Presentation | 2004/11/29 Extended Study on Identification of Active Classes of Drugs by TFS-based Support Vector Machine with Large Data(Scientific Data Mining)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining) YOSHIMASA TAKAHASHI, SATOSHI FUJISHIMA, KATSUMI NISHIKOORI, HIROAKI KATO, TAKASHI OKADA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In the preceding work, the author's investigated classification and prediction of dopamine D1 receptor agonists and antagonists with noises by TFS-based SVM. In this work, the data set was extended up to seven active classes (dopamine D1, D2 and auto-receptor agonists, D1, D2, D3, and D4 antagonists). And the noise ratio was also increased to ten times of those active compounds. Total number of compounds used in the present work is 16008 compounds for the training, and that for the prediction is 1779 compounds. The TFS-based SVM still gave us good and stable results in both classification and prediction, even in the case included ten times noise data. The model obtained resulted that it correctly predicted 97.2% of the prediction set of 1779 compounds. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | AI2004-47 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2004/11/29(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Extended Study on Identification of Active Classes of Drugs by TFS-based Support Vector Machine with Large Data(Scientific Data Mining)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining) |
Sub Title (in English) | |
Keyword(1) | |
1st Author's Name | YOSHIMASA TAKAHASHI |
1st Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology() |
2nd Author's Name | SATOSHI FUJISHIMA |
2nd Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
3rd Author's Name | KATSUMI NISHIKOORI |
3rd Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
4th Author's Name | HIROAKI KATO |
4th Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
5th Author's Name | TAKASHI OKADA |
5th Author's Affiliation | Department of Informatics, School of Science and Technology, Kwansei Gakuin University |
Date | 2004/11/29 |
Paper # | AI2004-47 |
Volume (vol) | vol.104 |
Number (no) | 487 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |