Human Daily Breathing Monitoring via Analysis of CSI Ratio Trajectories for WiFi Link Pairs on the I/Q Plane

The measurement of human breathing is crucial for assessing the condition of the body. It opens up possibilities for various intelligent applications, like advanced medical monitoring and sleep analysis. Conventional approaches relying on wearable devices tend to be expensive and inconvenient for users. Recent research has shown that inexpensive WiFi devices commonly available in the market can be utilized effectively for non-contact breathing monitoring. WiFi-based breathing monitoring is highly sensitive to motion during the breathing process. This sensitivity arises because current methods primarily rely on extracting breathing signals from the amplitude and phase variations of WiFi Channel State Information (CSI) during breathing. However, these variations can be masked by body movements, leading to inaccurate counting of breathing cycles. To address this issue, we propose a method for extracting breathing signals based on the trajectories of two-chain CSI ratios on the I/Q plane. This method accurately monitors breathing by tracking and identifying the inflection points of the CSI ratio samples' trajectories on the I/Q plane throughout the breathing cycle. We propose a dispersion model to label and filter out CSI ratio samples representing significant motion interference, thereby enhancing the robustness of the breathing monitoring system. Furthermore, to obtain accurate breathing waveforms, we propose a method for fitting the trajectory curve of the CSI ratio samples. Based on the fitted curve, a breathing segment extraction algorithm is introduced, enabling precise breathing monitoring. Our experimental results demonstrate that this approach achieves minimal error and significantly enhances the accuracy of WiFi-based breathing monitoring.