Breathing Rate Estimation for Multiple People Using Wi-Fi Channel State Information

Abnormal breathing in daily life can be indicative of various diseases. Daily measurement of breathing rate enables the early detection of diseases and rescue of patients in severe cases. Wi-Fi, which is widely used in day-to-day life, is a suitable sensing method for daily measurements. Accordingly, a breathing rate estimation method using the Wi-Fi channel state information (CSI) was developed. In the conventional method, an accuracy of up to 99% was achieved in the estimation of breathing rates for singular individuals. However, this accuracy is insufficient for multiple individuals owing to the interference of vital signals obtained from CSI. Therefore, this study proposes a multi-person breathing rate estimation system that suppresses vital signal interference. To estimate the breathing rate of multiple people, the proposed method employs Tucker decomposition to decompose vital signals from the CSI. The processing speed and accuracy were improved using the proposed method. Finally, the effectiveness of the proposed method was demonstrated through experiments.