Klasifikasi Ictal dan Interictal Berdasarkan Rekaman EEG pada Pasien Epilepsi di Rumah Sakit Universitas Airlangga Menggunakan Smooth Support Vector Machine

Cahyaningrum, Fibia Sentauri (2019) Klasifikasi Ictal dan Interictal Berdasarkan Rekaman EEG pada Pasien Epilepsi di Rumah Sakit Universitas Airlangga Menggunakan Smooth Support Vector Machine. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211540000074_Undergraduate_Theses.pdf] Text
06211540000074_Undergraduate_Theses.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (3MB) | Request a copy

Abstract

Epilepsi merupakan salah satu gangguan neurologi yang ditandai dengan serangan kejang berulang. Peningkatan risiko serangan epilepsi dapat digambarkan dengan menggunakan EEG (electroencephalogram), yaitu rekaman aktivitas listrik sepanjang kulit kepala yang dihasilkan oleh penembakan neuron dalam otak selama periode tertentu. Klinis dengan kejang (ictal) dan klinis tanpa kejang (interictal) berdasarkan rekaman EEG perlu diklasifikasikan untuk mempermudah tenaga medis dalam memberikan treatment kepada pasien epilepsi. Namun, hasil analisa rekaman EEG secara visual antar tenaga medis dapat menghasilkan diagnosa yang berbeda akibat dari subjektivitas dan pengalaman tenaga medis yang berbeda, sehingga diperlukan metode klasifikasi yang cepat dan tepat. Metode pre-processing data rekaman EEG yang digunakan adalah Discrete Wavelet Transform untuk mendekomposisikan sinyal sehingga didapatkan gelombang theta, alpha, dan beta. Gelombang tersebut diekstraksi ke dalam fitur energy, deviasi standar, maksimum, minimum, dan entropy. Selanjutnya, pada tahap klasifikasi ictal dan interictal berdasarkan rekaman EEG menggunakan SVM dan SSVM didapatkan AUC masing-masing sebesar 97.83% dan 100%, sehingga metode SSVM lebih baik dibandingkan metode SVM.
================================================================================================
Epilepsy is a neurological disorder characterized by recurrent seizures. The increased risk of epileptic seizures can be described using EEG (electroencephalogram), which is a record of electrical activity along the scalp produced by the firing of neurons in the brain over a period of time. Clinically with seizures (ictal) and clinical without seizures (interictal) based on EEG recordings need to be classified to facilitate medical personnel in providing treatment to epilepsy patients. However, the results of analyzing EEG recordings visually between medical personnel can produce different diagnoses as a result of subjectivity and experience of different medical personnel, so a fast and precise classification method is needed. The pre-processing method of EEG recording data used is Discrete Wavelet Transform to decompose signals so that theta, alpha, and beta waves are obtained. The wave is extracted into the energy feature, standard deviation, maximum, minimum and entropy. Furthermore, at the ictal and interictal classification stages based on EEG recordings using SVM and SSVM, the AUC was 97.83% and 100% respectively, so the SSVM method was better than the SVM.

Item Type: Thesis (Undergraduate)
Additional Information: RSSt 519.536 Cah k-1 2019
Uncontrolled Keywords: DWT, EEG, Epilepsi, SSVM, SVM
Subjects: H Social Sciences > HA Statistics
H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Fibia Sentauri Cahyaningrum
Date Deposited: 25 Nov 2021 02:35
Last Modified: 25 Nov 2021 02:35
URI: http://repository.its.ac.id/id/eprint/61622

Actions (login required)

View Item View Item