Improved time series clustering based on new geometric frameworks
作者：
Highlights：
• We use the geometrical information of the time series via Takens embedding.
• We analyze the geometrical information obtained by the embedding on the Stiefel, the unit sphere and the manifolds.
• We point out the gain obtained by such an embedding with respect to traditional time series clustering approaches.
• We analyze over 79 times series databases different frameworks.
• The advocated framework is the Stiefel embedding followed by the UMAP and HDBSCAN algorithms.
摘要
•We use the geometrical information of the time series via Takens embedding.•We analyze the geometrical information obtained by the embedding on the Stiefel, the unit sphere and the manifolds.•We point out the gain obtained by such an embedding with respect to traditional time series clustering approaches.•We analyze over 79 times series databases different frameworks.•The advocated framework is the Stiefel embedding followed by the UMAP and HDBSCAN algorithms.
论文关键词：Clustering,Time series,Delayed coordinate embedding,Embedding,Stiefel manifold,UMAP,HDBSCAN
论文评审过程：Received 2 November 2020, Revised 3 November 2021, Accepted 6 November 2021, Available online 9 November 2021, Version of Record 28 February 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108423
