A Method Based on Lie Group Machine Learning for Multivariate Time-Series Clustering

A multivariate time series (MTS) is a data series formed from observations of multiple variables at multiple time points, which may exhibit interdependencies and temporal dependencies. The high dimension and complex structure of MTS data present challenges to existing clustering methods in terms of feature dimension, computational complexity, and accuracy. To address these issues, we introduce a Lie Group machine learning method and propose a novel multivariate Time-series Clustering method based on Lie Group Intrinsic Mean (T-CLGIM) to enhance clustering performance. We conducted extensive experiments on eight public and challenging MTS datasets. The results demonstrate that our method significantly outperforms state-of-the-art methods.