부산대학교 도서관

Recent studies corroborate Wi-Fi Channel State Information (CSI) usability to monitor patients remotely and obtain health information non-invasively and with low-cost. In addition to monitoring vital signs, this technology can also be applied to presence detection, subject recognition, position and movement identification, among other uses. Despite its wide range of potential applications, there is a lack of CSI datasets that cover multiple activities and include participants’ phenotype information to help develop, test, and compare new solutions. This study highlights the importance of building a robust public Wi-Fi CSI dataset. Therefore, we present eHealth CSI , a CSI dataset that includes a variety of Wi-Fi CSI data from more than 100 people in various activities in a controlled room. We also include CSI data collected in the same room without the presence of participants. This dataset was made publicly available online to other researchers under request. In this work, we introduce CSI technology and describe the data collection setup. In addition to CSI data, our dataset includes participants’ phenotype information and heartbeat rate monitoring data using a smartwatch.