{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/disjoint-cnn-for-multivariate-time-series","title":"Disjoint-CNN for Multivariate Time Series Classification","arxiv_id":null,"date":"2022-01-20","proceeding":"2021 International Conference on Data Mining Workshops (ICDMW) 2022 1","authors":["Navid Mohammadi Foumani","Chang Wei Tan","Mahsa Salehi"],"abstract":"Time series classification algorithms have been mainly dominated by non-deep learning models.\r\nDeep learning for Multivariate Time Series Classification (MTSC) has gained huge interest in recent years. \r\nMost state-of-the-art deep learning methods are convolutional-based where 1-dimensional (1D) convolutions are used to extract features from the 2-dimensional time series. This study shows that factorization of 1D convolution filters into disjoint temporal and spatial components yields significant accuracy improvements with almost no additional computational cost.\r\nBased on our study on disjoint temporal-spatial filters, we have designed a novel filter block called ``1+1D\", which emphasizes the interaction between dimensions to improve the model performance of the convolution-based on deep learning MTSC models. We also proposed a new and effective MTSC method called Disjoint-CNN using our proposed 1+1D filter blocks and through our extensive experiments show that our model (called Disjoint-CNN) outperforms the state-of-the-art MTSC models on 26 datasets in the UEA Multivariate time series archive, achieving the highest average rank among 9 MTSC benchmark models.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9679860","url_pdf":"https://ieeexplore.ieee.org/abstract/document/9679860","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"disjoint-cnn-for-multivariate-time-series","repo_url":"https://github.com/Navidfoumani/Disjoint-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/time-series-classification-on-facedetection-1","task":"Time Series Classification","dataset":"FaceDetection","model":"Disjoint-CNN","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"0.5667"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-heartbeat","task":"Time Series Classification","dataset":"Heartbeat","model":"Disjoint-CNN","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"0.7594"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-pendigits-1","task":"Time Series Classification","dataset":"pendigits","model":"Disjoint-CNN","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"0.9947"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}