A Competitive Approach for Human Activity Recognition on Smartphones

Abstract. This paper describes a competitive approach developed for an activity recognition challenge. The competition was defined on a new and publicly available dataset of human activities, recorded with smart-phone sensors. This work investigates different feature sets for the activity recognition task of the competition. Moreover, the focus is also on the in-troduction of a new, confidence-based boosting algorithm called ConfAda-Boost.M1. Results show that the new classification method outperforms commonly used classifiers, such as decision trees or AdaBoost.M1.