• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.784-791
• /
• 2007

Most operational organization and railway authority which conduct scheduled maintenance(SM) have carried out the preventive maintenance(PM) based on the information provided from supplier and manufacturer of railway system. However these activities are far away from reality and low the efficiency, it is because an appropriate methods for system selection didn't take into account for improving maintenance efficiency. Therefore, the current SM tasks and maintenance activities lead to lots of spend on the cost and time. To solve the above problem, this thesis presents new approach methodology. This proposes the criteria for reliability centered maintenance(RCM) system selection through level of quantification of each parameter, i.e, frequency, severity and maintenance cost, etc. To do this, the field operation data and information of maintenance cost are essential. As applying this methodology, we can look forward to improving efficiency of PM/SM, and reducing cost.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.185-190
• /
• 2002

In distributed autonomous robotic systems (DARS), each robot must behave by itself according to its states ad environments, and if necessary, must cooperate with other robots in order to carry out their given tasks. Its most significant merit is that they determine their behavior independently, and cooperate with other robots in order to perform the given tasks. Especially, in DARS, it is essential for each robot to have evolution ability in order to increase the performance of system. In this paper, a schema co-evolutionary algorithm is proposed for the evolution of collective autonomous mobile robots. Each robot exchanges the information, chromosome used in this algorithm, through communication with other robots. Each robot diffuses its chromosome to two or more robots, receives other robot's chromosome and creates new species. Therefore if one robot receives another robot's chromosome, the robot creates new chromosome. We verify the effectiveness of the proposed algorithm by applying it to cooperative search problem.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.1722-1730
• /
• 2007

According to the result of recent studies, it was revealed that the error of safety-related personnel still plays a significant role in the accidents and/or incidents of a railway system. Accordingly, in order to reduce as well as prevent human errors, it is necessary to: (1) identify the root cause of accidents/incidents, and (2) conduct a research that can provide a systematic as well as an effective way to deal with the identified human errors. To this end, it is essential to suggest appropriate countermeasures based on the result of a task load analysis, which can soundly reduce a high level of the task load put on safety-related personnel. In the light of this concern, about the tasks of railway traffic signallers, a detailed task analysis was conducted in this study. After that, the associated task load scores were quantified by NASA-TLX technique that is one of the most well-known subjective workload measurement techniques. As a result, a set of significant tasks that could put a high task load on railway traffic signallers was identified.

• 센서학회지
• /
• 제32권6호
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• 한국산업보건학회지
• /
• 제29권2호
• /
• pp.159-166
• /
• 2019

Objectives: The purpose of this study was to evaluate the personal exposure to $PM_{10}$ by body parts for the development of dust monitoring wearable device for swine farmers. Methods: Tasks were classified by using motion pictures taken by action cameras attached to swine farmers. Concentrations of $PM_{10}$ were measured by attaching direct-reading instruments at the head, neck and waist of worker. Differences of $PM_{10}$ exposure between body parts were analyzed with linear regression. Results: We identified three tasks(vaccination, moving pigs, and manure treatment). $PM_{10}$ concentration during vaccination was the highest among the tasks, and the body part showing the highest concentration of $PM_{10}$ was the waist regardless of task. In all tasks, the closer distance between the body parts, the higher were the R-squared values(vaccination 0.4221, moving pigs 0.6990, and manure treatment 0.2164). Conclusions: We presumed that $PM_{10}$ concentrations were affected by the parts of the body in which they were measured. In order to develop swine farmer's wearable device for monitoring dust concentration in air, the determination of the positions of monitoring sensor to ensure accurate measurement is essential. Considering the results of this study, wearable sensor should be positioned at the waist.

• 대한간호학회지
• /
• 제51권6호
• /
• pp.758-768
• /
• 2021

Purpose: This study aimed to conduct a job analysis of nurse carecoordinators and to identify the frequency, importance and difficulty of each task of their job. Methods: A committee for developing a curriculum (DACUM) was formed and members of the committee defined nurse care coordinators' jobs and enumerated the duties, tasks and task elements by applying the DACUM technique. Then nurse care coordinators enrolled in the pilot project evaluated the frequency, importance and difficulty of each task. Results: From the job descriptions of nurse care coordinators, we identified 12 duties and 42 tasks. Each task comprised 1~5 task elements. Among tasks, 'assess the patient's general health status' was carried out most frequently. Nurse care coordinators perceived that 'check vital signs' and 'strengthen patient competence to promote health behaviors' were more important than all other tasks. The most difficult task was 'develop professionalism as a nurse care coordinator'. Conclusion: The nurse care coordinators' roles developed in this study will serve as the key guidelines for human resource management of care coordinators. Further, job specifications for nurse care coordinators need to be developed, which is necessary for designing education and training programs. We also need to integrate primary health care as an essential component in nursing education.

• 한국기록관리학회지
• /
• 제23권3호
• /
• pp.21-37
• /
• 2023

공공기관의 기관사 편찬은 기록 편찬의 한 유형으로 이용자들에게 매우 유용한 기록 콘텐츠가 될 수 있다. 그러나 대부분 공공기관에서 기관사 편찬에 대한 경험이 부족하고 참고할 지침이나 절차가 없어 어려움을 겪고 있다. 본 연구의 목적은 공공기관에서 참고하여 유연하게 적용이 가능한 기관사 편찬 모형을 개발하는 것이다. 이를 위해 문헌연구, 업무분석, 설문조사, 심층면담 및 전문가 평가를 하였다. 이러한 결과를 바탕으로 5개 프로세스, 20개 업무영역, 45개 업무요소의 기관사 편찬 모형을 제안하였다. 특히 31개의 기본업무와 14개의 선택업무로 구분하여 기관의 상황이나 기관사의 유형에 따라 유연하게 적용할 수 있도록 하였다. 본 연구의 모형은 공공기관에서 기관사 편찬 업무를 수행하는데 활용할 수 있으며, 기관사 편찬을 준비하는 단계에서 수행해야 할 업무 전반을 파악하여 일정과 계획을 수립하는 데도 활용할 수 있을 것이다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.159-162
• /
• 2007

The inverse kinematics problem in robotics is an essential work for grasping and manipulation tasks by robotic and humanoid hands. In this paper, an intelligent neural learning scheme for solving such inverse kinematics of humanoid fingers is presented. Specifically, a multi-layered neural network is utilized for effective inverse kinematics, where a dynamic neural learning algorithm is employed. Also, a bio-mimetic feature of general human fingers is incorporated to the learning scheme. The usefulness of the proposed approach is verified by simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1411-1414
• /
• 1997

It is essential to obtain a distane informaion in order to completely execute assembly tasks such as a grasping and an insertion. In this paper, we propose a method estimating a measurement distance from a sensor to an object through using the omni-directional image sensing system for assembly(OISSA) and show its features and feasibility by a computer simulation. The method, utilizing a forwarded motion stereo technique, is simple to search the corresponding points and possible to immediatiely obtain a three-dimensional 2.pi.-shape information.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.239-242
• /
• 2001

As systems for real time computer vision are confronted with prodigious amounts of visual information, it has become a priority to locate and analyze just that information essential to the task at hand, while ignoring the vast flow of irrelevant detail. A method of achieving this is to using human visual attention mechanism. In this paper, short review of human visual attention mechanisms and some computation models of visual attention were shown. This paper can be used as the basic data for researches on development of visual attention system that can perform various complex tasks more efficiently.