• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Proceedings of the ESK Conference
• /
• 1997.10a
• /
• pp.386-390
• /
• 1997

SAC 847 컴퓨터를 통해서 뇌파를 기본으로 턱과 다리의 근전도, 몸의 뒤척임, 심전도, 혈중 산소 농 도, 안전도 등을 동시에 기록하는 다원수면검사(polysomnogram)를 전자기가 차폐된 수면실에서 실시하 였고 수면단계기록 국제기준에 의한 수면단계와 최근 새롭게 제시되고 있는 수면의 경과에 따른 수면방 추파(sleep spindle)의 변동추적에 의한 수면단계 판정방법을 비교 분석하였다. 또한, 수면경과에 따른 .beta. .alpha. .theta. .delta. 파형의 발생빈도를 제시하고 평가하였다. 이러한 수면단계 분석은 종합 수면생리신호의 일환으로 인간공학적인 쾌적침대개발에 활용될 수 있을 것이다.

• The Journal of Korean society of community based occupational therapy
• /
• v.8 no.2
• /
• pp.29-37
• /
• 2018

Objective : Sleep disorder caused by stress or disease to elderly currently. We tried to make clear constant exercise according to exercise intensity would have effect on sleep disorder in elderly using EEG and melatonin. Methods : Thirty subjects were over 65 years old who lived a senior facility in some parts. They were able to communicate and understand the purpose of the study. They also expressed their intension to participate actively in experiment. They should have alert consciousness and orientation about time, place, and people. Sleep disorder was assessed via below 6 hr total sleep time and Pittsburge Sleep Quality Index, which was satisfied with both of criterion at the same time. Exercises composed of low intensity walking, moderate aerobic exercise, and high intensity resistance strength. We used QEEG 8-System (LAXTHA Inc. KOREA) to check wave type and Polysomnograpy (Compumedics, Australia) to test quality of sleep. and Histologic features were observed by TTC (triphenyltetrazolium chloride) staining and H & E (Hematoxylin & Eosin) staining. Results : There was a significant sleep index and change of melatonin after aerobic exercise. There was a significant SOL, S1, S2, and SWS in aerobic exercise, but there was a significant SWS in walking and resistance strength. There was a significant change of delta wave especially in frontal and temporal region between exercises. Conclusion : They had different effects according to type of exercise, when elderly who have chemical, behavioral change of circadian rhythms did exercise consistently. Aerobic exercise had more effect on sleep disorder than other exercise. Therefore, we may supply proper exercise to elderly and high quality of life.

• Korean Journal of Veterinary Research
• /
• v.16 no.2
• /
• pp.121-129
• /
• 1976

실혈견(失血犬)에 있어서 염산(鹽酸)케타민 전신마취(全身麻醉)가 심전도(心電圖), 뇌파(腦波) 및 혈압(血壓)에 미치는 영향(影響)을 조사(調査)하였던 바 그 성적(成積)은 다음과 같았다. 심전도소견(心電圖所見)에 있어서는 동성빈맥(洞性頻脈)이 지속(持續)되었으나 심장조율(心臟調律)에는 특이(特異)한 변화(變化)가 나타나지 아니 하였다. 그러나 건강견(健康犬)에 있어서 염산(鹽酸)케타민 마취군(麻醉群)과 비교(比較)해서 파형(波形)의 변화(變化)와 S-T분절(分節)의 편위(偏位)가 경미(輕微)하게 있었으며 P-Q와 Q-T 간격(間隔)은 상대적(相對的)으로 다소(多少) 연장(延長) 되었다. 뇌파(腦波)는 건강견(健康犬)에 있어서의 염산(鹽酸)케타민 마취군(麻醉群)과 유사(類似)한 양상(樣相)을 보였으나, 그 진폭(振幅)은 약간 감소(減少)되었다. 혈압(血壓)은 마취후(麻醉後) 약간 하락(下落)되었으나 곧 마취전(麻醉前)으로 회복(恢復)되었으며, 악화(惡化)되지는 아니하였다.

• Journal of Convergence for Information Technology
• /
• v.9 no.12
• /
• pp.8-16
• /
• 2019

Customized sleep care service needs to be provided differently for individuals since individual has different degree of sleep disorder. Because the brainwave data shows unique waveform characteristics for each person, this characteristic can be used to identify individuals. Personal identification provides an important role in enabling customized services. When you blink, you can obtain brain wave characteristics by measuring the area of the frontal lobe. Therefore, a real-time personal identification algorithm based on blinking EOG for customized sleep care service is proposed in this paper. For evaluation, 10 individuals were tested for personal identification accuracy. The results of the experiment confirmed that a maximum accuracy of 93% were taken. Algorithms can be developed by reflecting characteristics such as changes in the external environment in the future.

