Time-Series Clustering With Dynamic Feature Mining in the Framework of Belief Function Theory

Clustering time-series data has gained abundant popularity and has been widely used in diverse scientific areas. However, few studies have systematically addressed the ambiguity and uncertainty contained in time-series clustering, which often leads to degraded clustering performance due to the high variability of time-series curves. Such ambiguity and uncertainty can be explained as the random dynamic changes of individual time series and are reflected in the clustering memberships of time-series data. Focusing on these issues, this article proposes a novel algorithm to tackle ambiguity and uncertainty in time-series clustering by capturing their dynamic features under the framework of belief function theory. Specifically, it employs an evidential Markov model for each time series to formalize dynamic features as a transition mass matrix, and an evidential clustering algorithm then derives a credal partition to group the data. Ablation studies validate the effectiveness of each component, and experiments on 128 UCR datasets demonstrate the strong performance of the proposed algorithm.