Multidimensional time series classification with multiple attention mechanism
Abstract The classification of multidimensional time series holds significant importance across various domains, including action classification, medical diagnosis, and credit assessment. Within multidimensional time series data, features pertinent to classification exhibit variance in their positio...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01630-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571196306096128 |
|---|---|
| author | Chen Liu Zihan Wei Lixin Zhou Ying Shao |
| author_facet | Chen Liu Zihan Wei Lixin Zhou Ying Shao |
| author_sort | Chen Liu |
| collection | DOAJ |
| description | Abstract The classification of multidimensional time series holds significant importance across various domains, including action classification, medical diagnosis, and credit assessment. Within multidimensional time series data, features pertinent to classification exhibit variance in their positional distribution along the entirety of the sequence. Moreover, the relative significance of features across distinct dimensions also fluctuates, contributing to suboptimal performance in multidimensional time series classification. Consequently, the proposition of tailored deep learning models for feature extraction specific to multidimensional time series data becomes imperative. This paper introduces attention mechanisms applied to the temporal dimension, graph attention mechanisms for inter-dimensional relationships within multidimensional data, and attention mechanisms applied between channels post-convolutional calculations. These mechanisms are deployed for feature extraction across temporal, variational, and channel dimensions of multidimensional time series data, respectively. Furthermore, attention is directed towards inter-channel interactions within the squeeze-and-excitation network to enhance the model’s representational capacity. Experimental findings substantiate the viability of integrating attention mechanisms into multidimensional time series classification endeavors. |
| format | Article |
| id | doaj-art-c54b7b5325fe474cb11f4ad671ec2a44 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-c54b7b5325fe474cb11f4ad671ec2a442025-02-02T12:50:06ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111510.1007/s40747-024-01630-wMultidimensional time series classification with multiple attention mechanismChen Liu0Zihan Wei1Lixin Zhou2Ying Shao3Business School, University of Shanghai for Science and TechnologyBusiness School, University of Shanghai for Science and TechnologyBusiness School, University of Shanghai for Science and TechnologyBusiness School, University of Shanghai for Science and TechnologyAbstract The classification of multidimensional time series holds significant importance across various domains, including action classification, medical diagnosis, and credit assessment. Within multidimensional time series data, features pertinent to classification exhibit variance in their positional distribution along the entirety of the sequence. Moreover, the relative significance of features across distinct dimensions also fluctuates, contributing to suboptimal performance in multidimensional time series classification. Consequently, the proposition of tailored deep learning models for feature extraction specific to multidimensional time series data becomes imperative. This paper introduces attention mechanisms applied to the temporal dimension, graph attention mechanisms for inter-dimensional relationships within multidimensional data, and attention mechanisms applied between channels post-convolutional calculations. These mechanisms are deployed for feature extraction across temporal, variational, and channel dimensions of multidimensional time series data, respectively. Furthermore, attention is directed towards inter-channel interactions within the squeeze-and-excitation network to enhance the model’s representational capacity. Experimental findings substantiate the viability of integrating attention mechanisms into multidimensional time series classification endeavors.https://doi.org/10.1007/s40747-024-01630-wMultidimensional time seriesTime series classificationMultiple attentionDeep learning |
| spellingShingle | Chen Liu Zihan Wei Lixin Zhou Ying Shao Multidimensional time series classification with multiple attention mechanism Complex & Intelligent Systems Multidimensional time series Time series classification Multiple attention Deep learning |
| title | Multidimensional time series classification with multiple attention mechanism |
| title_full | Multidimensional time series classification with multiple attention mechanism |
| title_fullStr | Multidimensional time series classification with multiple attention mechanism |
| title_full_unstemmed | Multidimensional time series classification with multiple attention mechanism |
| title_short | Multidimensional time series classification with multiple attention mechanism |
| title_sort | multidimensional time series classification with multiple attention mechanism |
| topic | Multidimensional time series Time series classification Multiple attention Deep learning |
| url | https://doi.org/10.1007/s40747-024-01630-w |
| work_keys_str_mv | AT chenliu multidimensionaltimeseriesclassificationwithmultipleattentionmechanism AT zihanwei multidimensionaltimeseriesclassificationwithmultipleattentionmechanism AT lixinzhou multidimensionaltimeseriesclassificationwithmultipleattentionmechanism AT yingshao multidimensionaltimeseriesclassificationwithmultipleattentionmechanism |