| Presentation | 2023-03-02 Separate Predictive Time Series Reconstruction using Independent Low-Rank Matrix Analysis Hibiki Izumi, Jun Rokui, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Time series forecasting is the field to predict future values from past values, and various methods have been proposed. There is a signal processing technology called sound source separation in the field of speech signal processing, and it is a technology to estimate sound sourcesignals before mixing from observation signals in which multiple sound sources are mixed. In this study, we assume that independent signal components are included in the time series data and simplify the signal by applying independent low-rank matrix analysis(ILRMA: Independent Low-Rank Matrix Analysis), one of the source separation methods, to the time series(stock price) data. It can be expected that the time series data prediction becomes more accurate by the signal simplification. In this paper, we propose a method to obtain the predicted results by using LSTM(Long-Short Term Memory) for individual signals, and then recovering the original data using multiple regressions. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Time series prediction / ILRMA / LSTM |
| Paper # | PRMU2022-95,IBISML2022-102 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2023/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Future University Hakodate |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Seiichi Uchida(Kyushu Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
| Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) |
| Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Separate Predictive Time Series Reconstruction using Independent Low-Rank Matrix Analysis |
| Sub Title (in English) | |
| Keyword(1) | Time series prediction |
| Keyword(2) | ILRMA |
| Keyword(3) | LSTM |
| 1st Author's Name | Hibiki Izumi |
| 1st Author's Affiliation | University of Shizuoka(Univ of Shizuoka) |
| 2nd Author's Name | Jun Rokui |
| 2nd Author's Affiliation | University of Shizuoka(Univ of Shizuoka) |
| Date | 2023-03-02 |
| Paper # | PRMU2022-95,IBISML2022-102 |
| Volume (vol) | vol.122 |
| Number (no) | PRMU-404,IBISML-405 |
| Page | pp.pp.187-192(PRMU), pp.187-192(IBISML), |
| #Pages | 6 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |