Developing an Enhanced Fusion Model to Classify Biomedical data

Abstract: Classification is the technique where we discover the hidden class level of the unknown data. Multiple classifier fusion system needed to fuse the answers of several classifiers to enhance the accuracy. Here the proposed model will use each classifier for every individual data. In this paper, we have used principal component analysis to deal with issues of high dimensionality in biomedical classification. We have implemented three types of classification technique on micro array data after reduction. Eighty percent of data has been taken for the training and twenty percent for the testing. We have also implemented and compared three classification methods on the data like Multi Layer Perceptron, FLANN and PSO- FLANN and from the analysis; it has been observed that MLP has given better result. In this paper, we have also proposed a model for classifier fusion where the model will choose the relevant classifiers according to the different region of data set.

Keywords: Principal Component Analysis; Classification; Classifier fusion.