ENERGY DISTRIBUTION IMAGE PROCESSING OF EEG SIGNAL STROKE USING GRAY LEVEL CO-OCCURRENCE MATRIX AND CHANNEL SELECTION
SAFIRA AMALIA PUSPITASARI R

Informasi Umum

Kode

22.05.070

Klasifikasi

006.31 - Machine Learning

Jenis

Karya Ilmiah - Thesis (S2) - Reference

Subjek

Machine Learning

Dilihat

247 kali

Informasi Lainnya

Abstraksi

<p>Brain Computer Interface (BCI) is getting a lot of attention from researchers because<br /> BCI is a system used to translate, manage and recognize human brain activity.<br /> Electroencephalography (EEG) is one type of BCI which is included in non-invasive<br /> because EEG uses external sensors to measure brain activity. However, EEG has a<br /> non-stationary characteristic. Therefore the information on the EEG signal is difficult<br /> to process.<br /> This thesis proposes (i) converting the EEG signal into an image and (ii) optimizing<br /> the BCI system using feature selection and channel selection. The data used<br /> is the EEG stroke signal data set from Universiti Teknologi Malaysia. EEG signal<br /> feature extraction with the power spectrum density (PSD). The value of the energy<br /> distribution is carried out by brain mapping for each channel. The image feature<br /> extraction used is GLCM with 11 statistical characteristics. Feature selection using<br /> the GA, MI, and Chi-Square methods to find the optimal method for the system.<br /> Therefore, in this thesis, we propose channel selection in the energy distribution<br /> image to eliminate irrelevant channels by taking the value of the selected channel<br /> on the channel. The classification method in this thesis is Artificial Neural Network<br /> Back-Propagation (ANN-BP). The validity of the proposed BCI system is training<br /> accuracy, test accuracy, time complexity, and brain mapping.<br /> The feature selection results using the GA method are 7 GLCM characteristics:<br /> correlation, energy, homogeneity, inverse difference momentum, different variance,<br /> and sum variance. Optimization with channel selection produces 9 channels: AF4,<br /> FCz, FC4, FT8, C4, T8, Cp4, Pz, and Oz. Compared with the image system without<br /> and with channel selection, the accuracy with channel selection can improve 5%<br /> and the time complexity is faster, with a gap of 1,928 ms. Since the EEG signal<br /> has a non-stationary characteristic that makes each class challenging to identify,<br /> irrelevant values can be omitted because they can confuse the system. This thesis<br /> generates the optimal system by using an energy distribution image system using<br /> the GA-GLCM feature selection and channel selection.</p>

<p><br /> Keywords: EEG signal, energy distribution image, channel selection, feature<br /> selection, brain mapping.</p>

• TTI7Z4 - TESIS

Koleksi & Sirkulasi

Seluruh 1 koleksi sedang dipinjam

Pengarang

Penerbit

Sirkulasi

Download / Flippingbook