• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.8
• /
• pp.3925-3932
• /
• 2013

Emotion is closely related to the life of human, so has effect on many parts such as concentration, learning ability, etc. and makes to have different behavior patterns. The purpose of this paper is to extract important features based on physiological signals to recognize negative emotion. In this paper, after acquisition of electrocardiography(ECG), electroencephalography(EEG), skin temperature(SKT) and galvanic skin response(GSR) measurements based on physiological signals, we designed an accurate and fast algorithm using combination of linear discriminant analysis(LDA) and genetic algorithm(GA), then we selected important features. As a result, the accuracy of the algorithm is up to 96.4% and selected features are Mean, root mean square successive difference(RMSSD), NN intervals differing more than 50ms(NN50) of heart rate variability(HRV), ${\sigma}$ and ${\alpha}$ frequency power of EEG from frontal region, ${\alpha}$, ${\beta}$, and ${\gamma}$ frequency power of EEG from central region, and mean and standard deviation of SKT. Therefore, the features play an important role to recognize negative emotion.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.905-910
• /
• 2022

Drowsy driving requires a lot of social attention because it increases the incidence of traffic accidents and leads to fatal accidents. The number of accidents caused by drowsy driving is increasing every year. Therefore, in order to solve this problem all over the world, research for measuring various biosignals is being conducted. Among them, this paper focuses on non-contact biosignal analysis. Various noises such as engine, tire, and body vibrations are generated in a running vehicle. To measure the driver's heart rate and respiration rate in a driving vehicle with a piezoelectric sensor, a sensor plate that can cushion vehicle vibrations was designed and noise generated from the vehicle was reduced. In addition, we developed a system for classifying whether the driver is sleeping or not by extracting the model using the CNN-LSTM ensemble learning technique based on the signal of the piezoelectric sensor. In order to learn the sleep state, the subject's biosignals were acquired every 30 seconds, and 797 pieces of data were comparatively analyzed.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.502-505
• /
• 2019

노인들이 많이 이용하는 이동 보조 기구인 기존 보행기에 다양한 기능이 부족하여 안전 서비스, 알림 서비스, 스마트폰 애플리케이션 서비스로 분류하여 기능을 추가하였다. 안전 서비스 부문의 기능으로는 경사로 사고 방지 시스템, 장애물 알림 시스템, 밝기에 따른 전조등 시스템, 손잡이에서 손이 떨어지면 자동으로 동작되는 브레이크 시스템, 겨울철 손을 따뜻하게 유지하기 위한 난방 시스템이 있다. 알림 서비스로는 현재의 온·습도 및 미세먼지 농도를 알려준 후 외출하기에 부적합할 시 경고등으로 알려주는 시스템이 있다. 스마트폰 애플리케이션 서비스는 심박 및 체온을 알려주고, 노인의 위치와 SOS신호, 운동량을 알 수 있고, 도난 방지 시스템이 있는 스마트 안전 노인 보행기를 설계하였다.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.90-98
• /
• 2018

A Multilinear LDA Method of Tensor Representation for ECG Signal Based Individual Identification Electrocardiogram signals, included in the cardiac electrical activity, are often analyzed and used for various purposes such as heart rate measurement, heartbeat rhythm test, heart abnormality diagnosis, emotion recognition and biometrics. The objective of this paper is to perform individual identification operation based on Multilinear Linear Discriminant Analysis (MLDA) with the tensor feature. The MLDA can solve dimensional aspects of classification problems in high-dimensional tensor, and correlated subspaces can be used to distinguish between different classes. In order to evaluate the performance, we used MPhysionet's MIT-BIH database. The experimental results on this database showed that the individual identification by MLDA outperformed that by PCA and LDA.

• Journal of Chest Surgery
• /
• v.31 no.11
• /
• pp.1031-1036
• /
• 1998

Background: Medtronic-Hall mechanical valve is a world widely using prosthesis. But, in Korea, the clinical result from Medtronic-Hall valve replacement is not frequenthy available. Materials and methods: From March 1986 to May 1990, 50 patients underwent valve replacement surgery with Medtronic-Hall valve at Pusan National University Hospital. Seventeen were male and thirty three were female and ra nging in age from 16 to 70 years of age(mean=35 years). Results: The causes of valvular lesion were rheumatic in 43 patients, bicuspid aortic valve in 3 patients, degenerative lesion in three patients and bacterial endocarditis in one patient. The operative procedures were mitral valve replacement(MVR) in 38, aortic valve replacement(AVR) in 5 and double valve replacement(DVR) in 7. The most commonly used valve size was 21mm in AVR, 29mm in MVR. Concomitant surgical procedures were performed in 15 patients; left atrial thrombectomy in 9, left atrial auricle obliteration in 6 and tricuspid annuloplasty in 5(Kay: 2, DeVega: 3). New York Heart Association functional class was mostly Class Ⅲ or Ⅳ(91.5%) preoperatively and ClassⅠor Ⅱ(87.2%) after operation. The findings of postoperative echocardiogram of LAD, LVESD, LVEDD were reduced compared with preoperative period and ejection fraction was increased compared with preoperative period. Postoperative complications were massive bleeding in three, low cardiac output syndrome in two, thromboembolism in one and fulminant hepatitis in one patient. There were three hospital deaths and their causes were low cardiac output syndrome in two and rupture of left ventricle in one patient. The 5 year survival rate was 93.65±0.71% and 10 year actuarial survival rate was 88.27±6.42%. Conclusions: Medtronic-Hall mechanical valve has low valve related complication rate. It's durability and hemodynamic performance is comparable to other mechanical valves.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.73-77
• /
• 1996

정보는 의사결정자들의 수주에 있을 때 기업에 있어 강력한 경쟁무기가 된다. 의사결정자들의 정보에 대한 이러한 필요성을 충족시키기 위해서 데이타는 운영시스템(Operational System)에서 추출되어 데이타웨어하우스에 저장된다. 데이타웨어하우스는 핵심 비지니스영역(key business dimension)에 의해 정리된 historical data를 저장한다. 이러한 의사결정자들을 위한 데이타웨어하우스 정보의 전달은 기존의 클라이언트/서버 시스템 하에서는 많은 지원을 요구한다. 즉 기존 클라이언트/서버 시스템 하에서는 사용자들의 접근을 위해 데이타가 추출되고 조직화되어지고 나면, 반드시 분석 소프트웨어가 각 사용자의 컴퓨터에 설치되어야 하고 외부의 사용자를 위한 새로운 운영자가 고용되어야 한다. 사용자의 다양한 요구 그리고 계속적 사용자의 교체는 사용자 지원에 있어 심각한 기업부담으로 작용한다. 또한 클라이언트/서버 시스템에서는 기업외부의 정보 이용자들에게 정보를 제공하는데 있어 장소적 한계점을 가지고 잇다. 인트라넷과 인터넷은 이러한 클라이언트/서버 시스템 환경의 문제에 대해 해답을 제시한다. 인트라넷은 데이타웨어하우스로의 접근을 간단히 할뿐만 아니라 의사결정자들의 정보의 공유와 상호분석의 새로운 단계를 제공한다. 그리고 인터넷은 기업 외부 어디에서나 기업이 제공하는 정보를 이용하고자 하는 사람들에게 접근의 편의성을 제공한다. 즉 데이타웨어하우스의 목표와 인트라넷, 인터넷의 목표는 데이타로의 손쉬운 접근이라는 점에서 동일하다. 이러한 점에 착안하여 인트라넷과 인터넷하에서 운용되는 데이타웨어하우스 시스템 구축을 위한 방안을 제시하고자 한다.다(학생군:8.16kg 작업자군:12.9kg). 심박수를 이용한 생리학적 연구에서는 평균 심박수가 거의 100 이하를 유지하므로써 피실험자들이 8시간 작업기준으로 보아 무리가 없는 최대허용 하중을 결정하였음을 보였다. 또한 각 운반작업에 대한 최대허용 하중을 예측하는 회귀모형을 제시하였다.아직 정립되어 있지 않은 분산 환경하에서의 관계형 데이타베이스의 데이타관리의 분류체계를 나름대로 정립하였다는데 그 의의가 있다. 또한 이것의 응용은 현재 분산데이타베이스 구축에 있어 나타나는 기술적인 문제점들을 어느정도 보완할 수 있다는 점에서 그 중요성이 있다.ence of a small(IxEpc),hot(Tex> SOK) core which contains two tempegatlue peaks at -15" east and north of MDS. The column density of HCaN is (1-3):n1014cm-2. Column density at distant position from MD5 is larger than that in the (:entral region. We have deduced that this hot-core has a mass of 10sR1 which i:s about an order of magnitude larger those obtained by previous studies.previous studies.업순서들의 상관관계를 고려하여 보다 개선된 해를 구하기 위한 연구가 요구된다. 또한, 준비작업비용을 발생시키는 작업장의 작업순서결정에 대해서도 연구를 행하여, 보완작업비용과 준비비용을 고려한 GMMAL 작업순서문제를 해

• Journal of the korean academy of Pediatric Dentistry
• /
• v.27 no.2
• /
• pp.283-291
• /
• 2000

