Abstract
The main intension of the research is to classify the medical data with high accuracy value.In order to achieve promising results, we have designed to utilize orthogonal local preserving projection and optimal classifier.Initially, pre-processing will be applied to extract useful data and to convert suitable sample from raw medical datasets.In the proposed method, input dataset will be high dimensional or high features; so the high number of feature is a great obstruction for prediction.Therefore, feature dimension reduction method is used in our proposed technique.Here, orthogonal local preserving projection will be used to reduce the feature dimension.Once the feature reduction is formed, the prediction will be done by optimal classifier.Here modified group search optimizer algorithm combined with Fuzzy Min-Max neural network.The implementation will be done in MATLAB.The performance of the proposed technique is evaluated using accuracy, sensitivity and specificity.