BriefGPT.xyz
Dec, 2015
使用动态时间规整模板选择的多元时间序列分类，用于人类活动识别
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition
HTML
PDF
Skyler Seto, Wenyu Zhang, Yichen Zhou
TL;DR
本文提出了一种基于动态时间规整的模板选择方法，避免了复杂特征提取和领域知识，展示了该算法在模拟和真实智能手机数据上的预测能力。
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
classificat
→