• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.53-56
• /
• 1998

본 논문에서의 공학적인 체계성을 갖고 초기 연결 가중치 및 임계치를 결정해 주면서, 학습까지 가능한 신경망을 제안한다. 기존의 오류 역전파 신경망을 적용할 때 경험에 의하여 은닉층 노드수를 결정하거나 임의의 실수 값으로 초기 연결 가중치 및 임계값을 주었을 때 자주 발생하는 학습 마비 현상을 피할 수 있고, Bose가 제안된 Voronoi 공간 분류에 의한 신경망 구성에서 학습이 불가능하다는 제안적인 단점을 보안하였다. 초기 가중치는 Voronoi 공간 분류가 이루어져 있다고 할 때 Bose가 제안한 초기 가중치 결정법을 개선하여 사용하고, Bose의 경우 신경망 노드가 Step function을 이용하여 정보를 전달하였으나 본 연구에서는 학습이 가능한 함수인 Sigmoid function을 이용하였다. 제안된 새로운 신경망의 성능 및 효율성을 비교하기 위하여 선형분리가 불가능한 XOR문제를 실험한 결과, 기존의 학습 가능한 EBP에서 허용오차 0.05 수준일 때 80%정도 학습마비 현상이 발생하였던 심각한 문제점을 보완할 수 있었고, 또한 학습 속도면에서 8~9배 정도 빠른 성능을 나타내었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.540-540
• /
• 2015

유역의 하천관리 및 홍수관리를 위하여 강우량을 정확하게 예측하고자 많은 수문학자들에 의해 강우량을 예측하는 연구를 진행하였다. 강우를 예측하기 위한 여러 가지 방법 중 인공신경망을 이용하여 강우를 예측하는 선행연구들을 살펴볼 수 있었다. 그러나 기존에 강우량을 예측하는 사례들을 살펴보게 되면, 강우사상이 발생된 후 강우량 예측은 비교적 높은 정확도를 가지고 있으나, 강우가 발생하기 시작하는 시점에 대한 강우량 예측은 그 정확성이 떨어지는 것을 확인할 수 있었다. 이에 본 연구에서는 무강우 기간에도 보다 정확하게 강우량을 예측할 수 있는 인공신경망 모델을 제안하고자 한다. 이를 위해 강우량 이외에도 기온, 풍속, 습도, 증기압, 전운량을 인공신경망의 입력자료로 활용하고자 하였다. 입력자료을 구성을 여러 가지 CASE로 구분하여 부산지점의 강우량을 예측하고 그 정확성을 평가하고자 하였다. 이 때, 사용되는 자료는 기상청 부산지점에서 제공하고 있는 1시간 간격자료를 적용하였다. 본 연구를 통해 개발된 인공신경망 모형을 이용하여 예측된 강우량은 부산 내에 위치한 하천관리 뿐 만 아니라 하천의 홍수 예 경보에 필요한 기초적인 자료로 활용될 수 있을 것으로 판단된다.

• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.1 no.2
• /
• pp.128-133
• /
• 2008

Nerve compression is caused by external force or internal pathology, which symptom develops along nerve distribution. There are median, ulnar and radial nerve compression neuropathies below elbow. Carpal tunnel syndrome at the flexor retinaculum is most common among all the entrapment neuropathies. Other causes of median nerve neuropathy include Struther's ligament, biceps aponeurosis, pronator teres, FDS aponeurosis and aberrant muscles, which induce pronator syndrome or anterior interosseous nerve syndrome. Ulnar nerve can be compressed at the elbow by arcade of Struther, medial epicondylar groove, FCU two heads, which develops cubital tunnel syndrome, at the wrist by ganglion, fracture of hamate hook and vascular problem, which develops Guyon's canal syndrome. Radial tunnel syndrome is caused by supinator muscle, which compresses its deep branch. Treatment is conservative at initial stage like NSAID, night splint or steroid injection. If symptom persists, operative treatment should be considered after electrodiagnostic or imaging studies.

• Archives of Hand and Microsurgery
• /
• v.23 no.4
• /
• pp.267-270
• /
• 2018

Recurrent motor branch entrapment syndrome is a compressive mononeuropathy of recurrent motor branch of median nerve. It is a rare condition as a cause of thenar muscle wasting and may have different pathogenesis. If such an anatomical variation is the cause, there is a possibility that thenar muscle atrophy remains if only the transcarpal ligament release is performed. We report a 25-year-old male patient with carpal tunnel syndrome with thenar muscle wasting 1 month ago.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.302-310
• /
• 2010

In this paper, we studied Bagging neural network for predicting defect size of steam generator(SG) tube in nuclear power plant. Bagging is a method for creating an ensemble of estimator based on bootstrap sampling. For predicting defect size of SG tube, we first generated eddy current testing signals for 4 defect patterns of SG tube with various widths and depths. Then, we constructed single neural network(SNN) and Bagging neural network(BNN) to estimate width and depth of each defect. The estimation performance of SNN and BNN were measured by means of peak error. According to our experiment result, average peak error of SNN and BNN for estimating defect depth were 0.117 and 0.089mm, respectively. Also, in the case of estimating defect width, average peak error of SNN and BNN were 0.494 and 0.306mm, respectively. This shows that the estimation performance of BNN is superior to that of SNN.

