With the rapid development of artificial intelligence, the use of artificial intelligence in the field of employment, especially in recruitment, is gradually increasing. Artificial intelligence judges applications for employment of applicants and analyzes interview videos to determine emotional intelligence, communication skills, cognitive ability, and problem-solving ability. However, there is a risk of discrimination in evaluating humans in hiring by these automated decisions made by artificial intelligence. Discrimination in hiring according to gender, race, or disability is prohibited by various laws such as the Constitution, Labor Standards Act, Framework Act On Employment Policy, and Employment Security Act in Korea. In particular, the Act On The Prohibition Of Discrimination Against Persons With Disabilities, Remedy Against Infringement Of Their Rights and the Act On The Employment Promotion And Vocational Rehabilitation Of Persons With Disabilities require special protection for people with disabilities. Discrimination against persons with disabilities can be divided into direct discrimination against persons with disabilities without justifiable grounds, and indirect discrimination that results in disadvantageous consequences for persons with disabilities by applying standards that do not take disabilities into account even though they are not formally treated unfavorable. When hiring according to automated decision-making, (i) intentional discrimination that intentionally sets applicants with elements of the disablity to be excluded from recruitment, (ii) making an automated decision not to hire the disabled through the existing data which prejudice against the disabled is already reflected, and (iii) if the existing data lacks or does not have information on the disabled, the data itself lacks representativeness, leading to distorted decisions, there is a risk that will be judged as discrimination for the disabled. In Korea, the Credit Information Use And Protection Act has proposed the definition of automated evaluation for owner of credit information and protection standards, but it is limited to the protection of credit information, and a recent amendment of the Personal Information Protection Act suggests protection measures from decisions made by automated systems, but it is criticized for the scope of protection being reduced than that of the GDPR. In addition, special protection measures for workers, such as the ILO’s Code of Practice for Protection of Workers’ Personal Data, are not mentioned separately, so it is necessary to devise legal protection measures in the hiring process according to automated decision-making of disabled workers.

In this study, the types of thermal breakers applied to structures to prevent thermal bridges were identified. Condensation prevention performance was evaluated for apartment houses with standard floor structures to which a thermal breaker was applied. In addition, the effect of thermal cross-blocking was compared by calculating the total heat and equivalent U-value through the wall. (1) As a result of the evaluation of anti-condensation performance, when “가” grade insulation was applied, the surface temperature increased by about 1K due to the application of the thermal breaker. The TDR value increased by about 0.06 to 0.07. When "나" grade insulation was applied, the minimum surface temperature increased by about 1K, and the TDR value increased by about 0.05~0.06. (2) As a result of the evaluation of total heat and U-equivalent, it was possible to reduce the total heat by 38.5~44.9% and U-equivalent by 38.5~45.0% for the "가" grade insulation to which the thermal breaker was applied. In addition, the "나" grade insulation to which the thermal breaker was applied can reduce total heat by 38.9 to 43.6%, and reduce the Uequivalent by 38.9 to 43.7%.

본 연구는 머신러닝 기법을 토대로 15개 환경 변수를 활용하여 소나무재선충병의 위험지역 분포를 예측하였다. 연구는 최대 엔트로피 모델을 머신러닝 기법으로 활용하였고, 연구 지역은 경주이며 연구 기간은 2018∼2020년이다. 모델의 평가에는 AUC(area under the curve)를 이용하였다. 연구 지역에서 소나무재선충병의 감염목 핵심 분포 지역은 2018년 대비 2019년과 2020년에 각각 2.5배와 4.7배 확대되었다. 소나무재선충병의 감염목 분포 추정 모델의 AUC는 모든 해에 최소 0.86 이상이었다. 모델에서 가장 중요한 변수는 직전 해의 감염목 근접도 이었다. 지형과 도로와의 인접성, 목조건물 인접성, 5월 평균 기온도 중요한 변수이었다. 인간 활동과 매개충의 생장 환경이 소나무재선충병의 공간적 분포에 중요한 역할을 한다는 것을 의미한다. 나아가 연구의 결과는 감염목 분포 정보의 지속적인 구축과 공유가 소나무재선충병 예방을 위한 정책과 연구에 중요하다는 것을 시사한다.

