Short-Time Fourier Transform (STFT) is a signal processing method that divides a time-domain signal, such as CSI amplitude or phase data, into short overlapping temporal windows and applies the Fourier Transform to each segment, producing a time-frequency representation that reveals how the spectral content of the signal evolves over time. In Wi-Fi sensing, STFT is particularly valuable because human activities such as walking, gestures, and respiration induce dynamic, non-stationary variations in the wireless channel that are more discriminative when analyzed jointly in both time and frequency domains rather than in either domain alone. Key variants and related considerations include the choice of window function, window length, and overlap ratio, which govern the trade-off between time and frequency resolution, and STFT is often used as a precursor to generating spectrograms that serve as two-dimensional input representations for deep learning models such as convolutional neural networks in activity recognition and localization tasks.
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
- A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects ↗ — A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techni
- A Survey on Wireless Device-free Human Sensing: Application Scenarios, Current Solutions, and Open Issues ↗ — A Survey on Wireless Device-free Human Sensing: Application
- On CSI and Passive Wi-Fi Radar for Opportunistic Physical Activity Recognition ↗ — On CSI and Passive Wi-Fi Radar for Opportunistic Physical Ac
- Passive WiFi Radar for Human Sensing Using a Stand-Alone Access Point ↗ — Passive WiFi Radar for Human Sensing Using a Stand-Alone Acc
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information
- WiFi-Based Human Sensing With Deep Learning: Recent Advances, Challenges, and Opportunities ↗ — WiFi-Based Human Sensing With Deep Learning: Recent Advances