Fuzzy inference-based LSTM for long-term time series prediction
Abstract Long short-term memory (LSTM) based time series forecasting methods suffer from multiple limitations, such as accumulated error, diminishing temporal correlation, and lacking interpretability, which compromises the prediction performance. To overcome these shortcomings, a fuzzy inference-ba...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-47812-3 |
| _version_ | 1797452784902078464 |
|---|---|
| author | Weina Wang Jiapeng Shao Huxidan Jumahong |
| author_facet | Weina Wang Jiapeng Shao Huxidan Jumahong |
| author_sort | Weina Wang |
| collection | DOAJ |
| description | Abstract Long short-term memory (LSTM) based time series forecasting methods suffer from multiple limitations, such as accumulated error, diminishing temporal correlation, and lacking interpretability, which compromises the prediction performance. To overcome these shortcomings, a fuzzy inference-based LSTM with the embedding of a fuzzy system is proposed to enhance the accuracy and interpretability of LSTM for long-term time series prediction. Firstly, a fast and complete fuzzy rule construction method based on Wang–Mendel (WM) is proposed, which can enhance the computational efficiency and completeness of the WM model by fuzzy rules simplification and complement strategies. Then, the fuzzy prediction model is constructed to capture the fuzzy logic in data. Finally, the fuzzy inference-based LSTM is proposed by integrating the fuzzy prediction fusion, the strengthening memory layer, and the parameter segmentation sharing strategy into the LSTM network. Fuzzy prediction fusion increases the network reasoning capability and interpretability, the strengthening memory layer strengthens the long-term memory and alleviates the gradient dispersion problem, and the parameter segmentation sharing strategy balances processing efficiency and architecture discrimination. Experiments on publicly available time series demonstrate that the proposed method can achieve better performance than existing models for long-term time series prediction. |
| first_indexed | 2024-03-09T15:13:42Z |
| format | Article |
| id | doaj.art-6f3564f1a2e14d7d8bafdd7d1b19da9e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:13:42Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6f3564f1a2e14d7d8bafdd7d1b19da9e2023-11-26T13:12:02ZengNature PortfolioScientific Reports2045-23222023-11-0113111810.1038/s41598-023-47812-3Fuzzy inference-based LSTM for long-term time series predictionWeina Wang0Jiapeng Shao1Huxidan Jumahong2College of Information and Control Engineering, Jilin Institute of Chemical TechnologyCollege of Information and Control Engineering, Jilin Institute of Chemical TechnologySchool of Network Security and Information technology, YiLi Normal UniversityAbstract Long short-term memory (LSTM) based time series forecasting methods suffer from multiple limitations, such as accumulated error, diminishing temporal correlation, and lacking interpretability, which compromises the prediction performance. To overcome these shortcomings, a fuzzy inference-based LSTM with the embedding of a fuzzy system is proposed to enhance the accuracy and interpretability of LSTM for long-term time series prediction. Firstly, a fast and complete fuzzy rule construction method based on Wang–Mendel (WM) is proposed, which can enhance the computational efficiency and completeness of the WM model by fuzzy rules simplification and complement strategies. Then, the fuzzy prediction model is constructed to capture the fuzzy logic in data. Finally, the fuzzy inference-based LSTM is proposed by integrating the fuzzy prediction fusion, the strengthening memory layer, and the parameter segmentation sharing strategy into the LSTM network. Fuzzy prediction fusion increases the network reasoning capability and interpretability, the strengthening memory layer strengthens the long-term memory and alleviates the gradient dispersion problem, and the parameter segmentation sharing strategy balances processing efficiency and architecture discrimination. Experiments on publicly available time series demonstrate that the proposed method can achieve better performance than existing models for long-term time series prediction.https://doi.org/10.1038/s41598-023-47812-3 |
| spellingShingle | Weina Wang Jiapeng Shao Huxidan Jumahong Fuzzy inference-based LSTM for long-term time series prediction Scientific Reports |
| title | Fuzzy inference-based LSTM for long-term time series prediction |
| title_full | Fuzzy inference-based LSTM for long-term time series prediction |
| title_fullStr | Fuzzy inference-based LSTM for long-term time series prediction |
| title_full_unstemmed | Fuzzy inference-based LSTM for long-term time series prediction |
| title_short | Fuzzy inference-based LSTM for long-term time series prediction |
| title_sort | fuzzy inference based lstm for long term time series prediction |
| url | https://doi.org/10.1038/s41598-023-47812-3 |
| work_keys_str_mv | AT weinawang fuzzyinferencebasedlstmforlongtermtimeseriesprediction AT jiapengshao fuzzyinferencebasedlstmforlongtermtimeseriesprediction AT huxidanjumahong fuzzyinferencebasedlstmforlongtermtimeseriesprediction |