ABSTRACT
The characteristic features of magnetic resonant image (MRI) for Alzheimer patients’ brain image and normal image can be distinguished in terms of dimensional features with the help of wavelet decomposition. From literature review, it is observed that, when the data sets used are a combination of the MR images having very mild cognitive impairment and midcognitive impairment, the performance of the classifier reduces. This is because the features of these kind of MR images are difficult to distinguish from normal brain images. To solve this problem, the lossless feature extraction method along with the feature reduction method having a selection approach is suggested as a solution here. In this chapter, the two-dimensional discrete time continuous wavelet transforms and a genetic algorithm (GA) is used for feature selection and feature vector size reduction. The fuzzy neural network (FNN), which is suitable for the pattern recognition, is used here. The FNN with and without feature reduction is evaluated for identification of the combinational data set and shows satisfactory performance over artificial neural network (ANN), probabilistic neural network (PNN) classifiers, and feature reduction techniques.
