• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1807-1808
• /
• 2007

본 연구에서는 반도체 플라즈마 공정감시와 제어에 응용될 수 있는 모델을 제안한다. 본 모델은 광반사분광기(OES)정보와 신경망을 이용해서 개발하였으며, OES의 차수를 줄이기 위해 주인자 분석을 세 종류의 분산 (100, 99, 98%)에 대해서 적용하였다. 모델의 예측성능은 유전자 알고리즘을 이용하여 최적화하였다. 제안하는 모델링 방식은 MERIE를 이용한 Oxide 식각공정에 적용하였으며, 개발된 모델은 발표된 이전의 모델에 비해 증진된 예측성능을 보였다.

• Journal of Clinical Otolaryngology Head and Neck Surgery
• /
• v.29 no.2
• /
• pp.157-161
• /
• 2018

• Korean Journal of Clinical Laboratory Science
• /
• v.52 no.4
• /
• pp.317-326
• /
• 2020

Deep blocking of consciousness alone does not prevent a reaction to severe stimuli, and copious amounts of pain medication do not guarantee unconsciousness. Therefore, anesthesia must satisfy both: the loss of consciousness as well as muscle relaxation. Muscle relaxants improve the intra-bronchial intubation, surgical field of vision, and operating conditions, while simultaneously reducing the dose of inhalation or intravenous anesthesia. Muscle relaxants are also very important for breathing management during controlled mechanical ventilation during surgery. Excessive dosage of such muscle relaxants may therefore affect neurological examinations during surgery, but an insufficient dosage will result in movement of the patient during the procedure. Hence, muscle relaxation anesthesia depth and neurophysiological monitoring during surgery are closely related. Using excessive muscle relaxants is disadvantageous, since neurophysiological examinations during surgery could be hindered, and eliminating the effects of complete muscle relaxation after surgery is challenging. In the operation of neurophysiological monitoring during the operation, the anesthesiologist administers muscle relaxant based on what standard, it is hoped that the examination will be performed more smoothly by examining the trends in the world as well as domestic and global trends in maintaining muscle relaxant.

• Korean Journal of Clinical Laboratory Science
• /
• v.53 no.1
• /
• pp.122-130
• /
• 2021

The types of artifacts that are observed in intraoperative neurophysiological monitoring (INM) is truly diverse. The removal of artifacts that interfere with the examination is essential. In addition, improving the quality of the examination by removing artifacts is a reflection of the competency of the examiner and is also the best way to ensure patient safety. However, if knowledge of the equipment or anesthesia in the operating room is insufficient due to lack of experience, artifacts cannot be removed even with a method appropriate to the situation. If artifacts are not separated and removed, the reading of the examination results in confusion in the operation process. This can be a fatal problem in neurosurgery that requires rapid and sophisticated procedures. In this paper, the causes of artifacts that occur during surgery are classified into electrical factors, non-electrical factors, and other factors, and a method and examination method for removing artifacts according to the specific situation is mentioned. Although the operating room environment is a very critical place to simultaneously consider various scenarios, we hope that a stable and optimal INM will play a role by knowing the types and causes of various artifacts and how to tackle them.

• Journal of Convergence for Information Technology
• /
• v.7 no.6
• /
• pp.201-207
• /
• 2017

Failure of the power apparatus causes many inconveniences and problems due to power outage in all places using power such as industry and home. The main causes of faults in the Power Apparatus are aging, natural disasters such as typhoons and earthquakes, and animals. At present, the long high temperature status is monitored only by the assumption that a fault occurs when the temperature of the power apparatus becomes higher. Therefore, it is difficult to cope with the failure of the power apparatus at the right time. In this paper, we propose a power apparatus monitoring system as an efficient countermeasure against general faults except for faults caused by sudden natural disasters. The proposed monitoring system monitors the power apparatus in real time by attaching a thermal sensor, collects the monitored data, and predicts the failure using the accumulated information through learning using the artificial neural network. Through the learning and experimentation of artificial neural network, it is shown that the proposed method is efficient.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2001.10a
• /
• pp.102.2-102
• /
• 2001

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.1 s.94
• /
• pp.53-62
• /
• 2005

This study presents the NDE (non-destructive evaluation) technique for detecting the loosened bolts on joint steel structures on the basis of TOF (time of flight) and amplitudes of Lamb waves. Probabilistic neural network (PNN) technique which is an effective tool for pattern classification problem was applied to the damage estimation using PZT induced Lamb waves. Two kinds of damages were introduced by dominant damages (DD) which mean loosened bolts within the Lamb waves beam width and minor damages (MD) which mean loosened bolts out of the Lamb waves beam width. They were investigated for the establishment of the optimal decision boundaries which divide each damage class's region including the intact class. In this study, the applicability of the probabilistic neural networks was identified through the test results for the damage cases within and out of wave beam path. It has been found that the present methods are very efficient and reasonable in predicting the loosened bolts on the joint steel structures probabilistically.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.625-632
• /
• 2004

This study presents the NDE (non-destructive evaluation) technique for detecting the loosened bolts on joint steel structures on the basis of TOF (time of flight) and amplitudes of Lamb waves. Probabilistic neural network (PNN) technique which is an effective tool for pattern classification problem was applied to the damage estimation using PZT induced Lamb waves. Two kinds of damages were introduced by dominant damages (DD) which mean loosened bolts within the Lamb waves beam width and minor damages (MD) which mean loosened bolts out of the Lamb waves beam width. They were investigated for the establishment of the optimal decision boundaries which divide each damage class's region including the intact class. In this study, the applicability of the probabilistic neural networks was identified through the test results for the damage cases within and out of wave beam path. It has been found that the present methods are very efficient and reasonable in predicting the loosened bolts on the joint steel structures probabilistically.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.706-712
• /
• 2009

In this paper, a fault diagnosis method is proposed to detect and classifies faults that occur in press process line. An oil level automatic monitoring method is also presented to detect oil level. The FFT(fast fourier transform) frequency analysis and ART2 NN(adaptive resonance theory 2 neural network) with uneven vigilance parameters are used to achieve fault diagnosis in proposing method, and GUI(graphical user interface) program for fault diagnosis and oil level automatic monitoring using LabVIEW is produced and fault diagnosis was done. The experiment results demonstrate the effectiveness of the proposed fault diagnosis method of induction motors and oil level automatic monitor system.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2663-2665
• /
• 2001

역전파 신경망은 반도체 공정 모델링에 효과적으로 응용이 되고 있으며, 최근 선형뉴런을 비선형 함수 대신 출력층에 이용하여 모델의 예측정확도를 향상 시킨 바 있다. 본 연구에서는 그 원인을 규명하기 위한 모델의 평가지표로서의 유클리디언 웨이트 거리(Euclidean Weight Distance)를 제안한다. 이 지표를 이용하여 신경망의 입력층과 은닉층, 그리고 은닉층과 출력층의 웨이트를 감시하였으며, 그 결과 예측정확도의 향상이 이 지표의 감소에 기인하고 있음을 알았다. 모델링에 이용한 실험데이터는 다중 유도결합형 플라즈마 장비로부터 Langmuir Probe 진단 시스템을 이용하여 수집하였다.