Linear interpolation is a mathematical technique used in WiFi/CSI sensing to estimate missing or corrupted data values by computing a weighted average between two known neighboring data points, effectively filling gaps in CSI time-series or frequency-domain measurements caused by packet loss, hardware instability, or subcarrier noise. In the context of CSI-based sensing, it is critical for ensuring signal continuity and data quality, as incomplete or irregular CSI streams can significantly degrade the performance of downstream processing steps such as feature extraction, gait analysis, or occupancy classification. Common variants include time-domain linear interpolation, applied along the temporal axis to recover missing CSI amplitude or phase samples, and frequency-domain linear interpolation, used to reconstruct values across subcarrier indices where certain subcarriers are unreliable or absent.
Source Papers
- Device-Free Passive Identity Identification via WiFi Signals ↗ — Device-Free Passive Identity Identification via WiFi Signals
- 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