The Discrete Wavelet Transform (DWT) is a mathematical signal processing technique that decomposes a signal into multiple frequency sub-bands at varying resolutions by applying a series of high-pass and low-pass filter pairs in a hierarchical, multi-scale fashion, producing both approximation and detail coefficients. In CSI-based sensing research, DWT is valued for its ability to simultaneously capture time and frequency information from non-stationary signals such as those produced by human motion, making it effective for extracting discriminative features from CSI amplitude or phase streams while suppressing noise and environmental interference. Key variants relevant to this domain include multi-level decomposition using specific wavelet families such as Haar, Daubechies, or Symlets, each offering different trade-offs between compactness and smoothness that influence feature quality in tasks such as occupancy detection, crowd counting, and activity recognition.
Source Papers
- A Novel Device-Free Counting Method Based on Channel Status Information ↗ — A Novel Device-Free Counting Method Based on Channel Status
- A Survey on Human Behavior Recognition Using Channel State Information ↗ — A Survey on Human Behavior Recognition Using Channel State I
- Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing ↗ — Context-Aware Predictive Coding: A Representation Learning F
- CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing ↗ — CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- 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
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition ↗ — Understanding and Modeling of WiFi Signal Based Human Activi