A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer
Time series prediction is crucial for advanced control and management of complex systems, while the actual data are usually highly nonlinear and nonstationary. A novel broad echo state network is proposed herein for the prediction problem of complex time series data. Firstly, the framework of the br...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/13/6396 |
| _version_ | 1827655541000765440 |
|---|---|
| author | Wen-Jie Liu Yu-Ting Bai Xue-Bo Jin Jian-Lei Kong Ting-Li Su |
| author_facet | Wen-Jie Liu Yu-Ting Bai Xue-Bo Jin Jian-Lei Kong Ting-Li Su |
| author_sort | Wen-Jie Liu |
| collection | DOAJ |
| description | Time series prediction is crucial for advanced control and management of complex systems, while the actual data are usually highly nonlinear and nonstationary. A novel broad echo state network is proposed herein for the prediction problem of complex time series data. Firstly, the framework of the broad echo state network with cascade of mapping nodes (CMBESN) is designed by embedding the echo state network units into the broad learning system. Secondly, the number of enhancement layer nodes of the CMBESN is determined by proposing an incremental algorithm. It can obtain the optimal network structure parameters. Meanwhile, an optimization method is proposed based on the nonstationary statistic metrics to determine the enhancement layer. Finally, experiments are conducted both on the simulated and actual datasets. The results show that the proposed CMBESN and its optimization have good prediction capability for nonstationary time series data. |
| first_indexed | 2024-03-09T22:08:10Z |
| format | Article |
| id | doaj.art-216d9c46b075482b9f35440d982cd66c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:08:10Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-216d9c46b075482b9f35440d982cd66c2023-11-23T19:35:53ZengMDPI AGApplied Sciences2076-34172022-06-011213639610.3390/app12136396A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement LayerWen-Jie Liu0Yu-Ting Bai1Xue-Bo Jin2Jian-Lei Kong3Ting-Li Su4School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaTime series prediction is crucial for advanced control and management of complex systems, while the actual data are usually highly nonlinear and nonstationary. A novel broad echo state network is proposed herein for the prediction problem of complex time series data. Firstly, the framework of the broad echo state network with cascade of mapping nodes (CMBESN) is designed by embedding the echo state network units into the broad learning system. Secondly, the number of enhancement layer nodes of the CMBESN is determined by proposing an incremental algorithm. It can obtain the optimal network structure parameters. Meanwhile, an optimization method is proposed based on the nonstationary statistic metrics to determine the enhancement layer. Finally, experiments are conducted both on the simulated and actual datasets. The results show that the proposed CMBESN and its optimization have good prediction capability for nonstationary time series data.https://www.mdpi.com/2076-3417/12/13/6396time series predictionecho state networksbroad learning systemnonstationary analysis |
| spellingShingle | Wen-Jie Liu Yu-Ting Bai Xue-Bo Jin Jian-Lei Kong Ting-Li Su A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer Applied Sciences time series prediction echo state networks broad learning system nonstationary analysis |
| title | A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer |
| title_full | A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer |
| title_fullStr | A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer |
| title_full_unstemmed | A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer |
| title_short | A Novel Broad Echo State Network for Time Series Prediction: Cascade of Mapping Nodes and Optimization of Enhancement Layer |
| title_sort | novel broad echo state network for time series prediction cascade of mapping nodes and optimization of enhancement layer |
| topic | time series prediction echo state networks broad learning system nonstationary analysis |
| url | https://www.mdpi.com/2076-3417/12/13/6396 |
| work_keys_str_mv | AT wenjieliu anovelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT yutingbai anovelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT xuebojin anovelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT jianleikong anovelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT tinglisu anovelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT wenjieliu novelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT yutingbai novelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT xuebojin novelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT jianleikong novelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer AT tinglisu novelbroadechostatenetworkfortimeseriespredictioncascadeofmappingnodesandoptimizationofenhancementlayer |