| Presentation | 2019-07-30 Modeling and Prediction of Time Time-Series Shiao Yi Chen, Goutam Chakraborty, Chen Shin Fu, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Time series data reveals dynamic behavior of systems in real life, such as traffic flow, amount of rainfall, usage of electricity, share values, Forex rate etc.. Depending on the complexity of the system dynamics, algorithms differ to model the time series data accurately, so that the model can be used for interpolation and more commonly extrapolation or prediction. For example, AR model performs well in stationary time seri es, but for non stationary, it cannot capture the pattern well. In this research, we use Forex rate data, and tried various algorithms to capture the dynamics of the data. The success of the model is evaluated by accuracy in prediction. In our experiments, we applied two state of the art models Support Vector Regression (SVR) and Recurrent Neural Network (RNN). The experiment is the prediction of longer future by recursion (feeding back predicted value to input for the next step prediction). The result shows that RNN with proper Long Short Term Memory (LSTM) has better performance in predicting longer future. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Time series / Forex / SVR / RNN / LSTM |
| Paper # | CAS2019-2,VLD2019-8,SIP2019-18,MSS2019-2 |
| Date of Issue | 2019-07-23 (CAS, VLD, SIP, MSS) |
| Conference Information | |
| Committee | MSS / CAS / SIP / VLD |
|---|---|
| Conference Date | 2019/7/30(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Iwate Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shigemasa Takai(Osaka Univ.) / Taizo Yamawaki(Hitachi) / Naoyuki Aikawa(TUS) / Nozomu Togawa(Waseda Univ.) |
| Vice Chair | Atsuo Ozaki(Osaka Inst. of Tech.) / Yasuhiro Takashima(Univ. of Kitakyushu) / Kazunori Hayashi(Osaka City Univ) / Yukihiro Bandou(NTT) / Daisuke Fukuda(Fujitsu Labs.) |
| Secretary | Atsuo Ozaki(Osaka Univ.) / Yasuhiro Takashima(Hokkaido Univ.) / Kazunori Hayashi(Hitachi) / Yukihiro Bandou(Yamanashi Univ.) / Daisuke Fukuda(Hiroshima Univ.) |
| Assistant | Naoki Hayashi(Osaka Univ.) / Hiroki Sato(Sony LSI Design) / Motoi Yamaguchi(Renesas Electronics) / / Kazuki Ikeda(Hitachi) |
| Paper Information | |
| Registration To | Technical Committee on Mathematical Systems Science and its applications / Technical Committee on Circuits and Systems / Technical Committee on Signal Processing / Technical Committee on VLSI Design Technologies |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Modeling and Prediction of Time Time-Series |
| Sub Title (in English) | A Case Study with Forex Data |
| Keyword(1) | Time series |
| Keyword(2) | Forex |
| Keyword(3) | SVR |
| Keyword(4) | RNN |
| Keyword(5) | LSTM |
| 1st Author's Name | Shiao Yi Chen |
| 1st Author's Affiliation | Iwate Prefectural University(IPU) |
| 2nd Author's Name | Goutam Chakraborty |
| 2nd Author's Affiliation | Iwate Prefectural University(IPU) |
| 3rd Author's Name | Chen Shin Fu |
| 3rd Author's Affiliation | Iwate Prefectural University(IPU) |
| Date | 2019-07-30 |
| Paper # | CAS2019-2,VLD2019-8,SIP2019-18,MSS2019-2 |
| Volume (vol) | vol.119 |
| Number (no) | CAS-153,VLD-154,SIP-155,MSS-156 |
| Page | pp.pp.7-10(CAS), pp.7-10(VLD), pp.7-10(SIP), pp.7-10(MSS), |
| #Pages | 4 |
| Date of Issue | 2019-07-23 (CAS, VLD, SIP, MSS) |