• Korean Journal of Clinical Laboratory Science
• /
• v.36 no.1
• /
• pp.64-68
• /
• 2004

Brain death is defined as the irreversible cessation of all brain function. The diagnosis of brain death is primarily based on a careful neurological examination demonstrating unresponsiveness, absent of brain stem reflexes, and no respiratory activity. Several conditions which may mimic brain death must be excluded. In some cases investigations such as electroencephalography, angiography, transcranial doppler or evoked potentials can contribute to the diagnosis. The brief review will introduce medical technologist and clinician to the key issues in the definition and management of brain death.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.281-283
• /
• 1993

A new method of EEG spindle waveform detection i s presented. The method combines the signal conditioning in the time-domin and the analysis of local spectrum in the frequency-domain. Fast computation methods, utilizing some effective approximations, are also suggested for the desist and implementation of the filter as well as for the computation of the local spectrum. The presented approach is especially useful for the real-time implementation of the waveform detection system under a general purpose microcomputer environment. The overall detection system is implemented and tested on-line with the total 24 hour data of selected four subjects. The result show the average agreement of 86.7% with the visually inspected result.

• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.27-36
• /
• 2019

In this study, experiments on the improvement of the emotion classification, analysis and accuracy of EEG data were proceeded, which applied DEAP (a Database for Emotion Analysis using Physiological signals) dataset. In the experiment, total 32 of EEG channel data measured from 32 of subjects were applied. In pre-processing step, 256Hz sampling tasks of the EEG data were conducted, each wave range of the frequency (Hz); Theta, Slow-alpha, Alpha, Beta and Gamma were then extracted by using Finite Impulse Response Filter. After the extracted data were classified through Time-frequency transform, the data were purified through Independent Component Analysis to delete artifacts. The purified data were converted into CSV file format in order to conduct experiments of Machine learning algorithm and Arousal-Valence plane was used in the criteria of the emotion classification. The emotions were categorized into three-sections; 'Positive', 'Negative' and 'Neutral' meaning the tranquil (neutral) emotional condition. Data of 'Neutral' condition were classified by using Cz(Central zero) channel configured as Reference channel. To enhance the accuracy ratio, the experiment was performed by applying the attributes selected by ASC(Attribute Selected Classifier). In "Arousal" sector, the accuracy of this study's experiments was higher at "32.48%" than Koelstra's results. And the result of ASC showed higher accuracy at "8.13%" compare to the Liu's results in "Valence". In the experiment of Random Forest Classifier adapting ASC to improve accuracy, the higher accuracy rate at "2.68%" was confirmed than Total mean as the criterion compare to the existing researches.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.179-186
• /
• 2010

The present study is a partial extension of the Duncan-Johnson and Donchin (1979) and Soskins, Rosenfeld, and Niendam (2001) studies that found some effects of high pass filter (HPF) setting on P300 waveform. EEGs were recorded while the subjects performed a visual three-stimulus oddball task, and the Fz and Pz EEG signals were passed through 0.01 Hz, 0.3 Hz, and 1.0 Hz HPFs. P300 amplitudes at Fz and Pz were reduced at 1.0 Hz HPF compared to 0.01 Hz and 0.3 Hz HPFs. The negative peaks post P300 at Fz and Pz were not observed at 0.01 Hz HPF, but observed at 0.3 Hz and 1.0 Hz HPFs. The combination of 0.3 Hz HPF and peak-to-peak P300 measures was more useful than that of 0.01 Hz, 0.3 Hz, or 1.0 Hz HPF and baseline-to-peak P300 measures to discriminate between non-target and standard stimuli. The peak-to-peak P300 measures were more useful than the baseline-topeak P300 measures at 1.0 Hz HPF setting.

• Korean Journal of Clinical Laboratory Science
• /
• v.48 no.2
• /
• pp.144-152
• /
• 2016

Carotid-artery stenosis may reduce cerebral perfusion, and affect cerebral neuronal activities. We examined the question of whether the recovery of cerebral-perfusion reserve after carotid-artery stenting (CAS) can affect the EEG power-spectrum. Nineteen candidates for CAS were initially recruited. Subtraction imaging of single photon emissary computerized tomography (SPECT) and an electroencephalogram (EEG) were taken twice, before and 1 month after CAS. At each time point, the EEGs were recorded before and after injection of acetazolamide (pre-ACZ EEG and post-ACZ EEG). Finally, 7 patients were enrolled after exclusion of incomplete studies. We obtained the spectral ratio (SR) of each hemisphere. SR was defined as the divided value of the power-spectrum sum of fast activities by that of slow activities. The power-spectrum values between hemispheres were compared using the inter-hemispheric index of spectral ratio (IHISR), and we examined the correlation between the power-spectrum and the cerebral-perfusion reserve. Cerebral-perfusion reserve improved after CAS on the stent side in 6 of 7 patients. In 3 patients with unilateral carotid-artery stenosis, CAS increased SR on the pre-ACZ EEGs, and IHISR on the post-ACZ EEGs. The increases of SR and IHISR were concordant with the increment of cerebral-perfusion reserve. In contrast, the results in the other patients with bilateral stenosis showed complex patterns. The SR of pre-ACZ EEGs and IHISR of post-ACZ EEGs may be useful electrophysiological markers for the blood-flow reserve after CAS in patients with unilateral carotid-artery stenosis, but not in those with bilateral stenosis.