The Savitzky-Golay filter is a polynomial smoothing technique that fits successive subsets of adjacent data points with a low-degree polynomial via least-squares regression, effectively reducing noise while preserving the shape and higher-order moments of a signal. In CSI-based sensing research, it is applied as a preprocessing step to smooth raw CSI amplitude or phase time series, removing high-frequency noise and transient fluctuations that would otherwise obscure subtle motion-related features needed for accurate activity or occupancy recognition. Key variants differ in the choice of polynomial order and window size, where higher-order polynomials better preserve sharp signal features and larger windows provide stronger smoothing, requiring practitioners to balance noise suppression against signal fidelity depending on the temporal dynamics of the target behavior.
Source Papers
- A Survey on Human Behavior Recognition Using Channel State Information ↗ — A Survey on Human Behavior Recognition Using Channel State I
- Guiding Wi-Fi Sensor Placement for Enhanced CSI-Based Sensing in Stationary Crowd Counting ↗ — Guiding Wi-Fi Sensor Placement for Enhanced CSI-Based Sensin
- 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
- RSSI-Assisted CSI-Based Passenger Counting with Multiple Wi-Fi Receivers ↗ — RSSI-Assisted CSI-Based Passenger Counting with Multiple Wi-
- Time matters: Empirical insights into the limits and challenges of temporal generalization in CSI-based Wi-Fi sensing ↗ — Time matters: Empirical insights into the limits and challen
- Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free Crowd Counting and Localization ↗ — Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free