Fuzzy representational structures for trend based analysis of time series clustering and classification

作者：

Highlights：

• Quantifying the trend in time series by fuzzy linguistic structures named fuzzylets.

• Boundary values by k-means and fuzzy degrees for the state of time series values.

• Clustering of fuzzylets to find optimal clusters by distance threshold and scores.

摘要

•Quantifying the trend in time series by fuzzy linguistic structures named fuzzylets.•Boundary values by k-means and fuzzy degrees for the state of time series values.•Clustering of fuzzylets to find optimal clusters by distance threshold and scores.

论文关键词：Time series,Fuzzy logic,Fuzzylets,Silhouette score,Clustering

论文评审过程：Received 18 February 2020, Revised 15 March 2021, Accepted 24 March 2021, Available online 26 March 2021, Version of Record 3 April 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.106991