Analysis of EEG Spectrum Bands Using Power Spectral Density for Pleasure and Displeasure State

• Published in: IOP conference series. Materials Science and Engineering Vol. 557; no. 1; pp. 12030 - 12034
• Main Authors: Ameera, Anis, Saidatul, A., Ibrahim, Z
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.06.2019
• Subjects: Bandpass filters; Biomedical engineering; Brain; Discriminant analysis; Electroencephalography; Engineering education; Frequencies; Power spectral density; Signal processing
• ISSN: 1757-8981; 1757-899X
• DOI: 10.1088/1757-899X/557/1/012030

The technology of reading human mental states is a leading innovation in the biomedical engineering field. EEG signal processing is going to help us to explore the uniqueness of brain signal that carries thousands of information in human being. The aim of this study is to analyze brain signal features between pleasure and displeasure mental state. Brainwaves is divided into 5 sub frequency bands namely alpha (8 - 13 Hz), beta (13 - 30 Hz), gamma (30 - 100 Hz), theta (4 - 8 Hz) and delta (1 - 4 Hz). However, in this study, alpha and beta waves were analyzed to investigate the mental states. Twenty subjects were recruited from undergraduate engineering student's education background in UniMAP with age ranging between 19 to 23 years old. The subject must be healthy and right-handed. The subject was required to view a series of pleasure and displeasure images for 10 minutes and take rest for 30 seconds between pleasure and displeasure view. Truscan EEG device (Deymed Diagnostic, Alien Technic, Czech Republic) with 19 channels were used to acquire EEG data with frequency sampling of 1024 Hz and impedance is kept below 5 kΩ. A bandpass filter was used to extract alpha and beta waves. The signal was segmented and PSD value using Welch and Burg method was calculated for both mental states. 7 statistical features (mean, mode, median, variance, standard deviation, minimum and maximum) were obtained from PSD value and used as an input for the classifier. K-Nearest Neighbour (KNN) and Linear Discriminant Analysis (LDA) were used to classify into two mental states. As a result, Welch method gives the highest classification accuracy which is 99.3 % for alpha waves followed by 97.5 % for beta waves from channel F4. It can be concluded that alpha waves are the most potential waves to be used in order to differentiate pleasure and displeasure features.