Adaptively constrained dynamic time warping for time series classification and clustering.
Information Sciences(2020)
摘要
•State of the art survey of the development and application of trajectory similarity measurement methods.•Criticize the shortcomings of traditional Dynamic Time Warping (DTW) methods.•Develop new adaptive penalty functions to overcome the shortcomings.•Realize accurate measurement of distances between trajectories.•Demonstrate the advantages of the Adaptively Constrained Dynamic Time Warping (ACDTW) algorithm through trajectory classification and clustering experiments.
更多查看译文
关键词
Dynamic time warping,Distance measure,Time series classification,Vessel trajectory clustering
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络