Supervised Machine Learning Approach for Microarray Classification of Malignant Tissues Using Soft Computing Techniques

In today's highly integrated world, when solutions to problems are cross disciplinary in nature, Soft computing promises to become a powerful means for obtaining solutions to problem quickly, accurately and acceptably. Soft computing refers to a consortium of computational methodologies that has motivated many scientific researchers to contribute their efforts in designing highly powerful intelligent systems. During the early 20th century, the advent of malignant tissues in the human cells came into knowledge of medical researchers. A herculean task of classifying the tumorous cells became a very challenging task in the gamut of information, especially in the field of intelligent systems. In this work, we have applied Artificial Bee Colony (ABC) optimization along with the supervised learning technique i.e. Support vector machine (SVM) to estimate the cost of classification. We have also simulated the cancerous dataset with the implementation of Cat Swarm Optimization (CSO) with SVM. Prior to classification, we have tried our level best to eliminate redundant and unwanted data with the help of Principal Component Analysis (PCA) technique. A great deal of work in predicting feasible as well as global best solutions have been put forward by many innovative and advanced heuristic search strategies.