The purpose of this study was to compare the sedative effect of three routes of administration - intramuscular, intranasal drop-in, intranasal spray - with midazolam. The twenty two uncooperative children from 23 months to 76 months who required at least three dental appointment. Each patient was assigned randomly to receive intramuscular(Group I, 0.15mg/kg), intranasal drop-in(Group II, 0.20mg/kg), intranasal spray(Group III, 0.20mg/kg) administration at each visit. Sleep, crying, movement, and overall behavior response were evaluated, and the sedative effects were evaluated by Houpt's rating scale In order to monitor the sedated patients, pulse rate and peripheral oxygen saturation were measured by pulse oximeter during treatment procedures. The results were as follows 1. Pulse rate and peripheral oxygen saturation were stable through all the treatment procedures, and there were no statistically significant differences among three routes of administration(P>0.05). 2. The effect on sleep was, III, II, I, in order, III group was the most effective through all the treatment procedures, except rubber-dam placement and filling phase (P<0.0001). 3. The effects on crying, movement, overall behavior were II, III, I, in order, II group was the most effective through all treatment procedures(P<0.0001).

• Journal of Chest Surgery
• /
• v.31 no.1
• /
• pp.13-19
• /
• 1998

Aortic aneurysm has poor prognosis and high mortality, but the incidence of aortic aneurysm is in increasing state. From July, 1986 to July, 1996, we operated on 25 patients with aortic aneurysm and analysed the clinical results and relations between the duration from symptoms onset to operation(Sx-Op), the duration from admission to operation(Adm-Op), preoperative blood pressure, preoperative heart rate and postoperative mortality, retrospectively. The patients were classified as dissecting aneurysm(10 cases), abdominal aortic aneurysm(9 cases), Marfan's syndrome(3 cases), descending thoracic aortic aneurysm(3 cases). The operative technique were graft interposition in 17 cases, Bentall's operation in 4 cases, aneurysm bypass in 2 cases, and wrapping of aorta in 2 cases. Seven patients died of several causes, bleeding in 5 cases, acute renal failure in 1 case and respiratory failure in another one case. Before 1992, the early stage of operation, 6 mortality among 14 operated patients occurred, and after then 1 mortality among 11 operated patients occurred. Eighteen survivors were followed up from 1 to 118 months(mean 50.6 months), and total follow up was 911 patient-months. During the follow up period one patient died of melena 30 months after operation. The other patients did not complain chest pain or dyspnea. The surgical mortality was improved in the late period, and the major cause of death was intraoperative or postoperative bleeding. The Sx-Op duration, the Adm-Op duration, preoperative blood pressure and preoperative heart rate were proven to have no statistical relations with postoperative mortality.

• Korean Journal of Clinical Laboratory Science
• /
• v.50 no.2
• /
• pp.136-143
• /
• 2018

The rate pressure product (RPP) is expressed as a product of the heart rate and systolic blood pressure as an index indirectly measuring the myocardial oxygen consumption, and it indicates the burden on the myocardium. The aim of this study was to determine the optimal level of RPP for preventing metabolic syndrome in a treadmill exercise test in Korean adults. Metabolic syndrome was the diagnosis of the third executive summary report on the National Cholesterol Education Program Adult Treatment Panel III (NCEP-ATP III) criteria. According to the criteria, the metabolic syndrome diagnosis group (MetS, N=25), pre-metabolic syndrome group (Pre-MetS, N=106), and non-risk factor group (Non-MetS, N=65) were classified. The exercise stress test was performed based on the Bruce protocol. The RPP was calculated as (heart rate${\times}$systolic blood pressure)${\div}1,000$. The results showed that the maximum systolic blood pressure was high despite the low daily dose reached in the diagnostic group of metabolic syndrome. The optimal threshold of the RPP at the time of the exercise treadmill test for a metabolic syndrome prediction was $12.56mmHg{\times}beats/min{\times}10^{-3}$ in the first stage of the exercise stress test. The second stage of the exercise test was $16.94mmHg{\times}beats/min{\times}10^{-3}$, and at the third stage of the exercise test was $21.11mmHg{\times}beats/min{\times}10^{-3}$.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.414-421
• /
• 2015

This paper presents a new method to decompose a duplicated ECG signal, which is measured from two people, to two individual ECG signals. In paper, it is shown that the duplicated ECG signal can be decomposed, provided that their SAECG signals are known. As the SAECG signal is the average of a ECG signal, it is a feature to identify individual ECG signals from the duplicated signal. Since the ECG signal is nearly periodic, so-called heart-rate, the period of each ECG signal can be found by using the autocorrelation of the duplicated signal, That is, the autocorrelation has high peaks at the multiple instants of heart-rate of each person. With the heart-rate of each person obtained by some processing, all R-peaks are identified by the SAECG signals. To be concrete, the SAECG signal of each person is repeatedly placed at the R-peak instants with his heart-rate, and the weight of each SAECG signal is computed by LMSE optimization. Finally, as adding the error signal in the LMSE optimization processing to the weighted SAECG signal, each individual ECG signal is obtained. In experimental results, we demonstrate that the duplicated ECG signal is successfully decomposed into two ECG signals.