Classification of EEG Spectrogram Using ANN for IQ Application

• Main Authors: Mahfuzah, Mustafa, Norizam, Sulaiman
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/3794/2/fkee_mahfuzah_2013.pdf; http://umpir.ump.edu.my/id/eprint/3794/

The intelligence term can be view in many areas such as linguistic, mathematical, music and art. In this paper, the Intelligence Quotient (IQ) is measured using Electroencephalogram (EEG) from the human brain. The spectrogram images were formed from EEG signals, then the Gray Level Co-occurrence Matrix (GLCM) texture feature were extracted from the images. This texture feature produced big matrix data, thus Principal Component Analysis (PCA) is used to reduce the big matrix. Then, ANN algorithm is employed to classify the EEG spectrogram image in IQ application. The results will be validated based on the concept of Raven's Standard Progressive Matrices (RPM) IQ test. The results showed that the ANN was able to classify the EEG spectrogram image with 88.89% accuracy and 0.0633 MSE