2012 16th International Symposium on Wearable Computers (2012)
June 18, 2012 to June 22, 2012
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ISWC.2012.27
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.
Detectors, Correlation, Gravity, Acceleration, Measurement uncertainty, Wearable computers
Y. Shi, Y. Shi and X. Wang, "Inertial Body-Worn Sensor Data Segmentation by Boosting Threshold-Based Detectors," 2012 16th Annual International Symposium on Wearable Computers (ISWC), Newcastle, 2012, pp. 114-115.