K-NN classification of brain dominance

Khairul Amrizal, Abu Nawas and Mahfuzah, Mustafa and Rosdiyana, Samad and Pebrianti, Dwi and Nor Rul Hasma, Abdullah (2017) K-NN classification of brain dominance. International Journal of Electrical and Computer Engineering (IJECE), 8 (4). pp. 2494-2502. ISSN 2088-8708. (Published)

K-NN classification of brain dominance.pdf
Available under License Creative Commons Attribution Non-commercial.

Download (616kB) | Preview


The brain dominance is referred to right brain and left brain. The brain dominance can be observed with an Electroencephalogram (EEG) signal to identify different types of electrical pattern in the brain and will form the foundation of one’s personality. The objective of this project is to analyze brain dominance by using Wavelet analysis. The Wavelet analysis is done in 2-D Gabor Wavelet and the result of 2-D Gabor Wavelet is validated with an establish brain dominance questionnaire. Twenty one samples from University Malaysia Pahang (UMP) student are required to answer the establish brain dominance questionnaire has been collected in this experiment. Then, brainwave signal will record using Emotiv device. The threshold value is used to remove the artifact and noise from data collected to acquire a smoother signal. Next, the Band-pass filter is applied to the signal to extract the sub-band frequency components from Delta, Theta, Alpha, and Beta. After that, it will extract the energy of the signal from image feature extraction process. Next the features were classified by using K-Nearest Neighbor (K-NN) in two ratios which 70:30 and 80:20 that are training set and testing set (training: testing). The ratio of 70:30 gave the highest percentage of 83% accuracy while a ratio of 80:20 gave 100% accuracy. The result shows that 2-D Gabor Wavelet was able to classify brain dominance with accuracy 83% to 100%.

Item Type: Article
Uncontrolled Keywords: Wavelet; K-NN; Brain dominance
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Faculty of Electrical & Electronic Engineering
Depositing User: Pn. Hazlinda Abd Rahman
Date Deposited: 07 Oct 2019 08:08
Last Modified: 07 Oct 2019 08:08
URI: http://umpir.ump.edu.my/id/eprint/21013
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item