Analisis Monitoring Gelombang EEG Otak Pasien Anak dengan Epilepsi Menggunakan Model Markov Switching Autoregressive dengan Pendekatan EM-Gaussian dan Bayesian-Fernandez-Steel Skew Normal

Kuntaritas, Dede Yusuf P. (2023) Analisis Monitoring Gelombang EEG Otak Pasien Anak dengan Epilepsi Menggunakan Model Markov Switching Autoregressive dengan Pendekatan EM-Gaussian dan Bayesian-Fernandez-Steel Skew Normal. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06211940007001-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (2MB) | Request a copy

Abstract

Jumlah anak berkebutuhan khusus (ABK) di Indonesia mencapai angka 2,1 juta anak pada tahun 2021 berdasarkan data dari KEMENKO PMK. Seharusnya orang tua, guru, masyarakat, dan juga pemerintah perlu memberikan perhatian khusus pada tumbuh kembang ABK agar mereka dapat merasakan kesempatan yang sama seperti anak pada umumnya. Namun, pada kenyataannya orang tua masih kurang memiliki pengetahuan dasar dalam mengawasi dan memperhatikan ABK. Sehingga diperlukan seseorang yang memiliki keahlian dalam mengawasi aktivitas ABK. Salah satu cara pengawasan ABK ialah dengan memperhatikan pergerakan gelombang EEG otak. Gelombang EEG otak yang diamati merupakan data time series yang bersifat fluktuatif dan non linier. Melihat karakteristik dari data tersebut maka dilakukan penelitian mengenai pemodelan menggunakan markov switching autoregressive (MSAR) dengan pendekatan EM-Gaussian dan Bayesian-FSSN untuk memonitor gelombang EEG otak pasien anak dengan epilepsi. Data yang digunakan pada penelitian ialah hasil rekaman gelombang EEG otak anak dengan epilepsi di Rumah Sakit Universitas Airlangga Surabaya yang direkam selama 30 menit pada 22 channel. Namun pada penelitian ini hanya mengambil 10 detik rekaman pada channel T1-Cz dan T2-Cz. Hasil analisis yang dilakukan menunjukkan bahwa model FSSN MS(2)AR(1) merupakan model terbaik untuk memodelkan data gelombang EEG otak pada T1-Cz maupun T2-Cz. Selain itu dapat diketahui juga bahwa gelombang EEG otak anak dengan epilepsi yang diamati menunjukkan pergerakan yang abnormal.
====================================================================================================================================
The number of children with special needs (CWSN) in Indonesia reached 2.1 million in 2021 according to data from the Coordinating Ministry for Human Development and Cultural Affairs (KEMENKO PMK). Ideally, parents, teachers, the community, and the government should provide special attention to the growth and development of CWSN so that they can have equal opportunities like other children. However, in reality, parents still lack basic knowledge in supervising and attending to CWSN. Therefore, someone with expertise in monitoring the activities of CWSN is needed. One way to monitor CWSN is by observing the brain's EEG wave patterns. The observed brain EEG wave data is a fluctuating and nonlinear time series data. Considering the characteristics of the data, a research study was conducted on modeling using Markov switching autoregressive (MSAR) with the EM-Gaussian and Bayesian-FSSN approaches to monitor the brain EEG waves of child patients with epilepsy. The data used in the study were recordings of brain EEG waves of children with epilepsy at Airlangga University Hospital in Surabaya, recorded for 30 minutes on 22 channels. However, this study only took a 10-second recording on channels T1-Cz and T2-Cz. The results of the analysis showed that the FSSN MS(2)AR(1) model was the best model for modeling the brain EEG wave data on both T1-Cz and T2-Cz. Additionally, it was found that the observed brain EEG waves of children with epilepsy exhibited abnormal movements.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	EEG, Epilepsi, FSSN, Gaussian, MSAR; EEG, Epilepsy, FSSN, Gaussian, MSAR.
Subjects:	Q Science > QA Mathematics > QA246.8 Gaussian Q Science > QA Mathematics > QA274.2 Stochastic analysis Q Science > QA Mathematics > QA274.7 Markov processes--Mathematical models. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory. Q Science > QP Physiology > Q376.5 Electroencephalography (EEG)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Dede Yusuf P. Kuntaritas
Date Deposited:	23 Aug 2023 06:44
Last Modified:	03 Oct 2024 09:48
URI:	http://repository.its.ac.id/id/eprint/104329

Actions (login required)

View Item