• 대한의용생체공학회:의공학회지
• /
• 제15권1호
• /
• pp.105-110
• /
• 1994

In this paper, we present a method to evaluate source locations and distributed region which is specified brain activity, as indicated by locations and strengths of intracranial sources, using potential gradients of interpolation polynomials and topographic mapping of the EEG records. This method can analyze the variance of source temporally or spatially and leads to enable a quantitative evaluation of potential gradients drawing methods which is now being used in the clinic. In the result, we obtained the overall potentials distribution on the entire scalp and the information of potential source locations from the EEG records of a patient which was known to epilepsy.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(5)
• /
• pp.127-130
• /
• 2000

Classification of Electroencephalogram(EEG) makes one of key roles in the field of clinical diagnosis, such as detection for epilepsy. Spectrum analysis using the fourier transform(FT) uses the same window to signals, so classification rate decreases for nonstationary signals such as EEG's. In this paper, wavelet power spectrum method using wavelet transform which is excellent in detection of transient components of time-varying signals is applied to the classification of three types of Event Related Potential(EP) and compared with the result by fourier transform. In the experiments, two types of photic stimulation, which are caused by eye opening/closing and artificial light, are used to collect the data to be classified. After choosing a specific range of scales, scale-averaged wavelet spectrums extracted from the wavelet power spectrum is used to find features by Back-Propagation(13P) algorithm. As a result, wavelet analysis shows superiority to fourier transform for nonstationary EEG signal classification.

• Annals of Clinical Neurophysiology
• /
• 제2권1호
• /
• pp.27-30
• /
• 2000

Reflex epilepsies are distinct but not clearly understood clinical entity. Various cerebral activities induced by simple stimulation including visual, auditory, somatosensory stimulation, as well as diverse functional tasks such as reading, calculation, complex thinking are believed to be seizure-inducing factors. We experienced two patients whose seizures were readily precipitated by complex, strenuous thinking. Both patients was teen-aged boy at the onset of seizure(13, and 15 years of age each) with normal physical and mental growth. Although first seizure was precipitated by watching TV and playing puzzles in each patient, initial diagnosis was idiopathic generalized epilepsy, possibly juvenile myoclonic epilepsy( JME). For the first few years, seizures were infrequent but mostly precipitated by the tasks needs concentration such as playing computer games, decision-making, mathematics, reading, or during the examination. EEG revealed various thinking process including reading hard books, drawing complex figure, complex calculation induced epileptic discharges even if it usually needs certain period of concentration. Phenytoin, valproic acid, clonazepam, vigabatrin, and lamotrigine sometimes abated their seizures but none of these made them seizure-free. Complex reflex epilepsy induced by thinking was proposed to be a separate type of epilepsy or a variant of JME. Age, sex, stereotypic seizure-inducing factors, clinical course, and refractory epilepsies in these patients highly suggested this type of epilepsy as a variant of JME but its refractoriness and unique provocation still needs more speculation.

• 한국지능시스템학회논문지
• /
• 제18권2호
• /
• pp.251-256
• /
• 2008

많은 연구자들은 여러 개의 채널을 가진 Electroencephalogram(EEG) 신호를 기반으로 한 사람의 감정인식을 위해 두뇌와 컴퓨터의 인터페이스에 관한 연구를 하고 있다. EEG 신호를 이용한 연구들은 주로 의학 분야와 심리학의 영역에서 간질이나 발작 등을 알아내고 거짓말 탐지기로써의 역할로 많이 사용되어져 왔다. 최근에는 사람의 두뇌와 컴퓨터 간의 인터페이스에 관한 연구들이 뇌파를 이용한 로봇의 제어하거나 게임을 하는 등의 여러 가지 공학적인 접근으로써 많은 연구가 진행되고 있다. 특히, EEG 신호를 통해서 두뇌를 연구하는 분야에서 EEG 신호의 잡음을 제거해서 보다 정확한 신호를 추출하는 연구에도 많이 중점을 두고 있다. 본 논문에서는 사람의 감정에 따른 EEG 신호를 측정하고 측정된 EEG 신호를 5개 부분의 주파수 영역으로 분류하였다. 영역별로 분류된 EEG 신호들은 전체영역에 대한 상대적인 비율의 값으로 계산하게 된다. 그 값들은 Bayesian Networks를 통해서 현재 어떠한 감정을 나타내는지 확률 값으로 나타낸다. 그 결과 값에 따라 사람의 감정은 아바타로 표현하게 된다.

• 한국지능시스템학회논문지
• /
• 제17권6호
• /
• pp.832-837
• /
• 2007

많은 연구자들은 인간의 사고를 functional Magnetic Resonance Imaging (fMRI), Time Resolved Spectroscopy(TRS), Electroencephalography(EEG)등을 이용해서 두뇌 활동 영역을 연구하고 있다. 주로 의학 분야와 심리학의 영역에서 두뇌의 활동을 연구하여 간질이나 발작을 알아내고 거짓말 탐지 분야에서도 사용된다. 본 논문에서는 사람의 두뇌활동을 측정하여 인간의 감정을 인식하는 연구에 중점을 두었다. 특히, fMRI와 TRS 그리고 EEG를 이용해서 사람의 두뇌 활동을 측정하는 연구를 하였다. 많은 연구자들이 한 가지 측정 장치만을 사용하여서 측정하거나 fMRI와 EEG를 동시에 측정하는 연구를 진행하고 있다. 현재에는 단순히 두뇌의 활동을 측정하거나 측정 시 발생하는 잡음들을 제거하는 연구들에 중점을 두고 진행되고 있다. 본 연구에서는 fMRI와 TRS를 동시에 측정하여 얻은 두뇌 활동 데이터를 가지고 감정에 따른 활동영역의 EEG 신호를 측정하였다. EEG 신호분석에 있어서 기존의 뇌파만을 가지고 특징을 찾아내는 것을 넘어서 각각의 채널에서 기록되는 뇌파의 파형을 주파수에 따라서 분류하고 정확한 측정을 위해 낮은 주파수를 제거하고 연구자가 필요한 부분의 뇌파를 분석하였다.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.92-95
• /
• 2020

