| Summary: | Respiration, a vital basis for life, is a key indicator of health status for human being. Recently, with contact-based devices, some breathing signal detection methods have been proposed, which can achieve high precision, high signal to noise ratio performance. However, these methods require users to be contacted
with the devices, which can cause a series of problems, such as hindering the movement of users or bringing some unpleasant feelings to users. Therefore, there is an urgent need to call for a contactless solution to extract respiratory signals. With the popularity of the indoor wireless devices, breath detection
with wireless sensors has drawn a lot of attention. However, the multipath effects, which commonly exist in indoor environments, have serious impacts on the propagation of wireless signals, leading to signal attenuation and poor received quality. Moreover, although the channel state information (CSI) can be readily collected from commercial off-the-shelf (COTS) WiFi devices, the phase of the CSI is distorted due to various offsets introduced during the receiving and transmitting of the wireless signals. In this dissertation, we try to resolve the challenges mentioned above, and design a CNN model for indoor respiration detection, which utilizes the CSI data from COTS WiFi devices. The final result shows an accuracy of 96.05% for human respiration detection.
|
|---|