Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition
Authors:
- Skyler SetoSSSkyler Seto
- Wenyu ZhangWZWenyu Zhang
- Yichen ZhouYZYichen Zhou
Preprint
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Multivariate time series classification with parametric derivative dynamic time warpingExpert Systems with Applications, 2015
- Human motion recognition using a wireless sensor-based wearable systemPersonal and Ubiquitous Computing, 2011
- Activity recognition using cell phone accelerometersACM SIGKDD Explorations Newsletter, 2011
- A global averaging method for dynamic time warping, with applications to clusteringPattern Recognition, 2011
- Comparative study on classifying human activities with miniature inertial and magnetic sensorsPattern Recognition, 2010
- A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical RecognizerIEEE Transactions on Information Technology in Biomedicine, 2010
- Machine Learning Methods for Classifying Human Physical Activity from On-Body AccelerometersSensors, 2010
- Computing and Visualizing Dynamic Time Warping Alignments inR: ThedtwPackage2009
- Toward accurate dynamic time warping in linear time and spaceIntelligent Data Analysis: An International Journal, 2007
- Information Retrieval for Music and Motion2007