Computational intelligence PC tools
Computational intelligence PC tools
Particle Swarm Optimization Learning Fuzzy Systems Design
ICITA '05 Proceedings of the Third International Conference on Information Technology and Applications (ICITA'05) Volume 2 - Volume 02
Choosing SNPs Using Feature Selection
CSB '05 Proceedings of the 2005 IEEE Computational Systems Bioinformatics Conference
Improved binary PSO for feature selection using gene expression data
Computational Biology and Chemistry
Linear reduction method for predictive and informative tag SNP selection
International Journal of Bioinformatics Research and Applications
Hi-index | 0.00 |
In the current researches of disease-gene association, Single Nucleotide Polymorphism (SNP) is the most interested topic. However, genotyping all existing SNPs for a large number of samples is still challenging even though SNP arrays have been developed to facilitate the task. Therefore, it is essential to select only informative SNPs (tag SNP) representing the rest SNPs for genome-wide association studies. Accordingly, the cost of genotyping is expected to be largely reduced. In this study, the fuzzy guided binary particle swarm optimization (FBPSO) based approach make it possible to select tag SNPs with higher accuracy. The fuzzy logic is employed to tuning the inertia weight (w) of BPSO. Three publicly data sets from the literature have been used for testing the performance of FBPSO. The experimental results indicated that the fuzzy logic will reinforce the search capability of BPSO, which is more accurate than the state-of-the-art methods. On the average of testing results, it also outperforms SVM/STSA method about 3.7%.