Epileptic Seizure Detection Based on Bandwidth Features of EEG Signals

Wulandari, Diah Puspito; Putriz, Nomala G.P.; Suprapto, Yoyon K.; Purnami, Santi Wulan; Juniani, Anda Iviana; Islamiyah, Wardah Rahmatul

doi:10.1016/j.procs.2019.11.157

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The diversity of epileptic seizures makes it challenging to distinguish the sequence of epilepsy episodes from normal EEG. Wulandari et al [22] considered the EEG signal spectrum characteristics to differentiate seizure and non-seizure disorders of epilepsy. A technology that could predict the onset of the seizure event can alert both the patient and physician, and the quality of life of the patient can be improved significantly.…”

Section: Related Workmentioning

confidence: 99%

Classification of Seizure Types Using Random Forest Classifier

Ashjan¹,

Arif²

2021

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

Epilepsy is one of the most common mental disorders in the world, affecting 65 million people. The prevalence in Arab countries of Epilepsy is estimated at 174 per 100,000 individuals, and in Saudi Arabia is 6.54 per 1,000 individuals. Epilepsy seizures have different types, and each patient needs to have a treatment plan according to the seizure type. Hence, accurate classification of seizure type is an essential part of diagnosing and treating epileptic patients. In this paper, the features based on fast Fourier transform from EEG montages were used to classify different types of seizures. Since the distribution of classes was not uniform, the dataset suffered from severe imbalance. Various algorithms were used to under-sample the majority class and over-sample the minority classes. Random forest classifier produced classification accuracy of 96% to differentiate three types of seizures from the healthy EEG reading.

show abstract

Section: Related Workmentioning

confidence: 99%

Classification of Seizure Types Using Random Forest Classifier

Ashjan¹,

Arif²

2021

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

show abstract

“…Banyak metode pengobatan telah dilakukan untuk pasien dengan epilepsi, tetapi diperkirakan sekitar sepertiga pasien dengan epilepsi masih mengalami kondisi yang sama (Ramgopal, Thome-Souza, Jackson, Kadish, Fernandez, Klehm, Bosl, Reinsberger, Schachter, & Loddenkemper, 2014). Untuk memeriksa keadaan epilepsi, metode Electroenchepalography (EEG) telah banyak digunakan (Wulandari, et. al., 2019).…”

unclassified

EpCare: Prototipe Sistem Detektor Pre-Iktal Pasien Epilepsi Berbasis Fitur CSI dari Sinyal EKG 1 Kanal Menggunakan AD8232

Wulandari,

Kurniawan,

Nathanael

et al. 2023

JTIIK

View full text Add to dashboard Cite

Kejang epilepsi dapat terjadi di sembarang waktu dan tempat, dan dalam kondisi tertentu dapat menyebabkan cedera fatal. Oleh karena itu, kebutuhan akan perangkat wearable yang dapat mengirimkan peringatan kepada pengguna akan kejang yang akan datang adalah penting. Perangkat ini harus dapat merasakan kelainan pada sinyal biomedis pengguna dan mengirimkan peringatan sebelum kejang. Penelitian ini mengembangkan sistem yang mendeteksi kondisi pre-iktal pasien epilepsi berdasarkan fitur Cardiac Sympathetic Index (CSI) dari sinyal Elektrokardiogram (EKG). Listrik jantung pasien diukur menggunakan 3 elektroda yang dihubungkan ke AD8232 untuk mewakili sinyal 1 kanal. Algoritma Pan-Tompkins diimplementasikan untuk mendapatkan interval RR dari sinyal EKG. Kemudian fitur CSI dihitung berdasarkan nilai RR-interval. Distribusi setiap 100 interval RR dijadikan sebagai dasar untuk menentukan nilai ambang batas CSI. Ketika nilai CSI melebihi ambang batas ini, sistem akan mengirimkan peringatan ke aplikasi seluler, yang disebut EpCare. Eksperimen dilakukan pada dua kelompok data, yaitu kelompok data primer dari non-penderita epilepsi dan kelompok data sekunder dari penderita epilepsi. F-measure dari eksperimen yang menggunakan ambang batas dari orang normal sebesar 0.64, sedangkan F-measures dari eksperimen yang menggunakan ambang batas individual penderita epilepsy sebesar 0.50. AbstractEpileptic seizures may occur at anytime and anywhere, and in certain conditions may lead to fatal injury. Therefore, the need for wearable device that can alert user to an impending seizure is important. This device should be able to sense abnormality in user’s biomedical signals and send alert prior to seizure. This research develops a system that detects pre-ictal condition of epilepsy patient based on Cardiac Sympathetic Index (CSI) feature from Electrocardiogram (ECG) signals. Patient’s heart electricity is measured using 3 electrodes which are connected to AD8232 to represent 1 channel signal. Pan-Tompkins algorithm is implemented to obtain RR intervals of ECG signals. Then, CSI feature is calculated based on the values of RR-intervals. A distribution of every 100 RR-intervals is made as basis to determine a threshold value of CSI. When CSI value exceeds this threshold, system will send alert to a mobile application, called EpCare. Experiments were conducted on two groups of data, which are primary one from non-epileptic persons, and secondary one from epileptic patients. F-measures of experiments used threshold of non-epileptic person is 0.64, while F-measures of experiments used individual threshold of epileptic person is 0.50.

show abstract