Abstract:

Electroencephalography (EEG) is a method to measure the electrical activity of brain signals by electrodes attached to the scalp at multiple locations. In this study we used the EEG signals of Alcoholic and Control subjects were obtained from Machine Learning repository according to the 10-20 International System. There were 29 subjects from control group and 29 from alcoholic comprising of electrodes from different brain lobes such as Central Lobe (C3, C4), Frontal (F3, F4, F7, F8), Occipital Lobe (O1, O2), Parietal Lobe (P3, P4), Temporal Lobe (T7) and Front Polar (Fp1, Fp2). In the first phase, the nonlinear complexity based features are computed such as Approximate Entropy, Sample Entropy and Wavelet Entropy. These features for each electrode are passed as input to the Machine Learning classifiers such as Multilayer Perceptron (MPL), K-nearest Neighbor (KNN) and LIB Support Vector Machine (SVM) to classify for alcoholic and control group. The highest accuracy was obtained using MLP of 98.22 % at electrode C3. Moreover, above 90% accuracy was obtained using MPL at electrode C3, C4, F7; KNN at electrodes C3, C4, F7 and LIB SVM at electrodes C3, C4, F7 where KNN gives highest accuracy of 97.67% at electrode C4 and LIB SVM an accuracy of 94.67 % at electrode F7. Secondly, the ensemble methods are employed such as Minimum, Maximum, Sum, Average, Product, Majority Vote, Bayes, Decision Template and Dempster Shefer Fusion. Using ensemble methods most electrodes depicted higher accuracy than individual classifier such as Electrode F4, Fp2, O1, O2 and T7. While electrode C3 the ensemble methods Moving Average, DT, DFT gives highest accuracy of 98.22% and at electrodes C4 Moving Average, Sum, Average, DT, DFT provided an accuracy of 97.11%.