Loading [a11y]/accessibility-menu.js
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition | IEEE Conference Publication | IEEE Xplore

Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition


Abstract:

Accurate and computationally efficient means for classifying human activities have been the subject of extensive research efforts. Most current research focuses on extrac...Show More

Abstract:

Accurate and computationally efficient means for classifying human activities have been the subject of extensive research efforts. Most current research focuses on extracting complex features to achieve high classification accuracy. We propose a template selection approach based on Dynamic Time Warping, such that complex feature extraction and domain knowledge is avoided. We demonstrate the predictive capability of the algorithm on both simulated and real smartphone data.
Date of Conference: 07-10 December 2015
Date Added to IEEE Xplore: 11 January 2016
Print ISBN:978-1-4799-7560-0
Conference Location: Cape Town, South Africa