A Classifier Fusion Approach for Microarray Data Set

AbstractAnalysis of micro array data (MAD) plays a vital role for diagnosis and treatment for diseases. Classification is the process where we have to find out the unknown pattern of the new data. For a long time, efforts are made in improving efficiency, accuracy and reliability of classifiers for a wide range of applications. Number of classification method are fused together to enhance the performance. In this paper, a model has been proposed for classifier fusion which selects the classifier according to the accuracy with respect to different class level. The proposed model has been used with three different classification techniques like Multi Layer Perceptron (MLP), Bayesian classification and Support Vector Machine (SVM) on three different MAD. Simulation result shows that the proposed classifier fusion technique is superior and faster than the static selection method