A moving average filter is a signal smoothing technique that replaces each data point in a time series with the average of a surrounding window of consecutive samples, effectively attenuating high-frequency noise while preserving the underlying trend of the signal. In WiFi CSI sensing, it is applied to raw CSI amplitude or phase streams to reduce transient fluctuations caused by environmental interference, hardware imperfections, and multipath variability, thereby improving the reliability of features extracted for tasks such as human activity recognition. Key variants include the simple moving average, which weights all samples in the window equally, and the exponential moving average, which assigns greater weight to more recent samples and responds more adaptively to genuine signal changes, with window size serving as the primary tuning parameter that governs the trade-off between noise suppression and temporal resolution.
Source Papers
- CRPF-QC: An Efficient CSI Recurrence Plot-Based Framework for Queue Counting ↗ — CRPF-QC: An Efficient CSI Recurrence Plot-Based Framework fo
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning ↗ — Human Activity Recognition via Wi-Fi and Inertial Sensors Wi
- OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors ↗ — OPERAnet, a multimodal activity recognition dataset acquired
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information