We present XEM, an eXplainable-by-design Ensemble method for Multivariate time series classification. XEM relies on a new hybrid ensemble method that combines an explicit boosting-bagging approach to handle the bias-variance trade-off faced by machine learning models and an implicit divide-and-conquer approach to individualize classifier errors on different parts of the training data. Our evaluation shows that XEM outperforms the state-of-the-art MTS classifiers on the public UEA datasets. Furthermore, XEM provides faithful explainability-by-design and manifests robust performance when faced with challenges arising from continuous data collection (different MTS length, missing data and noise).
@article{arxiv.2005.03645,
title = {XEM: An Explainable-by-Design Ensemble Method for Multivariate Time Series Classification},
author = {Kevin Fauvel and Élisa Fromont and Véronique Masson and Philippe Faverdin and Alexandre Termier},
journal= {arXiv preprint arXiv:2005.03645},
year = {2022}
}
Comments
Accepted for publication in Data Mining and Knowledge Discovery