Multiscale Temporal Dynamic Learning for Time Series Classification

Abstract

Time series classification (TSC) is crucial in many applications, yet accurately modeling complex time series patterns remains challenging. Model-based TSC strives to aptly model time series by capturing their intrinsic temporal dynamics, deriving effective dynamic representations for classification. Despite significant progress in this domain, existing works are still constrained by a singular and overly simplistic modeling paradigm, which proves inadequate to handle the multiscale hierarchies inherent in time series. Additionally, the prevailing reliance on manual model configuration fails to address the diverse dynamic characteristics across varying data scenarios. In this paper, we amalgamate multiple recurrent reservoirs to devise a model-based Multiscale Temporal Dynamic Learning (MsDL) approach. These reservoirs are endowed with varied recurrent connection skips, ensuring a comprehensive capture of temporal dynamics across different timescales. We also present a multi-objective optimization algorithm, which adaptively configures the memory length of each reservoir, allowing for more accurate time series modeling. This optimization further encourages time series from the same class to look closer, while separating those from different classes, thereby enhancing the category-discriminability. Extensive experiments on public datasets demonstrate that MsDL outperforms the state-of-the-art methods. Additionally, ablation studies confirm that our multiscale design and optimization algorithm effectively enhance classification accuracy.