Monitoring vital signs at rest while using channel state information of wi-fi signals and artificial intelligence tools /

Abstract

Breathing and heart rate are vital signs that might help identifying pathological conditions by its monitoring. This master’s thesis presents a system for monitoring breathing and heart rate, which combines con- ventional Channel State Information sensing approaches with Machine Learning techniques to provide a reliable monitoring. Also, a new sen- sitive subcarrier selection method, which is an important step for pro- cessing Channel State Information data, based on Hilbert Transform is presented. Along with the system’s description, this thesis provides the base theory for understanding each system’s component and the task that each component does. An exhaustive analysis was also performed and presented in order to understand Channel State Information data as well as the processing of data for vital signs monitoring. Results show that a reliable breathing rate monitoring can be achieved and raise questions about heart rate monitoring which are also answered in the same chapter.