Publications-Proceedings
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
| Title | Forecasting exchange rate using EMD and BPNN optimized by particle swarm optimization |
| Creator | Yang, Heng-Li ;Lin, Han Chou;Huang, Stevenson 楊亨利 |
| Contributor | 資管系 |
| Key Words | Back-propagation neural networks; Empirical mode decomposition; Exchange rate forecasting; Exchange rates; Hilbert Huang transforms; Hybrid model; Intrinsic mode functions; Mean absolute percentage error; Random Walk; Backpropagation; Data mining; Forecasting; Functions; Information technology; Neural networks; Signal processing; Torsional stress; Particle swarm optimization (PSO) |
| Date | 2011 |
| Date Issued | 8-Oct-2015 17:40:47 (UTC+8) |
| Summary | This study applied back-propagation neural network (BPNN) and empirical mode decomposition (EMD) techniques and optimized the hybrid model by particle swarm optimization (PSO) to forecast exchange rate. The aim of this study is to examine the feasibility of the proposed EMD-BPNN-PSO model in exchange rate forecasting. In the first stage, the original exchange rate series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). In the second stage, kernel predictors such as BPNN are constructed for forecasting. Compared with traditional model (random walk), the proposed model performs best. The mean absolute percentage errors are significantly reduced. © 2011 AICIT. |
| Relation | Proceedings - 3rd International Conference on Data Mining and Intelligent Information Technology Applications, ICMIA 2011 |
| Type | conference |
| dc.contributor | 資管系 | - |
| dc.creator (作者) | Yang, Heng-Li ;Lin, Han Chou;Huang, Stevenson | - |
| dc.creator (作者) | 楊亨利 | - |
| dc.date (日期) | 2011 | - |
| dc.date.accessioned | 8-Oct-2015 17:40:47 (UTC+8) | - |
| dc.date.available | 8-Oct-2015 17:40:47 (UTC+8) | - |
| dc.date.issued (上傳時間) | 8-Oct-2015 17:40:47 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/78898 | - |
| dc.description.abstract (摘要) | This study applied back-propagation neural network (BPNN) and empirical mode decomposition (EMD) techniques and optimized the hybrid model by particle swarm optimization (PSO) to forecast exchange rate. The aim of this study is to examine the feasibility of the proposed EMD-BPNN-PSO model in exchange rate forecasting. In the first stage, the original exchange rate series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). In the second stage, kernel predictors such as BPNN are constructed for forecasting. Compared with traditional model (random walk), the proposed model performs best. The mean absolute percentage errors are significantly reduced. © 2011 AICIT. | - |
| dc.format.extent | 176 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | Proceedings - 3rd International Conference on Data Mining and Intelligent Information Technology Applications, ICMIA 2011 | - |
| dc.subject (關鍵詞) | Back-propagation neural networks; Empirical mode decomposition; Exchange rate forecasting; Exchange rates; Hilbert Huang transforms; Hybrid model; Intrinsic mode functions; Mean absolute percentage error; Random Walk; Backpropagation; Data mining; Forecasting; Functions; Information technology; Neural networks; Signal processing; Torsional stress; Particle swarm optimization (PSO) | - |
| dc.title (題名) | Forecasting exchange rate using EMD and BPNN optimized by particle swarm optimization | - |
| dc.type (資料類型) | conference | en |