A novel extreme adaptive GRU for multivariate time series forecasting
Abstract Multivariate time series forecasting is a critical problem in many real-world scenarios. Recent advances in deep learning have significantly enhanced the ability to tackle such problems. However, a primary challenge in time series forecasting comes from the imbalanced time series data that...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-53460-y |
| _version_ | 1827327885974700032 |
|---|---|
| author | Yifan Zhang Rui Wu Sergiu M. Dascalu Frederick C. Harris |
| author_facet | Yifan Zhang Rui Wu Sergiu M. Dascalu Frederick C. Harris |
| author_sort | Yifan Zhang |
| collection | DOAJ |
| description | Abstract Multivariate time series forecasting is a critical problem in many real-world scenarios. Recent advances in deep learning have significantly enhanced the ability to tackle such problems. However, a primary challenge in time series forecasting comes from the imbalanced time series data that include extreme events. Despite being a small fraction of the data instances, extreme events can have a negative impact on forecasting as they deviate from the majority. However, many recent time series forecasting methods neglect this issue, leading to suboptimal performance. To address these challenges, we introduce a novel model, the Extreme Event Adaptive Gated Recurrent Unit (eGRU), tailored explicitly for forecasting tasks. The eGRU is designed to effectively learn both normal and extreme event patterns within time series data. Furthermore, we introduce a time series data segmentation technique that divides the input sequence into segments, each comprising multiple time steps. This segmentation empowers the eGRU to capture data patterns at different time step resolutions while simultaneously reducing the overall input length. We conducted comprehensive experiments on four real-world benchmark datasets to evaluate the eGRU’s performance. Our results showcase its superiority over vanilla RNNs, LSTMs, GRUs, and other state-of-the-art RNN variants in multivariate time series forecasting. Additionally, we conducted ablation studies to demonstrate the consistently superior performance of eGRU in generating accurate forecasts while incorporating a diverse range of labeling results. |
| first_indexed | 2024-03-07T15:09:55Z |
| format | Article |
| id | doaj.art-31058f0dc6b54b98bee23e787988fe4e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:09:55Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-31058f0dc6b54b98bee23e787988fe4e2024-03-05T18:42:40ZengNature PortfolioScientific Reports2045-23222024-02-0114111010.1038/s41598-024-53460-yA novel extreme adaptive GRU for multivariate time series forecastingYifan Zhang0Rui Wu1Sergiu M. Dascalu2Frederick C. Harris3Department of Computer Science and Engineering, University of NevadaDepartment of Computer Science, East Carolina UniversityDepartment of Computer Science and Engineering, University of NevadaDepartment of Computer Science and Engineering, University of NevadaAbstract Multivariate time series forecasting is a critical problem in many real-world scenarios. Recent advances in deep learning have significantly enhanced the ability to tackle such problems. However, a primary challenge in time series forecasting comes from the imbalanced time series data that include extreme events. Despite being a small fraction of the data instances, extreme events can have a negative impact on forecasting as they deviate from the majority. However, many recent time series forecasting methods neglect this issue, leading to suboptimal performance. To address these challenges, we introduce a novel model, the Extreme Event Adaptive Gated Recurrent Unit (eGRU), tailored explicitly for forecasting tasks. The eGRU is designed to effectively learn both normal and extreme event patterns within time series data. Furthermore, we introduce a time series data segmentation technique that divides the input sequence into segments, each comprising multiple time steps. This segmentation empowers the eGRU to capture data patterns at different time step resolutions while simultaneously reducing the overall input length. We conducted comprehensive experiments on four real-world benchmark datasets to evaluate the eGRU’s performance. Our results showcase its superiority over vanilla RNNs, LSTMs, GRUs, and other state-of-the-art RNN variants in multivariate time series forecasting. Additionally, we conducted ablation studies to demonstrate the consistently superior performance of eGRU in generating accurate forecasts while incorporating a diverse range of labeling results.https://doi.org/10.1038/s41598-024-53460-y |
| spellingShingle | Yifan Zhang Rui Wu Sergiu M. Dascalu Frederick C. Harris A novel extreme adaptive GRU for multivariate time series forecasting Scientific Reports |
| title | A novel extreme adaptive GRU for multivariate time series forecasting |
| title_full | A novel extreme adaptive GRU for multivariate time series forecasting |
| title_fullStr | A novel extreme adaptive GRU for multivariate time series forecasting |
| title_full_unstemmed | A novel extreme adaptive GRU for multivariate time series forecasting |
| title_short | A novel extreme adaptive GRU for multivariate time series forecasting |
| title_sort | novel extreme adaptive gru for multivariate time series forecasting |
| url | https://doi.org/10.1038/s41598-024-53460-y |
| work_keys_str_mv | AT yifanzhang anovelextremeadaptivegruformultivariatetimeseriesforecasting AT ruiwu anovelextremeadaptivegruformultivariatetimeseriesforecasting AT sergiumdascalu anovelextremeadaptivegruformultivariatetimeseriesforecasting AT frederickcharris anovelextremeadaptivegruformultivariatetimeseriesforecasting AT yifanzhang novelextremeadaptivegruformultivariatetimeseriesforecasting AT ruiwu novelextremeadaptivegruformultivariatetimeseriesforecasting AT sergiumdascalu novelextremeadaptivegruformultivariatetimeseriesforecasting AT frederickcharris novelextremeadaptivegruformultivariatetimeseriesforecasting |