Disjoint-CNN for Multivariate Time Series Classification

Seyed Navid Mohammadi Foumani, Chang Wei Tan, Mahsa Salehi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

Time series classification algorithms have been mainly dominated by non-deep learning models. Deep learning for Multivariate Time Series Classification (MTSC) has gained huge interest in recent years. Most 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. Based 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.

Original languageEnglish
Title of host publicationProceedings - 21st IEEE International Conference on Data Mining Workshops, ICDMW 2021
EditorsBing Xue, Mykola Pechenizkiy, Yun Sing Koh
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages760-769
Number of pages10
ISBN (Electronic)9781665424271
ISBN (Print)9781665424288
DOIs
Publication statusPublished - 2021
EventInternational Workshop on Spatial and Spatiotemporal Data Mining 2021 - Online, Auckland, New Zealand
Duration: 7 Dec 20217 Dec 2021
Conference number: 16th
https://ieeexplore.ieee.org/xpl/conhome/9679833/proceeding (Proceedings)

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
PublisherIEEE, Institute of Electrical and Electronics Engineers
Volume2021-December
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

ConferenceInternational Workshop on Spatial and Spatiotemporal Data Mining 2021
Abbreviated titleSSTDM 2021
Country/TerritoryNew Zealand
CityAuckland
Period7/12/217/12/21
Internet address

Keywords

  • convolutional neural networks
  • multivariate time series classification
  • temporal-spatial filters

Cite this