The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 52-460
Full Name: Kun-Hong Liu
Position: Lecturer
Age: ON
Sex: Male
Address: Software School of Xiamen University, Xiamen, Fujian Province, China
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: lkhqz@sina.com
Other E-mails: lkhqz@xmu.edu.cn
Title of the Paper: A GA Based Approach to Improving the ICA Based Classification Models for Tumor Classification
Authors as they appear in the Paper: Xia-Hou Jianbing, Kun-Hong Liu
Email addresses of all the authors: jbxiahou@xmu.edu.cn; lkhqz@xmu.edu.cn
Number of paper pages: 11
Abstract: As it was pointed out that different ICs are of different biological significance, this paper tries to explore the IC selection problem based on a set of experiments. A regression model and a classification model, which are referred as penalized independent component regression (P-ICR) and ICA based Support Vector Machine (ICA+SVM), are applied to illustrate the necessity and efficiency of IC selection. A genetic algorithm (GA) is deployed to the selection process, along with an early stopping technique deployed to avoid overfitting in evolution. In particular, the individuals in the selected generation are used to combine an ensemble system, so as to achieve high classification accuracy. We test the two models with and without the selection methods based on three microarray data sets. The experiment results demonstrate that IC selection methods can further improve the classification accuracy of the ICA based prediction models, and the GA is more effective than the!
existing methods.
Keywords: Microarray data; Independent component analysis (ICA); Genetic algorithm (GA); Early stopping; Support Vector Machine(SVM); Overfitting;
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Pattern Recognition; Machine Learning; Bioinformatics
IP ADDRESS: 58.23.40.125
