Abstract:
In view of the high dimensionality and complexity of time series data bringing trouble to data mining and the importance of clustering analysis in the field of time series data mining, this paper summarizes the research status of time series data clustering at home and abroad. Time series clustering can be divided into the whole-time-series clustering, the subsequence clustering, and it can be studied from the aspects of feature representation, similarity measurement, clustering algorithm and cluster prototype, as well as the specific applications analysis. According to the main problems existed in the time series clustering, this work proposes some contents and directions that are worthy of being researched in the future. All the work is to better promote the research and development of time series data clustering.