Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition
Year: 2015
Type: conference-paper
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.
Authors: Skyler Seto, Wenyu Zhang, Yichen Zhou
Institution: Cornell University
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2963434542
