A Multi-view Feature Construction and Multi-Encoder-Decoder Transformer Architecture for Time Series Classification

Time series data plays a significant role in many research fields since it can record and disclose the dynamic trends of a phenomenon with a sequence of ordered data points. Time series data is dynamic, of variable length, and often contains complex patterns, which makes its analysis challenging especially when the amount of data is limited. In this paper, we propose a multi-view feature construction approach that can generate multiple feature sets of different resolutions from a single dataset and produce a fixed-length representation of variable-length time series data. Furthermore, we propose a multi-encoder-decoder Transformer (MEDT) architecture to effectively analyze these multi-view representations. Through extensive experiments using multiple benchmarks and a real-world dataset, our method shows significant improvement over the state-of-the-art methods.