ABSTRACT
The first works on human activity recognition (HAR) date back to the late ’90s [99, 49]. However, there are still a number of opportunities for the development of new techniques to improve accuracy, efficiency, and pervasiveness. This chapter surveys the state-of-the-art in human activity recognition systems using wearable sensors. In addition, it also includes a qualitative evaluation of these systems according to several aspects, such as the type of activities that they recognize, the sensors utilized, their energy consumption and computational complexity, the accuracy, and others.