국내외 해상 위험·유해물질(HNS, Hazardous and Noxious Substances) 물동량 증가와 함께 HNS 유출 사고가 빈번히 발생하고 있다. HNS는 전 세계적으로 약 6,000여 종으로 대부분 유독한 성질을 가지므로 이러한 유출 사고 발생은 해양 생태계 파괴를 비롯하여 폭발 및 화재 등으로 인한 인명 및 재산피해를 유발한다. 따라서 해상 HNS 유출 사고를 대비하여 파장에 따른 HNS 분광 라이브러리 구축 및 탐지 알고리즘을 개발해야 한다. 본 연구에서는 프랑스 현지에서 지상 HNS 유출 실험을 진행하였다. 초분광센서 관측을 통해 파장에 따른 톨루엔 라이브러리 스펙트럼을 구축하였으며, 분광혼합 알고리즘을 활용하여 초분광 HNS를 탐지하였다. 전처리 과정으로 주성분 분석을 적용하여 노이즈 제거 및 차원 압축을 수행하였으며, N-FINDR 기법을 통해 영상을 대표하는 톨루엔과 해수의 엔드멤버 스펙트럼을 추출하였다. 스펙트럼 기반의 톨루엔 및 해수의 점유비율을 계산함으로써 모든 픽셀의 HNS 탐지 정확도를 확률로 제시하였다. 최대 탐지 정확도를 가지는 점유비율 선정을 위해 418.15 nm 파장의 복사도 영상과 비교하였으며, 그 결과 약 42%의 비율에 서 99% 이상의 정확도를 나타내었다. 해상 HNS 유출은 높은 위험성으로 인해 사람이 쉽게 접근할 수 없는 한계를 지닌다. 본 HNS 실험과정 및 탐지 결과는 초분광 원격탐사에 기반한 HNS 오염 해역 추정에 도움이 될 것이다.

The water supply facilities of Korea have achieved a rapid growth, along with the other social infrastructures consisting a city, due to the phenomenon of urbanization according to economic development. Meanwhile, the level of water supply service demanded by consumer is also steadily getting higher in keeping with economic growth. However, as an adverse effect of rapid growth, the quantity of aged water supply pipes are increasing rapidly, Bursts caused by pipe aging brought about an enormous economic loss of about 6,161 billion won as of 2019. These problems are not only worsening water supply management, also increasing the regional gap in water supply services. The purpose of this study is to classify hazard evaluation indicators and to rank the water distribution network hazard by cluster using the TOPSIS method. In conclusion, in this study, the entropy-based multi-criteria decision-making methods was applied to rank the hazard management of the water distribution network, and the hazard management ranking for each cluster according to the water supply conditions of the county-level municipalities was determined according to the evaluation indicators of water outage, water leakage, and pipe aging. As such, the hazard ranking method proposed in this study can consider various factors that can impede the tap water supply service in the water distribution network from a macroscopic point of view, and it can be reflected in evaluating the degree of hazard management of the water distribution network from a preventive point of view. Also, it can be utilized in the implementation of the maintenance plan and water distribution network management project considering the equity of water supply service and the stability of service supply.

In this study, dual drainage system based runoff model was established for W-drainage area in G-si, and considering the various rainfall characteristics determined using Huff and Mononobe methods, the degree of flooding in the target area was analyzed and the risk was compared and analyzed through the risk matrix method. As a result, the Monobe method compared to the Huff method was analyzed to be suitable analysis for flooding of recent heavy rain, and the validity of the dynamic risk assessment considering the weight of the occurrence probability as the return period was verified through the risk matrix-based analysis. However, since the definition and estimating criteria of the flood risk matrix proposed in this study are based on the return period for extreme rainfall and the depth of flooding according to the results of applying the dual drainage model, there is a limitation in that it is difficult to consider the main factors which are direct impact on inland flooding such as city maintenance and life protection functions. In the future, if various factors affecting inland flood damage are reflected in addition to the amount of flood damage, the flood risk matrix concept proposed in this study can be used as basic information for preparation and prevention of inland flooding, as well as it is judged that it can be considered as a major evaluation item in the selection of the priority management area for sewage maintenance for countermeasures against inland flooding.

In this study, dual drainage system based runoff model was established for W-drainage area in G-si, and considering the various rainfall characteristics determined using Huff and Mononobe methods, the degree of flooding in the target area was analyzed and the risk was compared and analyzed through the risk matrix method. As a result, the Monobe method compared to the Huff method was analyzed to be suitable analysis for flooding of recent heavy rain, and the validity of the dynamic risk assessment considering the weight of the occurrence probability as the return period was verified through the risk matrix-based analysis. However, since the definition and estimating criteria of the flood risk matrix proposed in this study are based on the return period for extreme rainfall and the depth of flooding according to the results of applying the dual drainage model, there is a limitation in that it is difficult to consider the main factors which are direct impact on inland flooding such as city maintenance and life protection functions. In the future, if various factors affecting inland flood damage are reflected in addition to the amount of flood damage, the flood risk matrix concept proposed in this study can be used as basic information for preparation and prevention of inland flooding, as well as it is judged that it can be considered as a major evaluation item in the selection of the priority management area for sewage maintenance for countermeasures against inland flooding.

