Perbandingan Support Vector Machine dan Least Square Support Vector Machine untuk Klasifikasi Ictal dan Interictal Berdasarkan Data Rekaman EEG Pasien Epilepsi di Rumah Sakit Universitas Airlangga

Nuraisyah, Triajeng (2019) Perbandingan Support Vector Machine dan Least Square Support Vector Machine untuk Klasifikasi Ictal dan Interictal Berdasarkan Data Rekaman EEG Pasien Epilepsi di Rumah Sakit Universitas Airlangga. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211540000080-Undergraduate_Theses.pdf] Text
06211540000080-Undergraduate_Theses.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2022.

Download (3MB) | Request a copy

Abstract

Epilepsi merupakan penyakit neurologis yang ditandai dengan kejang berulang tanpa alasan. Sekitar 50 juta orang di seluruh dunia menderita epilepsi sehingga epilepsi dianggap sebagai penyakit neurologis paling umum. Proses diagnosis penyakit epilepsi dapat dilakukan melalui electroencephalogram (EEG). Pada perekaman EEG terdapat dua periode yang perlu diperhatikan, yaitu periode ictal (klinis dengan kejang) dan interictal (klinis tanpa kejang). Seringkali pemeriksaan secara visual sinyal EEG melibatkan unsur subyektifitas dan membutuhkan pengalaman. Oleh karena itu, perlu dilakukan deteksi otomatis periode ictal dan interictal dengan metode klasifikasi. Dalam penelitian ini digunakan metode Support Vector Machine (SVM) dan Least Square Support Vector Machine (LS SVM). Sebelum dilakukan klasifikasi, terlebih dahulu dilakukan proses pre-processing dengan metode Discrete Wavelet Transform (DWT). Hasil penelitian menunjukkan klasifikasi dengan metode SVM kernel RBF lebih baik daripada metode LS SVM kernel RBF. Hal ini didasarkan pada performansi klasifikasi SVM kernel RBF yang konsisten baik pada pembagian data menggunakan metode 10-fold cross validation atau data pasien 2 sebagai data testing baru.
================================================================================================
Epilepsy is a neurological disease characterized by recurrent seizures without reason. About 50 millions people worldwide suffer from epilepsy. It makes epilepsy become one of the most common neurological diseases globally. The process of diagnosing epilepsy can be done through electroencephalogram (EEG). There are two periods that need to be considered in EEG, such as ictal and interictal. Visual inspection of EEG signals often involves subjectivity and needs experiences. Therefore, it is necessary to do automatic detection about ictal and interictal using classification method. In this study, Support Vector Machine (SVM) and Least Square Support Vector Machine (LS SVM) classifier is used. Before classify EEG signals, pre-processing data is firstly done, using Discrete Wavelet Transform (DWT). The classification result shows that SVM RBF is better than LS SVM RBF. It is based on the consistency of the SVM RBF’s performance while using 10-fold cross validation or data of patient 2 as new testing data.

Item Type: Thesis (Undergraduate)
Additional Information: RSSt 616.804 754 7 Nur p-1 2019
Uncontrolled Keywords: DWT, EEG, Ictal, Interictal, LS SVM, SVM
Subjects: Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
R Medicine > RC Internal medicine > RC386.5 Electroencephalography.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Nuraisyah Triajeng
Date Deposited: 13 Dec 2021 08:34
Last Modified: 13 Dec 2021 08:34
URI: http://repository.its.ac.id/id/eprint/61705

Actions (login required)

View Item View Item