الفهرس | Only 14 pages are availabe for public view |
Abstract The most prevalent form of dementia; memory loss, is Alzheimer’s disease. The Early detection of this disease is crucial in order to reduce its negative effects on the human memory. In this research, A data set consisted of 120 samples categorized into three groups; Alzheimer’s disease (AD), mild cognitive impairment (MCI), and cognitively normal (NC). 3D MRI images that are selected from all 3D volume were firstly normalized and preprocessed to extract twelve features. Two algorithms were exploited in classification phase to differentiate between the three categories. The utilized algorithms were support vector machine (SVM) with polynomial kernel and K-nearest neighbor (KNN) with different values of K. For each classifier, the more pronounced features were selected to give the highest average accuracy. in view of every conceivable permutations and combination between all used features. The classification result demonstrates a moderately high grouping accuracy between the three clinical classifications groups. The classification strategies can be utilized as a noninvasive analytic mechanism for Alzheimer’s disease, with the highest ability for characterizing early phases of the disease. The best average accuracy was 97.92% using SVM polynomial orde three, and best all average accuracy was 95.833% using KNN with K=6, and K=7 for random selection of testing data with SVM and KNN. The main objective of this research is to study the prediction of Alzheimer’s disease and all stages of disease by using image processing techniques and different machine learning algorithm’s . |