EEG Based Diagnosis of Alzheimer`s Disease Detection Using SVM Classifier

Abstract

Alzheimer’s disease is a neurodegenerative disease that demolishes memory and other important cognitive and behavioral functions. It is one of the severe mental diseases in which brain cell connections and the cells themselves degenerate and die. Alzheimer’s is caused by an integration of genetic, environmental and lifestyle factors that affect the brain over time. An early diagnosis provides patient with a better chance of benefiting from treatment and also helps his family to take preventive measures for patient. Therefore, the aim of this research work is to detect Alzheimer’s in early stage by means of analyzing the electroencephalogram signals in time and frequency domain. In present research work, wavelet based features are analyzed and given as an input for classifier. Daubechies wavelet is used for signal analysis. Accordingly, statistical features such as mean, variance, standard deviation, skewness and kurtosis are computed and used for classification. Support Vector Machine, a semi-supervised classifier is used for classifying the data into two classes giving satisfactory results. The research is carried on experimental database. Therefore, the presented work presents a reliable methodology for Alzheimer’s diagnosis.