|
JAIST Repository >
Center for Strategic Development of Science and Technology 2003-2008 >
JAIST PRESS Publications >
KSS'2007 >
Please use this identifier to cite or link to this item:
https://hdl.handle.net/10119/4145
|
| Title: | Currency Crisis Forecasting with a Multi-Resolution Neural Network Learning Approach |
| Authors: | Yu, Lean
Wang, Shouyang
Lai, Kin Keung
Cong, Guodong |
| Keywords: | Artificial neural networks
empirical mode decomposition
multi-resolution learning
currency crisis forecasting |
| Issue Date: | Nov-2007 |
| Publisher: | JAIST Press |
| Abstract: | In this study, an empirical mode decomposition (EMD) based multi-resolution neural network learning paradigm via Hilbert-Huang transform (HHT) is proposed to predict currency crisis for early-warning purpose. In the proposed learning paradigm, the original currency exchange rate series are first decomposed into various independent intrinsic mode components (IMCs) with a multi-resolution Hilbert-EMD algorithm. Then these IMCs with different scales are input into an artificial neural network (ANN) for training purpose. Using the trained ANN, the future currency crisis conditions can be predicted based on the historical data. For verification, two typical currencies — South Korean Won and Thai Baht — are used to test the effectiveness of the proposed multi-resolution neural learning paradigm. |
| Description: | The original publication is available at JAIST Press http://www.jaist.ac.jp/library/jaist-press/index.html
Proceedings of KSS'2007 : The Eighth International Symposium on Knowledge and Systems Sciences : November 5-7, 2007, [Ishikawa High-Tech Conference Center, Nomi, Ishikawa, JAPAN]
Organized by: Japan Advanced Institute of Science and Technology |
| Language: | ENG |
| URI: | https://hdl.handle.net/10119/4145 |
| ISBN: | 9784903092072 |
| Appears in Collections: | KSS'2007
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| 40.pdf | | 115Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
