• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.719-720
• /
• 2006

Ad hoc networks does not need any wired network infrastructure. Therefore, they have been developed in temporary networks or mainly in military networks. Infostations offer geographically intermittent coverage at high speeds. Up-to-date there have been frequent big forest fires in Korea mountain areas. It is very important to detect them early to prevent them from being big disasters. In this paper, we propose a disaster emergency management system using sensor attached wild boars' mobility combined with infostation system. We also make a numerical analysis of the performance of the system.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.819-820
• /
• 2006

The purpose of this study is to develop an automatic algorithm to detect the arousal events. The proposed method is based on time-frequency analysis and the support vector machine classifier using single channel electroencephalogram. To extract features, first we computed 6 indices to find out the information of sleep states. Next powers of each of 4 frequency bands were computed using spectrogram of arousal region. And finally we computed variations of power of EEG frequency to detect arousals. The performance has been assessed using polysomnographic recordings of twenty patients with sleep apnea, snoring and excessive daytime sleepiness. We have shown that proposed method was effective for detecting the arousal events.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1257-1264
• /
• 2011

Delirium is a neuropsychiatric disorder accompanying symptoms of hallucination, drowsiness, and tremors. It has high occurrence rates among elders, heart disease patients, and burn patients. It is a medical emergency associated with increased morbidity and mortality rates. That s why early detection and prevention of delirium ar significantly important. And This mental illness like delirium occurred by complex interaction between risk factors. In this paper, we identify risk factors and interactions between these factors for delirium using multi-factor dimensionality reduction (MDR) method.

• Journal of Trauma and Injury
• /
• v.27 no.3
• /
• pp.71-74
• /
• 2014

Among chest trauma patients, cardiac laceration is a rare, but severe, condition requiring prompt management. Depending on the patient's hemodynamic status, early detection rate of a cardiac laceration may or may not be occur. If a possibility of cardiac laceration exists, an emergent thoracotomy should be performed. Furthermore, patients who experience a cardiac laceration also experience different kinds of complications. Therefore, close follow-up and monitoring are required. Herein, we report a 41-year-old man with a left atrium and a left ventricle laceration caused by a thoracic stab injury.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1348-1349
• /
• 2015

본 논문에서는 응급구조의 신고 상황에서의 수보자의 보다 정확하고 신속한 대응를 위하여 수화자의 음향환경을 분석하여 주변상황에 대한 정보를 알고자 심화 신경망 기반의 음성 부재구간 검출 기법을 제안한다. 제안한 알고리즘은 음성 신호에서의 23차의 Mel-filter bank를 추출하고 이를 심화 신경망 기법을 이용하여 음성 부재구간을 검출한다. 객관적인 성능 평가를 위해 제안된 기법은 실제 응급구조 상황에서 평가되었으며, 기존의 음성검출기를 이용한 음성 부재구간 검출 성능에 비하여 향상된 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.926-928
• /
• 2015

아두이노 의 출현과 함께 소형컴퓨터를 이용한 연구가 다양해졌다. 또한 아두이노를 통해 각종 센서들을 이용해 상태를 판단하는 것을 쉽게 구현 할 수 있게 되었다. 이 연구는 아두이노에 각종 사고들이 발생 할 수 있는 증상들을 모니터링 할 수 있는 센서들을 연결하고 이를 차량에 부착하여, 센서들로부터 오는 정보를 통해 사량의 사고 유무를 판단하고 알람을 주는 시스템을 구현하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1067-1070
• /
• 2004

우리는 갈수록 지능화, 분산화, 자동화 되어 가고 있는 침입에 대해 효과적으로 대처하기 위해 신경망을 적용한 침입탐지 시스템을 설계 하였다. 본 논문은 신경망을 학습시키기 위해 학습 견본과 신경망 적용 인자를 정의 하였으며 학습 기법으론 MLP(Multi Layer Perceptron)을 이용 하였다. 새롭게 설계된 침입탐지 시스템의 탐지 모듈은 기존의 패턴 매치 방식의 모듈과 신경망 모듈이 적용되어 보다 정확한 침입 탐지가 가능하다.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.416-417
• /
• 2019

In this paper, an effective power flow control strategy (PFCS) based on the centralized control approach and a DC-link (DCV) restoration algorithm for DC microgrid (DCMG) are presented. By investigating the statuses of system power units, eleven operating modes are given to ensure the system power balance under various conditions. To avoid the system power imbalance caused by the delay of grid fault detection, a reliable DCV restoration algorithm is proposed. In the proposed scheme, when an abnormal variation of the DCV is detected, the battery instantly starts a local emergency control mode to restore the DCV to the nominal value regardless of the control mode from the central controller. The simulations and experiments are carried out to prove the effectiveness of the PFCS and the proposed DCV restoration algorithm.

• Proceedings of the PSK Conference
• /
• 2003.10b
• /
• pp.119.1-119.1
• /
• 2003

To determinate dextromethorphan (DMP) and its active metabolite dextrorphan (DRP) in urine was performed using $REMEDi^TM$ (Rapid EMErgency Drug identification) that is a fully automated multicolumn high performance liquid chromatographic (HPLC) system with a scanning ultraviolet detector. The limits of detection for DMP and DRP were 0.10 and 0.15 $\mu$g/mL, respectively. The standard curves were linear, with correlation coefficients (r ＞ 0.975) in the concentration range of 0.5~10.0 $\mu$g/mL. (omitted)

• Journal of Multimedia Information System
• /
• v.7 no.4
• /
• pp.257-262
• /
• 2020

In this paper, a method of detecting the emergency situations such as body fall is proposed by using color images. We detect body areas and key parts of a body through a pre-learned Mask R-CNN in the images captured by a camera. Then we find the centerline of the body through the joint points of both shoulders and feet. Also, we calculate an angle to the center line and then calculate the amount of change in the angle per hour. If the angle change is more than a certain value, then it is decided as a suspected fall. Also, if the suspected fall state persists for more than a certain frame, then it is determined as a fall situation. Simulation results show that the proposed method can detect body fall situation accurately.