• 대한안전경영과학회지
• /
• 제8권1호
• /
• pp.17-26
• /
• 2006

Basis frame-work's base in a semiconductor industry have gas, chemical, electricity and various facilities in bring to it. That it is a foundation by fire, power failure, blast, spill of toxicant huge by large size accident human and physical loss and damage because it can bring this efficient, connect with each kind mechanical, physical thing to prevent usefully need that control finding achievement factor of human factor of human action. Large size accident in a semiconductor industry to machine and human and it is involved that present, in system by safety interlock defect of machine is conclusion for error of behaviour. What is not construing in this study, do safety in a semiconductor industry to do improvement. Control human error analyzes in human control with and considers mechanical element and several elements. Also, apply achievement factor using O'conner Model by control method of human error. In analyze by failure mode effect using actuality example.

• 한국도시철도학회논문집
• /
• 제6권4호
• /
• pp.287-298
• /
• 2018

본 연구는 철도안전관리체계 기술기준의 11.7 철도관제를 중심으로 철도교통관제사의 다양한 측면에서 업무를 이해하고 실무적 제언을 하고자 한 논문이다. 분석방법으로는 시스템다이내믹스의 소프트적 방법인 인과순환지도를 작성하여 11.7철도관제의 업무를 분석하였다. 그리고 4개 철도운영기관 별 11.7 철도관제를 비교분석 하여 운영기관 별 관제업무의 특징들을 비교하여 철도관제업무의 중요성과 향후 실무적 개선안을 제시하고자 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.1897-1902
• /
• 2008

The computer system is used in many application domains and any system error in these domains may either cause critical loss or threaten environment or human life. Though examples of these domains can be found in many areas, the system, which is used in domains for carrying passengers including rolling stocks in particular, is expected to show satisfactory operation all the time. The relay control logic, which is used in rolling stocks, is complex in hardware and occupies considerably large volume. Nevertheless, it has been used for a long time, to let the system safely operate even in the occurrence of an error in the computer system. However, the relay control logic circuit is so complex that the analysis of proper circuit operation and interlocking tends to be dependent only on the designer's experiences instead of being systematically performed. Especially, the analysis following a change, addition and deletion of a previous circuit according to the requirements from a source of demand is significantly limited. In this paper, the accuracy of relay control logic is verified by the use of properties of Petri Net model. In addition, how main circuit breaker (MCB) control circuit is modeled and analyzed by the design methodology is shown.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.776-783
• /
• 2022

Since Mechanical, Electrical, and Plumbing(MEP) routing is a repetitive and experience-centered process that requires considerable time and human resources, if automated, design errors can be prevented and the previously required time and human resources can be reduced. Although research on automatic routing has been conducted in many industries, the MEP routing in AEC projects has yet to be identified due to the complexity of system configuration, distributed expertise, and various constraints. Therefore, the purpose of this study is to identify the target subjects for MEP routing automation and the constraints of each subject. The MEP design checklist provided by a CM company and existing literature review were conducted, and target subjects and constraints were identified through process observation and in-depth expert interviews for five days by visiting a MEP design company. The target subjects were largely divided into six categories: air conditioning plumbing, air conditioning duct, restroom sanitary plumbing, heating plumbing, and diagram. The findings from interviews show that work reduction and error reduction has the greatest effect on air conditioning plumbing while the level of difficulty is the highest in air conditioning duct and restroom sanitary plumbing. Major constraints for each subject include preventing cold drafts on air conditioning pipes, deviation in ventilation volume in air conditioning ducts, routing order on restroom sanitary plumbing, and separation distance from the wall on heating plumbing. In this way, subjects and constraints identified in this study can be used for MEP automatic routing.

• 대한전자공학회논문지SP
• /
• 제42권3호
• /
• pp.107-114
• /
• 2005

선으로 구성된 회로도나 설계도 같은 특수 목적 영상을 처리할 경우 에지가 강조된 영상을 필요로 한다. 또한 프린터, 팩시밀리, LCD TV 등과 같은 이진 출력 장치에 연속 계조 영상을 표현하기 위한 디지털 해프토닝 방법 중 오차 확산 방법으로 이진 영상을 생성할 경우 에지가 흐려진다. 본 논문은 회로도나 설계도 등의 영상 뿐 아니라 이진 출력 장치 등에 사용되는 이진 영상의 에지를 강조하는 방법을 제안한다. 인간의 눈은 한 화소의 명암값이 아니라 국부 평균을 인식한다는 것을 이용하여 제안 방법은 원화소의 명암값과 $3{\times}3$ 블록의 평균 명암값과의 차이 값에 공간적 위치 값에 따른 가중치를 결합하여 국부 공간 변화량(LAM: local activity measure)을 사용한다. 제안된 시스템은 또한 LAM에 평균 명암도를 곱하여 얻어진 에지 강조 정보량(IEE: information of edge enhancement)을 사용한다. IEE를 양자화기 입력에 더하여 이진 영상의 에지를 강조한다. 컴퓨터 시뮬레이션은 제안 방법이 기존의 방법에 비해 영상의 에지가 강조되어 시각적으로 선명한 영상을 생성한다. 또한 거리에 따른 에지 상관도와 로컬 평균 일치도를 이용하여 제안 방법과 기존 방법의 특성을 분석한다.

• 대한전자공학회논문지
• /
• 제27권10호
• /
• pp.68-77
• /
• 1990

본 논문에서는 CAD 시스템의 신경망을 이용한 자동 입력기 구축을 위한 논리 심볼 인식방법을 제시한다. 손으로 작성한 도면을 인식하기 위해 특징 추출과 log mapping, 그리고 패턴 인식의 다단계 과정을 거친다. 각 논리 심볼의 현태 정보를 추출하기 위해 억제 가중치를 학습할 수 있는 경쟁 학습법을 제안하고 회전과 크기의 변화를 병진된 결과로 나타내는 log mapping을 하고 형태가 변한 심볼을 인식할 수 있도록 겹쳐지는 수용야(Receptive field)를 준비하여 error back propagation을 이용한 다층망으로 심볼을 인식한다.