• 제어로봇시스템학회논문지
• /
• 제10권6호
• /
• pp.545-550
• /
• 2004

Recent natural disasters like flooding and slope collapse have shown the need for natural risk management system, as they endanger directly public health and cause severe damages on the national economy. In order to improve the efficiency of risk management systems, this management system based on AANN(Auto-Associative Neural Network)is proposed in this paper. AANN can be effectively used for identification of abnormal data and data compression. The proposed AANN-based risk management system collects and stores measurement data from sensors and transmits them to remote server for web-monitoring. Generally, it is desirable to transmit the compressed data instead of raw data in normal state. However, if dangerous situation happens, rapid tramission of measurement data should be required. These requirements are easily satisfied by using AANN. In order to verify the feasibilities of the proposed system, The AANN-based risk management system is applied to slope collapse monitoring system.

• 산업경영시스템학회지
• /
• 제31권4호
• /
• pp.49-58
• /
• 2008

This paper proposes a methodology to measure the risk level in real-time for Business Activity Monitoring (BAM). A decision-tree methodology was employed to analyze the effect of process attributes on the result of the process execution. In the course of process execution, the level of risk is monitored in real-time, and an early warning can be issued depending on the change of the risk level. An algorithm for estimating the risk of ongoing processes in real-time was formulated. Comparison experiments were conducted to demonstrate the effectiveness of our method. The proposed method detects the risks of business processes more precisely and even earlier than existing approaches.

• 대한안전경영과학회지
• /
• 제15권3호
• /
• pp.1-6
• /
• 2013

This study was conducted to compare the value of the working environment measurement with the expected exposure value drawn by using a program, thereby going to investigate whether it is available to the risk assessment of domestic workplace. We used the ECETOC TRA program which is one of the exposure predictive models. Four kinds of substances were measured in two workplace which was exposed to organic solvents and one kind of substance was measured in three workplace which was exposed to dusts and then an exposure assessment of chemical risk factors was conducted. The result value of the working environment measurement, solid substance exceeded standard in one site, and it was found that the other solid and liquid substances were within the standard. The value of the exposure assessment program showd the same result; it was higher than the value of the working environment measurement, suggesting that due to its nature, the exposure assessment program is run only on the worst situation. Therefore, it was found that when the exposure assesment program is used, variables should be substituted only after accurately assessing the workplace and it is a good idea to assess the risk beforehand with the exposure assessment program in the case of the workplace which employs no more than 5 people and where it is hard to assess the working environment.

• 인터넷정보학회논문지
• /
• 제25권4호
• /
• pp.97-108
• /
• 2024

인공지능 로봇의 산업화가 활발해짐에 따라 윤리적, 기술적 문제가 심각해지고 있음에도 위험성에 관한 연구는 미흡하다. 이러한 실정에서 연구자는 인공지능 로봇의 신체, 권리, 재산, 사회적 위험성을 측정할 수 있는 검증된 지표 52개를 개발하였다. 인공지능 로봇의 위험성 유형별 측정지표 개발을 위해 IRB 심의 이후, 전문가 11명에게 심층 면접하였다. 또한 현장성 검증을 위해 인공지능 로봇이 도입될 수 있는 여러 분야 종사자 328명에게 설문 조사하였으며, 타당성 및 신뢰성 측정을 위해 탐색적 요인분석과 신뢰도 분석, 변수 계산을 위한 상관관계 분석과 다중 회귀분석 등 통계 검증하였다. 이 논문에서 제시하는 측정지표가 표준화된 인공지능 로봇의 개발·인증·교육·정책 등에 널리 활용되어, 사회적으로 공감받고 안전한 인공지능 로봇 산업화의 초석이 되기를 기대한다.

• 디지털융복합연구
• /
• 제16권2호
• /
• pp.421-430
• /
• 2018

본 연구에서는 대구지역의 사춘기청소년을 대상으로 건강위험행동에 대한 척도기준을 분석하는 데 있다. 연구방범은 우리나라 사춘기청소년의 건강특성에 맞는 건강위험행동 측정항목을 개발하고자, 기존 THI의 측정항목에 대한 내용 타당성(CVR)분석을 하고, 이후 확인적 요인분석을 통하여 구체화 한 건강위험행동의 척도를 비교 분석하였다. 분석결과, 요인분석을 통해 개발된 사춘기청소년들의 건강위험행동 척도에 대한 신뢰도 검증을 실시하여 전신상태, 호흡기, 순환기, 소화기, 정신건강 기타항목 등의 측정항목을 도출하였다. 개발된 건강위험행동 척도의 신뢰도와 타당도는 상당히 양호한 것으로 나타났다. 이러한 연구를 통해서 사춘기청소년들의 건강과 관련된 위험행동을 감소시킬 수 있는 예방프로그램을 개발하고, 정책수립에 기초적인 자료를 제공할 수 있는 전략을 고안해 낼 수 있을 것이다.

• 산업공학
• /
• 제24권1호
• /
• pp.24-39
• /
• 2011

In this paper, we study the methodology for the measurement and integration of market risk and credit risk using Copula. We apply the methodology of Rosenberg, and Schuermann(2006) to the assets of pension system. Firstly we estimate dynamics of risk factors and their effects on investment returns, then use the estimated result to simulate future movement of risk factors and distribution of investment returns. Finally we measure integrated risk using integrated return distribution by Copula and simulated future investment return distributions. We found the integrated risk changing with the correlation of risks and investment weights of risks and confirmed the diversification effect of risks. This result is consistent when we use normal Copula and normal marginals, t-Copula and t(3) marginals, and normal Copula and non-parametric marginals. And in the case of non-parametric maginals, larger integrated risk is calculated. It means that use of non-parametric marginals is more conservative.

