Soft Computing for Machine Learning and Bioinformatics

Hybridization using different soft computing tools has been explored for efficient data mining clust- ering and classification. An evolutionary-rough feature selection algorithm has been developed for feature selection and classi- fication of gene expre- ssion patterns. Next A detailed clustering algorithm is developed by integrating the advantage of both rough and fuzzy set theories. The remaining three chapters are devoted for biclustering problem. The whole work of this book is divided into the follow- ing: i) Mining important features from high dimen- sional gene datasets; ii) Biclustering or local stru- cture determination in gene expression data using soft tools; iii) Collaborative clustering for global structure determination in large data; iv) Covering various machine learning and bioinformatics applica- tions using soft computing; and v) A special chapter is written for designing a new paradigm for optimi- zation. The book focuses on some applications of the newly developed soft computing based methodologies for machine learning optimizationand bioinformatic Problems. The book covers how to design a hybrid system for real life problem solving.