In this paper, the new architecture of seizure prediction using CNN and LSTM and DWT was presented. In the proposed architecture, EEG data was labeled into a preictal and interictal section, and DWT was adopted to the preprocessing process to apply the characteristics of the time and frequency domain of the processed EEG signal. Also, CNN was applied to extract the spatial characteristics of each electrode used for EEG measurement, and LSTM neural network was applied to verify the logical order of the preictal section. The learning of the proposed architecture utilizes the CHB-MIT Scalp EEG dataset, and the sliding window technique is applied to balance the dataset between the number of interictal sections and the number of preictal sections. As a result of the simulation of the proposed architecture, a sensitivity of 81.22% and an FPR of 0.174 were obtained.

• The Korean Journal of Physiology and Pharmacology
• /
• 제23권2호
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• Journal of Korean Neurosurgical Society
• /
• 제56권3호
• /
• pp.248-253
• /
• 2014

Objective : Cortical dysplasia (CD) is one of the common causes of epilepsy surgery. However, surgical outcome still remains poor, especially with frontal lobe epilepsy (FLE), despite the advancement of neuroimaging techniques and expansion of surgical indications. The aim of this study was to focus on surgical strategies in terms of extent of resection to improve surgical outcome in the cases of FLE with CD. Methods : A total of 11 patients of FLE were selected among 67 patients who were proven pathologically as CD, out of a total of 726 epilepsy surgery series since 1992. This study categorized surgical groups into three according to the extent of resection : 1) focal corticectomy, 2) regional corticectomy, and 3) partial functional lobectomy, based on the preoperative evaluation, in particular, ictal scalp EEG onset and/or intracranial recordings, and the lesions in high-resolution MRI. Surgical outcome was assessed following Engel's classification system. Results : Focal corticectomy was performed in 5 patients and regional corticectomy in another set of 5 patients. Only 1 patient underwent partial functional lobectomy. Types I and II CD were detected with the same frequency (45.45% each) and postoperative outcome was fully satisfactory (91%). Conclusion : The strategy of epilepsy surgery is to focus on the different characteristics of each individual, considering the extent of real resection, which is based on the focal ictal onset consistent with neuroimaging, especially in the practical point of view of neurosurgery.

• 정신신체의학
• /
• 제19권2호
• /
• pp.101-108
• /
• 2011

연구목적: 주의력결핍 과잉행동장애(Attention Deficit Hyperactivity Disorder, ADHD)와 간질 사이에서 나타나는 공통적 특성을 연구할 목적으로 Korea-Child Behavior Checklist(K-CBCL)과 ADHD Diagnostic System (ADS), Electroencephalogram(EEG)를 평가하여 두 질환군의 공통적 특성(Common features)을 알아보고자 하였다. 방 법: 6세부터 16세까지의 소아,청소년들을 대상으로 ADHD군 30명 간질군 34명 그리고 대조군은 29명이었다. 평가도구는 K-CBCL과 자가보고 도구인 ADS를 사용하였으며 뇌파를 측정하였다. 모든 결과의 분석은 다중변량분석(MANOVA)과 교차분석(${\chi}^2$-test)을 이용하였다. 결 과: 간질군, ADHD군 간의 공통적 특성으로 뇌파에서 비정상 뇌파 소견(대조군 13.8%, 간질군 97.1%, ADHD군 40%)을 보인 것과 ADS에서 부주의, 반응시간 표준편차 항목에서 유의미한 차이가 있음이 확인되었다. 결 론: 간질군과 ADHD군에서 비정상 뇌파 소견, 부주의, 반응시간 표준편차라는 공통적 특성이 있음을 확인하였다.

• Biomedical Engineering Letters
• /
• 제8권4호
• /
• pp.373-382
• /
• 2018

Since epileptic seizure is unpredictable and paroxysmal, an automatic system for seizure detecting could be of great significance and assistance to patients and medical staff. In this paper, a novel method is proposed for multichannel patient-specific seizure detection applying the earth mover's distance (EMD) in scalp EEG. Firstly, the wavelet decomposition is executed to the original EEGs with five scales, the scale 3, 4 and 5 are selected and transformed into histograms and afterwards the distances between histograms in pairs are computed applying the earth mover's distance as effective features. Then, the EMD features are sent to the classifier based on the Bayesian linear discriminant analysis (BLDA) for classification, and an efficient postprocessing procedure is applied to improve the detection system precision, finally. To evaluate the performance of the proposed method, the CHB-MIT scalp EEG database with 958 h EEG recordings from 23 epileptic patients is used and a relatively satisfactory detection rate is achieved with the average sensitivity of 95.65% and false detection rate of 0.68/h. The good performance of this algorithm indicates the potential application for seizure monitoring in clinical practice.