The Fast Fourier Transform (FFT) is a computationally efficient algorithm for converting time-domain or spatial-domain signals into their frequency-domain representations, decomposing a signal into its constituent frequency components. In WiFi/CSI sensing, FFT is applied to raw CSI amplitude and phase data to extract frequency-domain features that capture periodic motion patterns — such as the rhythmic movements characteristic of gestures or the subtle environmental disturbances caused by occupants — which are difficult to discern in the time domain. Key variants relevant to this field include the Short-Time Fourier Transform (STFT), which applies FFT over sliding temporal windows to capture time-varying spectral content, and the Inverse FFT (IFFT), which is used in channel reconstruction or noise filtering pipelines to transform processed frequency-domain data back into the time or spatial domain.

Source Papers

  • A Survey on Green Wireless Sensing: Energy-Efficient Sensing via WiFi CSI and Lightweight Learning — A Survey on Green Wireless Sensing: Energy-Efficient Sensing
  • An Overview on IEEE 802.11bf: WLAN Sensing — An Overview on IEEE 802.11bf: WLAN Sensing
  • Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey — Deep Learning-Enhanced Human Sensing with Channel State Info
  • Device-Free Passive Identity Identification via WiFi Signals — Device-Free Passive Identity Identification via WiFi Signals
  • Device-Free Wireless Sensing for Gesture Recognition Based on Complementary CSI Amplitude and Phase — Device-Free Wireless Sensing for Gesture Recognition Based o
  • Device-free occupancy detection and crowd counting in smart buildings with WiFi-enabled IoT — Device-free occupancy detection and crowd counting in smart
  • FreeCount: Device-Free Crowd Counting with Commodity WiFi — FreeCount: Device-Free Crowd Counting with Commodity WiFi
  • Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning — Human Activity Recognition via Wi-Fi and Inertial Sensors Wi
  • MMCOUNT: Stationary Crowd Counting System Based on Commodity Millimeter-Wave Radar — MMCOUNT: Stationary Crowd Counting System Based on Commodity
  • OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors — OPERAnet, a multimodal activity recognition dataset acquired
  • Passive WiFi Radar for Human Sensing Using a Stand-Alone Access Point — Passive WiFi Radar for Human Sensing Using a Stand-Alone Acc
  • 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
  • Towards Environment Independent Device Free Human Activity Recognition — Towards Environment Independent Device Free Human Activity R
  • WiFi Sensing with Channel State Information — WiFi Sensing with Channel State Information