• 한국산업보건학회지
• /
• 제31권4호
• /
• pp.440-450
• /
• 2021

Objectives: This study aims to investigate whether working environment measurement institutions(WEMIs) are conducting safety and health education, risk assessment, and oversight of special management materials, and whether working environment measurement and special medical examinations are being conducted as prescribed in the Occupational Safety and Health Act(OSHA). Methods: In of February 2021, a questionnaire was prepared and distributed to 33 WMEIs registered with the Ministry of Employment and Labor(MoEL) in Busan and Gyeongsangnam-do Province. The responses were collected and then analyzed. Results: The findings show that 5 WEMIs(15%) complied fully with OSHA. Risk assessment was conducted by 13 WMEIs(39%) and safety education by 11 WMEIs(33%). Eighteen WMEIs(55%) conducted working environment measurement, and 29 WMEIs(88%) conducted special medical examinations. The implementation rate of the risk assessment in the health industry(85%) was higher than the one in the special technology industry(11%)(p<0.05). The implementation rate of the special medical examination in the examiners(54%) was not as high as the one in the analysts(91%)(p<0.05). Conclusions: The MoEL needs to check whether basic OSHA requirements are being observed during regular inspections by WEMIs. These findings indicate that it is necessary to prepare a plan to improve the rate of compliance with OSHA regulations.

• 한국항만경제학회지
• /
• 제34권1호
• /
• pp.99-110
• /
• 2018

본 연구는 해운기업의 주요 비용요인 벙커 가격과 환율의 불확실성으로 인한 재무적 리스크를 수치화하는 방법론을 2010년 1월 1일부터 2018년 1월 31일까지의 일별자료를 대상으로 적용한다. 기하브라운 운동 (Geometric Brownian Motion 이하 GBM)과 이를 확장한 조건부 이분산성(heteroskedasticity) 및 점프 확산 프로세스(jump diffusion process)에 의존하는 모형으로부터 추정한 현금 흐름 리스크 추정치는 다음 세 가지 학술적 기여로 요약할 수 있다. 첫째, 운임수익률과 같은 단일 변수에 의존한 리스크 분석을 벙커가격과 환율 수익률 변동성과 같이 복합요인으로부터 발생하는 영향으로 분석을 확장하였다. 둘째, 개별기업 수준에서 벙커가격과 환율 리크스 관리의 필요성을 민감도 분석을 통해 현금흐름수준으로 제시하였다. 마지막으로 분석결과가 제시하는 리스크 규모를 근거로 해운기업은 리스크 관리를 위한 수단으로 무엇이 적절한가를 고민해야 할 필요성이 있음을 제기한다.

• STI Policy Review
• /
• 제4권2호
• /
• pp.41-54
• /
• 2013

R&D is inherently an uncertain endeavor, yet now more than ever those performing R&D with public funding are called upon to clarify the utility of their research. Calls for public accountability are mounting with the increase in constraints on government budgets due to the recent worldwide economic recession, in response to which both policymakers and researchers pay much more attention to rigorously assessing publicly funded R&D. A key issue complicating R&D evaluation in these circumstances is how to adequately account for the nature and degree of risk involved in a given R&D program or project. This study deliberates on certain issues involving the measurement of ex-ante risk in public R&D evaluation: (i) information asymmetry between R&D sponsors and performers, (ii) ambiguity in the measurement of returns in both prospective and retrospective evaluation, and (iii) the dilemma between measurement error and omitted variable bias for empirical estimation of R&D performance. The study then presents an analysis of hypothetical evaluation results that apply risk-relevant weights to the annual evaluation outcomes of South Korea's national R&D programs funded during 2006~2012. In this counterfactual re-evaluation of public R&D program performance, high-risk R&D programs turn out to receive higher evaluation than non-high-risk programs. The current study suggests that R&D evaluation ignoring ex-ante risk is not only conceptually invalid since R&D activities are intrinsically uncertain endeavors, but unfair as R&D performers are asked to be accountable for the results that were in fact out of their reach.

• 한국전문물리치료학회지
• /
• 제30권2호
• /
• pp.102-109
• /
• 2023

Background: While efforts have been made to differentiate fall risk in older adults using wearable devices and clinical methodologies, technologies are still infancy. We applied a decision tree (DT) algorithm using inertial measurement unit (IMU) sensor data and clinical measurements to generate high performance classification models of fall risk of older adults. Objects: This study aims to develop a classification model of fall risk using IMU data and clinical measurements in older adults. Methods: Twenty-six older adults were assessed and categorized into high and low fall risk groups. IMU sensor data were obtained while walking from each group, and features were extracted to be used for a DT algorithm with the Gini index (DT1) and the Entropy index (DT2), which generated classification models to differentiate high and low fall risk groups. Model's performance was compared and presented with accuracy, sensitivity, and specificity. Results: Accuracy, sensitivity and specificity were 77.8%, 80.0%, and 66.7%, respectively, for DT1; and 72.2%, 91.7%, and 33.3%, respectively, for DT2. Conclusion: Our results suggest that the fall risk classification using IMU sensor data obtained during gait has potentials to be developed for practical use. Different machine learning techniques involving larger data set should be warranted for future research and development.