Heterogeneous Feature Based Time Series Classification With Attention Mechanism
Time series classification (TSC) problem has been a significantly attractive research problem for decades. A large number of models with various types of features have been proposed. However, with the rapid development of new applications, like IoT and intelligent manufacturing, the time series data...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9815074/ |
| _version_ | 1811160930551070720 |
|---|---|
| author | Hanbo Zhang Peng Wang Shen Liang Tongming Zhou Wei Wang |
| author_facet | Hanbo Zhang Peng Wang Shen Liang Tongming Zhou Wei Wang |
| author_sort | Hanbo Zhang |
| collection | DOAJ |
| description | Time series classification (TSC) problem has been a significantly attractive research problem for decades. A large number of models with various types of features have been proposed. However, with the rapid development of new applications, like IoT and intelligent manufacturing, the time series data from different industries and applications are constantly emerging. To classify these data accurately, data scientists face the challenges of 1) how to select the optimal features and classification models and 2) how to interpret the results. To tackle these two challenges, in this paper, we propose a heterogeneous feature ensemble network, named FEnet. Multiple features, including time-domain, frequency-domain, and so on, are combined to build the model so that it can deal with the diversity of the data characteristics. Furthermore, to improve the interpretability, we propose a two-level attention mechanism. Finally, we propose two model optimization strategies to enhance classification accuracy and efficiency. Extensive experiments are conducted on real datasets and the results verify the accuracy, operation efficiency, and interpretability of FEnet. |
| first_indexed | 2024-04-10T06:06:05Z |
| format | Article |
| id | doaj.art-547acf510f8f4e30874e681c18de883b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:06:05Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-547acf510f8f4e30874e681c18de883b2023-03-03T00:00:23ZengIEEEIEEE Access2169-35362023-01-0111193731938410.1109/ACCESS.2022.31883939815074Heterogeneous Feature Based Time Series Classification With Attention MechanismHanbo Zhang0Peng Wang1https://orcid.org/0000-0002-8136-9621Shen Liang2Tongming Zhou3Wei Wang4https://orcid.org/0000-0003-0264-788XSchool of Computer Science, Fudan University, Yangpu, ChinaSchool of Computer Science, Fudan University, Yangpu, ChinaData Intelligence Institute of Paris (diiP), Université Paris Cité, Paris, FranceSchool of Computer Science, Fudan University, Yangpu, ChinaSchool of Computer Science, Fudan University, Yangpu, ChinaTime series classification (TSC) problem has been a significantly attractive research problem for decades. A large number of models with various types of features have been proposed. However, with the rapid development of new applications, like IoT and intelligent manufacturing, the time series data from different industries and applications are constantly emerging. To classify these data accurately, data scientists face the challenges of 1) how to select the optimal features and classification models and 2) how to interpret the results. To tackle these two challenges, in this paper, we propose a heterogeneous feature ensemble network, named FEnet. Multiple features, including time-domain, frequency-domain, and so on, are combined to build the model so that it can deal with the diversity of the data characteristics. Furthermore, to improve the interpretability, we propose a two-level attention mechanism. Finally, we propose two model optimization strategies to enhance classification accuracy and efficiency. Extensive experiments are conducted on real datasets and the results verify the accuracy, operation efficiency, and interpretability of FEnet.https://ieeexplore.ieee.org/document/9815074/Time series classificationfeature ensembleattention mechanism |
| spellingShingle | Hanbo Zhang Peng Wang Shen Liang Tongming Zhou Wei Wang Heterogeneous Feature Based Time Series Classification With Attention Mechanism IEEE Access Time series classification feature ensemble attention mechanism |
| title | Heterogeneous Feature Based Time Series Classification With Attention Mechanism |
| title_full | Heterogeneous Feature Based Time Series Classification With Attention Mechanism |
| title_fullStr | Heterogeneous Feature Based Time Series Classification With Attention Mechanism |
| title_full_unstemmed | Heterogeneous Feature Based Time Series Classification With Attention Mechanism |
| title_short | Heterogeneous Feature Based Time Series Classification With Attention Mechanism |
| title_sort | heterogeneous feature based time series classification with attention mechanism |
| topic | Time series classification feature ensemble attention mechanism |
| url | https://ieeexplore.ieee.org/document/9815074/ |
| work_keys_str_mv | AT hanbozhang heterogeneousfeaturebasedtimeseriesclassificationwithattentionmechanism AT pengwang heterogeneousfeaturebasedtimeseriesclassificationwithattentionmechanism AT shenliang heterogeneousfeaturebasedtimeseriesclassificationwithattentionmechanism AT tongmingzhou heterogeneousfeaturebasedtimeseriesclassificationwithattentionmechanism AT weiwang heterogeneousfeaturebasedtimeseriesclassificationwithattentionmechanism |