-Fi CSI-based room-level occupancy Estimation: an experimental study in multi-zone residential environments ↗ — Implementing Wi-Fi CSI-based room-level occupancy Estimation