A novel prediction algorithm of thermostable proteins by using hurst exponent and choquet integral regression model

ASIA unversity > 資訊學院 > 生物資訊與醫學工程學系 > 會議論文 > Item 310904400/8799

Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/8799

Title:	A novel prediction algorithm of thermostable proteins by using hurst exponent and choquet integral regression model
Authors:	Liu, Hsiang-Chuan (1);Tu, Yu-Chieh (2);Jeng, Bai-Cheng (2);Liu, Tung-Sheng (3)
Contributors:	Department of Bioinformatics
Keywords:	Algorithms;Integral equations;Intelligent systems;Proteins;Systems analysis;Choquet integral;Classification algorithm;Cross validation;Fractal properties;Hurst exponents;Multiple regression model;Physicochemical property;Prediction algorithms;Prediction model;Regression model;Ridge regression
Date:	2008
Issue Date:	2010-04-08 12:06:13 (UTC+0)
Publisher:	Asia University
Abstract:	In search of good prediction algorithm of thermostable proteins is an important issue. In this paper, a novel prediction algorithm of thermostable proteins by using Hurst exponent and Choquet integral regression model based on ?measure and ?support is proposed. This method not used before is the first one integrating the physicochemical properties, fractal property and Choquet integral regression model. For evaluating the performance of this new algorithm, a real data experiment by using Leaveoneout CrossValidation accuracy is conducted. Experimental result shows that this new classification algorithm is useful and batter than those methods by using Hurst exponent and the traditional prediction models, multiple regression model and ridge regression model. © 2008 IEEE.
Relation:	Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008 :147-152
Appears in Collections:	[生物資訊與醫學工程學系 ] 會議論文

Files in This Item:

File	Description	Size	Format
		0Kb	Unknown	459	View/Open
249.doc		30Kb	Microsoft Word	319	View/Open

Loading...