Analysis of Home Health Sensor Data

This chapter focuses on the analysis of data that is collected from sensors in the home environment. First we discuss the need for a good model that relates sensor data (or features derived from the data) to indicators of health and well-being. Then we present several methods for model building. We distinguish between supervised methods that need data annotated with the desired health indicators, unsupervised methods that find characteristic patterns by just analyzing large amounts of data, and knowledge-driven methods that use expert knowledge. We discuss the advantages and disadvantages of the different methods.