A Novel Modelling Technique for Early Recognition and Classification of Alzheimer’s disease

Abstract

A new algorithm is proposed in this paper using combined point detection based feature extraction methods like SURF, FAST, BRISK, Harris and Min Eigen for early prediction of various stages of Alzheimer's disease An analysis of the proposed method is done by combining it with Random Forest and Tree Bagger classifiers and the performance parameters are evaluated. From the experimental results, the classification accuracy obtained when random forest classifier is used is 98.42% and the classification accuracy obtained when Tree Bagger classifier is used is 98.17%. The random forest classifier provides more accuracy rate with high sensitivity and specificity when compared to Tree Bagger classifier. The new method is flexible to both classification and regression problems. Also it works well with both categorical and continuous values. From the experimental results, the proposed algorithm is found to be superior to the methods which uses single feature extraction and feature selection methods which are developed for the prediction and classification of Alzheimer’s disease.