EVALUATION OF FEATURE EXTRACTION AND CLASSIFICATION TECHNIQUES FOR EEG-BASED SUBJECT IDENTIFICATION

The ability to identify a subject is indispensable in affective computing research due to its wide range of applications. User profiling was created based on the strength of emotional patterns of the subject, which can be used for subject identification. Such system is made based on the emotional states of happiness and sadness, indicated by the electroencephalogram (EEG) data. In this paper, we examine several techniques used for subject profiling or identification purposed. Those techniques include feature extraction and classification techniques. In the experimental study, we compare three techniques for feature extraction namely, Power Spectral Density (PSD), Kernel Density Estimation (KDE), and Mel Frequency Cepstral Coefficients (MFCC). As for classification we compare three classification techniques, they are; Multilayer Perceptron (MLP), Naive Bayesian (NB), and Support Vector Machine (SVM). The best result achieved was 59.66%, using the MFCC and MLP-based techniques using 5-fold cross validation. The experiment results indicated that these profiles could be more accurate in identifying subject compared to NB and SVM. The comparisons demonstrated that profile-based methods for subject identification provide a viable and simple alternative to this problem.