Special session on feature selection and extraction in bioinformatics of OSB2007

Special Session on Feature Selection & Exaction in Bioinformatics 数据挖掘研究院

http://cs.shu.edu.cn/gzli/pub/osb07.htm

Organizer:

数据挖掘研究院

E-mail: gzli@shu.edu.cn  

数据挖掘研究院

Homepage: http://cs.shu.edu.cn/gzli 数据挖掘实验室

Meng Wang, Ph.D.
Research Associate, Dana-Farber cancer Institute, D709,  Harvard Medical School
Harvard University, 44, Binney, Street Boston, MA02115, USA
Fax: 617-632-5417 数据挖掘研究院

E-mail: Meng_Wang2@dfci.harvard.edu

数据挖掘研究院

Feature Selection and extraction are special optimization techniques, which will help to remove noisy features and reduce the dimensionality of biological data sets, they have been studied widely especially in micro-array analysis because the high dimensionality of micro-array data sets hurts generalization ability of machine learning methods. Research in mathematics, statistics, computer science, engineering and bioinformatics confront similar issues in feature selection and extraction, and we see a pressing need for and benefits in the interdisciplinary exchange and discussion of ideas. We anticipate that our collaborations will shed light on research directions and provide the stimulus for creative breakthroughs. 数据挖掘研究院

This special session will bring together researchers from different disciplines and encourage collaborative research in feature selection and extraction. Dimensionality reduction including feature selection and extraction is an essential step in successful bioinformatics applications; it has practical significance in many areas such as bioinformatics, statistics, pattern recognition, machine learning, and data mining. The objectives of feature selection and extraction include: building simpler and more comprehensible models, improving biomedical data mining performance, and helping to prepare, clean, and understand data.

数据挖掘研究院

Original research papers are solicited in the theory behind feature selection and extraction as well as novel applications in bioinformatics, additional session topics include the following, including but not limited to the following topics.

·         Dimensionality reduction

数据挖掘研究院

·         Feature ranking

·         Subset selection 数据挖掘研究院

·         Feature extraction 数据挖掘研究院

·         Feature construction 数据挖掘研究院

·         Selection for labeled and unlabeled data 数据挖掘研究院

·         Modeling variable and feature selection

·         Goodness measures and evaluation 数据挖掘实验室

·         Selection bias 数据挖掘研究院

·         Selection with small samples 数据挖掘研究院

·         Cross-discipline comparative studies 数据挖掘研究院

·         Integration with data mining algorithms

数据挖掘研究院

数据挖掘研究院

Manuscripts should be submitted via the submission system of OSB07, which will be blindly reviewed by at least two reviewers, accepted papers will be published in Lecture Notes in Operations Research (LNOR) by Springer on the conference, and selected papers will be invited to publish in a special issue on feature selection and extraction of Journal of Computational Intelligence in bioinformatics after this conference.

数据挖掘研究院

Important Dates 数据挖掘实验室

·         Paper submission deadline            April 15, 2007

数据挖掘研究院

·         Acceptance notification                 May 31, 2007

数据挖掘研究院

·         Early registration deadline            June 15, 2007 数据挖掘研究院

·         Final paper submission deadline   June 15, 2007

·         Symposium                                    August 7-9, 2007 数据挖掘研究院