• Applied Microscopy
• /
• v.42 no.2
• /
• pp.77-86
• /
• 2012

The morphological and histologic differentiation of the central nervous system (CNS) in the wolf spider Arctosa kwangreungensis with respect to postembryonic development are studied using light and scanning electron microscopes. The organization of CNS which consisted of supraesophageal ganglion (SpG) and subesophageal ganglion (SbG) are established prior to the postembryo stage. The brain of first instar spiderling after a molt of the postembryo is also made up of supraesophageal ganglion and subesophageal ganglion. Although development of the optic nerve and optic lobe in SpG are not completed during the postembryoic stage, completion of whole neural system resemble to that of adult are established during the second instar stage. In particular, optic gangalion is developed from the undifferentiated cell clusters of the SpG, moreover four pairs of appendage ganglia and another pairs of abdominal ganglia are produced from the SbG. Nerve cells of the most developing stages are composed of typical monopolar neur1ons, and total three types of neurons can be identified through the histological and morphological basis of present study. These cell clusters are differentiated into neurons and grow dendritic fibers according to further development of the CNS.

• Journal of Chest Surgery
• /
• v.41 no.6
• /
• pp.807-810
• /
• 2008

From October 2005 to August 2006, sympathetic nerve reconstruction with using the intercostal nerve was performed in 4 patients with severe compensatory hyperhidrosis following thoracoscopic sympathetic surgery for facial hyperhidrosis. The interval between the initial sympathetic clipping and the sympathetic nerve reconstruction was a median of 23.1 months. The compensatory sweating after sympathetic nerve reconstruction was improved for 2 patients, but it was not improved for 2 patients. Thoracoscopic sympathetic nerve reconstruction may be one of the useful treatment methods for the patients with severe compensatory hyperhidrosis after they under go sympathetic nerve surgery for hyperhidrosis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.380-384
• /
• 2010

기후온난화, 국지성 호우 및 대규모 태풍으로 인한 피해가 증대되면서 사회 경제적 손실 또한 날로 증가하고 있어 재해로 인한 피해 발생가능성을 효율적으로 예측하는 모델을 통한 선제적 대응이 필요하다. 재난 재해의 위험성 분석 방법은 주로 확률 통계기법을 기반으로 하는 연구가 주류를 이루었으나, 본 논문에서는 포착된 현상의 데이터를 이용해 그 데이터를 지배하는 경험적 규칙성을 학습하고 획득하는데 다른 기법보다 탁월한 성능을 가진 신경망 모델을 적용하여 자연재해 피해예측 모델을 연구하였다. 1991년부터 2005년 사이에 우리나라에서 발생한 자연재해의 피해자료와 기상개황 자료를 이용하여 지역별 자연재해로 인한 피해를 예측하는 신경망 모델은 우리나라 232개 행정구역에 대하여 누적강우량과 최대풍속, 그리고 재해사상 발생 5일 이내의 선행강우량을 입력변수로 하고 총 피해액을 출력변수로 한다. 또한 학습을 통한 최적의 해를 찾기 위해 신경망의 매개변수 학습률, 모멘텀, 편의값을 유전자알고리즘으로 결정하여 학습을 수행 하였다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

• Journal of Chest Surgery
• /
• v.32 no.9
• /
• pp.813-817
• /
• 1999

Background: Conventional thoracoscopic thoracic sympathectomy or sympathicotomy is an effective method in treating localized hyperhidrosis; however, this may result in a postoperatively embarrassing compensatory hyperhidrosis or facial anhidrosis in the treatment of palmar hyperhidrosis. We modified the conventional sympathicotomy by limiting the extent of nerve transection. The purpose of this study was to assess the result of the limited thoracoscopic sympathetic nerve transection in hyperhidrosis. Material and Method: From May to August 1998, 17 patients underwent limited transection of the sympathetic nerve. For 9 patients with facial hyperhidrosis, we transected only the interganglionic fiber between the first and the second ganglion, whereas the conventional method cuts two interganglionic fibers. Eight patients with palmar hyperhidrosis underwent limited transection of the interganglionic fiber between the second and third ganglion. Result: Sixteen patients had improved symptom postoperatively. There was a recurred facial sweating in 1 patient 1 month after the operation. Among the 9 facial hyperhidrosis patients, postoperative compensatory hyperhidrosis was severe in 4, moderate in 4 and minimal in 1. But in 8 cases of palmar hyperhidrosis compensatory hyperhidrosis was moderate in 3, and minimal in 1, none in 4. Facial sweating was not disturbed postoperatively in all of the palmar hyperhidrosis patients. Conclusion: Limited sympathetic nerve transection is a practical and less invasive method for the treatment of localized hyperhidrosis and may reduce the incidence of compensatory truncal hyperhidrosis and facial anhidrosis in case of palmar hyperhidrosis.