This study examines the trends of domestic and foreign smart industries and discusses safety and security issues. Based on the actual situation survey and interview of the smart factory, we would like to examine the perspectives on risks and threats. We will examine safety and health issues related to new harmful and risk factors that may occur in smart factories and suggest institutional development directions for future safety and health. First, a safety and health-related work environment for smart factory workers is investigated and interviews are conducted. Second, we investigate new risk factors and threats to prevent industrial accidents for workers in smart factories. The purpose of this study is to examine what are the new risk factors in the smart factory. In addition, we will try to find reasonable improvement measures by finding out the risks and threats of smart factories through case studies in advanced countries, on-site interviews and surveys.

Using the frequency-based decomposition, I decompose the consumption growth to explain well-known patterns of stock returns in the Korean market. To be more specific, the consumption growth is decomposed by its half-life of shocks. The component over four years of half-life is called the business-cycle consumption component, and the components with half-lives under four years are short-run components. I compute the long-run and short-run components of stock excess returns as well and use component- by-component sensitivities to price stock portfolios. As a result, the business-cycle consumption risk with half-life of over four years is useful in explaining the cross-section of size-book-to-market portfolios and size-momentum portfolios in the Korean stock market. The short-run components have their own pricing abilities with mixed direction, so that the restricted one short-term factor model is rejected. The explanatory power with short- and long-run components is comparable to that of the Fama-French three-factor model. The components with one- to four-year half-lives are also helpful in explaining the returns. The results about the long-run components emphasize the importance of long-run component in consumption growth to explain the asset returns.

침입우려 고위험 해충 9종(Aceria diospyri, Bactrocera dorsalis, Bactrocera minax, Bactrocera tsuneonis, Cydia pomonella, Lobesia botrana, Proeulia sp., Solenopsis invicta, Stephanitis takeyai)에 대한 예찰조사를 2020년 4월부터 10월까지 전국 7개 권역, 78지역, 222지점에서 실시하였다. 조사기간 동안, 총 12,045개의 트랩운용/달관조사를 실시하였으며, 9종 모두 발견되지 않았다. 침입우려 고위험 해충 9종에 대한 예찰조사는 2018년부터 시작되었으며, 3년동안의 조사연구를 통해 7개 대학이 참여하는 전국단위의 외래해충 감시체계가 구축되었고 예찰조사 거점 지역들을 확보하였다.

선박의 주묘 위험성을 평가할 수 있는 프로그램이 개발되어 있지만 선박의 제원에 해당되는 다양한 입력요소들을 직접 찾아서 입력해야 하므로 VTS 관제사가 정박지에 정박 중인 선박들로부터 이러한 입력요소들을 모두 확인하여 프로그램을 활용하는 것은 현실적으로 어려운 상황이다. 이에 본 연구에서는 VTS 관제사 입장에서 선박으로부터 쉽게 획득할 수 있는 총톤수(GT)를 독립변수로 설정하고 프로그램 입력요소들을 종속변수로 하여 선형 및 비선형 회귀분석을 실시하였다. 다항식 모델(선형)과 멱급수 모델(비선형)의 적합도를 비교한 결과, 컨테이너선과 벌크선의 경우에는 모든 입력요소에서 멱수급 모델이 적합한 것으로 평가되었다. 하지만 탱커선의 경우에는 수선간장, 선폭, 흘수는 멱수급 모델이 적합하고, 정면풍압면적, 앵커의 무게, 의장수, 묘쇄공으로부터 선저까지의 높이는 다항식 모델이 더 적합한 것으로 평가되었다. 또한 탱커선의 정면풍압면적 요소를 제외한 다른 나머지 종속변수들은 모두 결정계수가 0.7 이상으로 높은 적합도를 보였다. 따라서 주묘 위험성 평가 프로그램의 입력요소 중 외력 요소, 해저 저질, 수심 및 앵커 체인의 신출량을 제외한 나머지 입력요소들은 선박의 총톤수만 입력하면 회귀분석 모델식에 의해 자동으로 입력됨으로써 주묘 위험성 평가가 가능할 것으로 판단된다.

정부(해양수산부) 및 관계기관에서는 안전관리 취약선박의 해양안전 증진을 위한 많은 정책을 시행하고 있으나, 선박의 안전관리에 대한 위험성평가 부재로 각 제도의 효과성에 다소 아쉬움이 확인되었다. 선박의 위험성평가에 대한 국내 선행연구는 대부분 개별적 해양사고 위험성에 대한 단편적 위험성만을 취급하고 있어 포괄적 해양사고 위험성평가를 위한 새로운 방식이 필요하다. 선박의 안전관 리에 대한 포괄적 위험성평가 적용사례로 항만국통제와 노르웨이 해사국의 점검대상 선정방법이 있다. 본 연구에서는 국내 해양사고 및 등록현황의 높은 비중을 차지하고 있는 연근해어선을 대상으로 포괄적 선박안전관리 위험성평가를 위한 지표를 개발하고 적용하였다. 그 결과, 각 선박별 위험성을 계량적 수치로 확인하였고, 개별적 안전관리 취약요소의 순위를 식별하였다.