XEM: An explainable-by-design ensemble method for multivariate time series classification

We present XEM, an eXplainable-by-design Ensemble method for Multivariate time series classification. XEM relies on a new hybrid ensemble that combines explicit boosting-bagging approach to handle the bias-variance trade-off faced by machine learning models and implicit divide-and-conquer individualize classifier errors different parts of training data. Our evaluation shows outperforms state-of-the-art MTS classifiers public UEA datasets. Furthermore, provides faithful explainability-by-design manifests robust performance when with challenges arising from continuous data collection (different length, missing noise).