Inertial Body-Worn Sensor Data Segmentation by Boosting Threshold-Based Detectors

Abstract

Using inertial body-worn sensors, we propose a segmentation approach to detect when a user changes actions. We use Adaboost to combine three threshold-based detectors: force/gravity ratios, peaks of autocorrelation, and local minimums of velocity. Experimenting with the CMU Multi-Modal Activity Database, we find that the first two features are the most important, and our combination approach improves performance with an acceptable level of granularity.