A GP Based Approach to the Classification of Multiclass Microarray Datasets

Authors:
Chun-Gui Xu;Kun-Hong Liu
Affiliations:
Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China 230031 and Department of Biology, University of Science and Technology of China, Hefei, China 230026;Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China 230031
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Artificial Intelligence
Year:
2008

Citing 8
Cited 0

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Multiclass cancer classification and biomarker discovery using GA-based algorithms

Bioinformatics
Pattern classification in DNA microarray data of multiple tumor types

Pattern Recognition
The classification of cancer based on DNA microarray data that uses diverse ensemble genetic programming

Artificial Intelligence in Medicine
Dynamic maximum tree depth: a simple technique for avoiding bloat in tree-based GP

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII
Application of genetic programming for multicategory patternclassification

IEEE Transactions on Evolutionary Computation
A novel approach to design classifiers using genetic programming

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a genetic programming (GP) based approach to analyze multiclass microarray datasets. Here, a multiclass problem is divided into a set of two-class problems. Instead of applying a tree for each two-class problem, a small-scale ensemble system containing a set of trees is deployed and denoted by sub-ensemble (SE). The SEs tackling the respective two-class problems are combined to construct an individual of the GP, so that an individual can deal with a multiclass problem directly. In the experiments, the GP implements classification and feature selection at the same time. The results obtained at independent test sets show that our method is efficient in the search of genes with great biological significance, and achieves high classification accuracy at the same time.