Improving the Supervised Learning of Activity Classifiers for Human Motion Data

Abstract

The ability to accurately recognize human activities from motion data is an important stepping-stone toward creating many types of intelligent user interfaces. Many supervised learning methods have been demonstrated for learning activity classifiers from data; however, these classifiers often fail due to noisy sensor data, lack of labeled training samples for rare actions and large individual differences in activity execution. In this chapter, the authors introduce two techniques for improving supervised learning of human activities from motion data: (1) an active learning framework to reduce the number of samples required to segment motion traces, and (2) an intelligent feature selection technique that both improves classification performance and reduces training time. They demonstrate how these techniques can be used to improve the classification of human household activities, an area of particular research interest since it facilitates the development of elder-care assistance systems to monitor household occupants.