Presentation | 2011/6/16 Development of rule emsumble method for survival data TOSIO SHIMOKAWA, MITSUHIRO TSUJI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | One of the important themes in survival analysis is to explore prognoses factors that influence survival time. Recently, the tree-structured method has been applied to evaluate covariates; however, it is well known that this method has provides poor prediction model. This problem could be improved by modeling many trees in a linear combination, namely, ensemble learning. The ensemble learning method is actively studied in machine learning and statistics. In this presentation, we extended the rule ensumble method to analyze survival data, namely survival rule fit method (SRF method). SRF model is constructed by Cox proportional hazard model, and weight (regression) parameters for each rule (base learner) are estimated by lasso. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | Vol.2011-BIO-25 No.8 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2011/6/16(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 | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Development of rule emsumble method for survival data |
Sub Title (in English) | |
Keyword(1) | |
1st Author's Name | TOSIO SHIMOKAWA |
1st Author's Affiliation | Graduate School of Medicine and Engineering, University of Yamanashi() |
2nd Author's Name | MITSUHIRO TSUJI |
2nd Author's Affiliation | Faculty of Informatics, Kansai University |
Date | 2011/6/16 |
Paper # | Vol.2011-BIO-25 No.8 |
Volume (vol) | vol.111 |
Number (no) | 96 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |