• Journal of the Korean Society of Earth Science Education
• /
• v.14 no.2
• /
• pp.112-122
• /
• 2021

The goal of this study is to explore ways to restructure Convergence Elective Courses in science in preparation for the high school credit system, ahead of the 2022 revised science curriculum. This study started from the problem that the 2015 revised science curriculum has not guaranteed science subject choice for students with non-science/engineering career aptitudes. To this end, a survey was conducted by randomly sampling high schools across the country. A total of 1,738 students responded to the questionnaire of 3 science elective courses such as Science History, Life & Science, Convergence Science. In addition, in-depth interviews with 12 science teachers were conducted to examine the field operation of these three courses, which will be classified and revised as Convergence Elective subjects in the 2022 revised curriculum. According to the results of the study, high school students perceive these three courses as science literacy courses, and find these difficult to learn due to lack of personal interest, and difficulties in content itself. The reason students choose these three courses is mainly because they have aptitude for science, or these courses have connection with their desired career path. Teachers explained that students mainly choose Life & Science, and both teachers and students avoid Science History because the course content is difficult. Based on the research results, we suggested ways to restructure Convergence Electives for the 2022 revised curriculum including developing convergence electives composed of interdisciplinary convergence core concepts with high content accessibility, developing convergence electives with core concepts related to AI or advanced science, developing module-based courses, and supporting professional development of teachers who will teach interdisciplinary convergence electives.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.403-409
• /
• 2024

In this paper, the guidelines for the design of an Artificial Intelligence(AI) based Integrated Process Safety Management(PSM) system to enhance workplace safety using data from process safety reports submitted by hazardous and risky facility operators in accordance with the Occupational Safety and Health Act is proposed. The system composed of the proposed guidelines is to be implemented separately by individual facility operators and specialized process safety management agencies for single or multiple workplaces. It is structured with key components and stages, including data collection and preprocessing, expansion and segmentation, labeling, and the construction of training datasets. It enables the collection of process operation data and change approval data from various processes, allowing potential fault prediction and maintenance planning through the analysis of all data generated in workplace operations, thereby supporting decision-making during process operation. Moreover, it offers utility and effectiveness in time and cost savings, detection and prediction of various risk factors, including human errors, and continuous model improvement through the use of accurate and reliable training data and specialized datasets. Through this approach, it becomes possible to enhance workplace safety and prevent accidents.

• Journal of The Korean Association of Information Education
• /
• v.23 no.6
• /
• pp.675-687
• /
• 2019

As interest in artificial intelligence increases, each university has been establishing a special graduate school with artificial intelligence major, and recently, the Korea government has established various support policies for artificial intelligence education. However, each university has a lot of difficulties because it has little experience in operating graduate education with the latest field of artificial intelligence and it is not easy to find experts. In this study, the response of graduate school students majoring in artificial intelligence was analyzed using IPA technique, and the direction of education of graduate school artificial intelligence major was searched. Among the 40 items surveyed by IPA, 12 items such as systematization of artificial intelligence curriculum, progress of class considering learning level, improvement of academic relations with guidance professors were extracted as items to be improved first. On the other hand, 8 items such as assistant capacity, and relationship with colleagues were overloaded, and twelve items such as instructor's lecture competency, appropriateness of educational contents, learner's artificial intelligence skills and knowledge, and attitude acquisition were to be maintained. In addition, eight items such as convergence education curriculum and diversity of education methods were all low in importance and performance. It is suggested that AI graduate school should be divided into two tracks(technical specialization, convergence expansion) by educational goal, and each track should be conducted by level-specific educational contents and methods suitable for student level. The curriculum should be elaborate and systematic to acquire AI knowledge, skills, and attitudes, and should have an individualized guidance system centered on excellent faculty members.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1375-1380
• /
• 2021

Korea's security response to application service app is still insufficient due to the initial opening of the public safety network. Therefore, preemptive security measures are essential. In this study, we proposed to establish a 'public safety network app security system' to prevent potential vulnerabilities to the app store that distributes app in public safety network and android operating system that operate app on dedicated terminal devices. In order for an application service app to be listed on the public safety network mobile app store, a dataset of malicious and normal app is first established to extract characteristics and select the most effective AI model to perform static and dynamic analysis. According to the analysis results, 'Safety App Certificate' is certified for non-malicious app to secure reliability for listed apps. Ultimately, it minimizes the security blind spots of public safety network app. In addition, the safety of the network can be secured by supporting public safety application service of certified apps.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.19-27
• /
• 2022

In this study, we propose a language and platform to describe and manage the MLOps(Machine Learning Operations) workflow for time series data anomaly detection. Time series data is collected in many fields, such as IoT sensors, system performance indicators, and user access. In addition, it is used in many applications such as system monitoring and anomaly detection. In order to perform prediction and anomaly detection of time series data, the MLOps platform that can quickly and flexibly apply the analyzed model to the production environment is required. Thus, we developed Python-based AI/ML Modeling Language (AMML) to easily configure and execute MLOps workflows. Python is widely used in data analysis. The proposed MLOps platform can extract and preprocess time series data from various data sources (R-DB, NoSql DB, Log File, etc.) using AMML and predict it through a deep learning model. To verify the applicability of AMML, the workflow for generating a transformer oil temperature prediction deep learning model was configured with AMML and it was confirmed that the training was performed normally.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.106-106
• /
• 2023

저수지 수문자료는 강우량, 유입량, 저수량, 방류량이다. 이 중에서 관측되고 있는 것은 저수량과 일부 수로방류량에 불과하다. 그럼에도 모의에 의해 유입량을 고정시키면, 물수지에 의해 방류량을 계산할 수 있다. 그러나 저수량 오차로 모의 유입량과 계산 방류량의 신뢰도는 반드시 확인돼야 한다. 신뢰도가 낮으면 모의 유출량과 계산 방류량을 조정하며 신뢰도를 높여야 한다. 신뢰도는 평가주기가 짧을수록 보장된다. 여기서는 유역면적 218.80km², 유효저수량 3,494만m³, 수혜면적 5,117ha인 탑정지에 대해 2020년 1월1일부터 12월31일까지 1시간 단위로 1달, 10일, 3일, 2일 간격의 주기로 저수지 운영자료를 생산하고, 그 신뢰도를 평가하여 평가주기가 짧을수록 오차가 감소되는 것을 관찰코자 했다. 1시간 간격의 유입량은 ONE 모형으로 모의했고, 저수지 물수지 모형을 구축하여 모의 유입량에 저수량 변화를 더해 방류량을 계산했다. 또한 저수지 물수지에 의해 저수위를 모의했으며, 관측 저수위와의 오차제곱근(RMSE)으로 신뢰도를 평가한 결과는 다음과 같다. 1달 간격으로 신뢰도를 평가한 경우 RMSE는 132.466m, 10일 간격은 46.922m, 3일 간격은 0.520m, 2일 간격은 0.349m로 나타났다. 위의 결과로부터 저수지 수문자료의 평가주기를 짧게 할수록 신뢰도는 개선된다고 말할 수 있다. 이상의 결과는 과거 자료에 대해 1년 동안 1시간 간격으로 유입량을 모의하고 방류량을 계산한 결과를 고정시키고, 평가주기를 달리하며 수위오차를 분석한 결과이다. 만약 평가주기별로 유입량과 방류량을 실제 상황에 적합하게 조정하면, 그 신뢰도는 훨씬 더 개선될 것이다. 현재 저수지 수위만을 관리하고 있는 현장의 상황에서 이 연구결과가 시사하는 바는 매우 크다. 첨언하면 AI 시대의 핵심은 자료다. AI의 먹이는 자료다. 다시 말해 자료 없는 AI는 시체와 같다. 자료는 기본이고 진실이다. 자료 없는 결과는 가짜다. 또한 위의 결과는 자료는 상시 관찰돼야 한다는 것을 말한다. 1년에 한 번 수문자료를 평가하는 제도로는 고품질의 자료를 생산할 수 없다. 무엇보다 자료는 상시 관찰하는 제도가 정착돼야 하며, 그 때 비로소 AI와 공존과 협력으로 물관리 기술의 혁신을 이룰 것이라 확신한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.6-6
• /
• 2022

최근 수재해에 대응하기 위한 물관리 환경은 기후변화에 따른 홍수 피해 심화와 댐과 하천 시설의 노후화 점증, 하천관리일원화 등 정책적 변화, 그리고 포스트코로나 디지털 혁신 등 복합적 대전환 시대 진입에 따라 복잡다단한 양상을 보이고 있다. 디지털 트윈은 디지털 대전환(digital transformation) 시대 다양한 산업 영역에서 지능화와 생산성 향상을 목적으로 도입되고 있다. 본 국가 시범사업에서는 170 km에 달하는 섬진강 유역 전체를 대상으로 홍수에 대응하기 위한 디지털 트윈 플랫폼(K-Twin SJ)을 구축하고 있다. 본 플랫폼은 국가 인프라 지능정보화 사업의 일환으로 시작되었으며, 공간정보와 시설물 모델링, 홍수 분석 등 수재해에 대응하기 위한 수자원 분야의 다학제적인 강소기업들과 K-water에서 컨소시엄을 구성하여 추진하고 있다. 본 사업의 내용은 섬진강 댐-하천 유역에 대하여 고정밀도 3D 공간정보화, 실시간 물관리 데이터 연계, 홍수 분석 시뮬레이션, AI 댐 운영 최적화, AI 사면 정보 생성, 하천 제방 안전성 평가, AI 지능형 CCTV 영상분석, 간이 침수피해 예측, 드론 제약사항 조사 체계 개발을 포함하고 있다. 물관리 데이터와 하천 시설정보를 트윈 플랫폼 상에서 위치기반으로 시각화 표출하기 위해서는 유역의 공간정보를 3차원으로 구축하는 과정이 필수적이다. 따라서 GIS 기반의 섬진강 하천 중심 공간정보 구축을 위해 유역의 국가 정사영상과 5m 수치표고모형(DEM)은 최신성과를 협조 받아 적용하였으며, 홍수 분석을 위한 하천 중심 공간정보는 신규 헬기에 LiDAR 매핑을 수행하여 0.5m 급 DEM을 신규 구축하였다. 또한 하천 시설물 중 섬진강댐과 79개 주요 하천 횡단 교량과 3개 보 시설을 지상기준점 측량과 드론 매핑, 패턴 방식의 경량화 작업을 통해 트윈에 탑재할 수 있는 시설물 3D 객체 모델을 제작하였다. 홍수 분석을 위해서는 섬진강 유역에 대해 K-Drum, K-River, K-Flood 모델을 구축하였으며, AI 하천 수위 예측 학습 모델을 개발하였다. 섬진강 디지털 트윈 유역 물관리 플랫폼을 통해 데이터 기반의 똑똑한 물관리를 구현하고자 한다.

• Journal of the Korean Society of Radiology
• /
• v.85 no.4
• /
• pp.693-704
• /
• 2024

Artificial intelligence (AI) technology is actively being applied for the interpretation of medical imaging, such as chest X-rays. AI-based software medical devices, which automatically detect various types of abnormal findings in chest X-ray images to assist physicians in their interpretation, are actively being commercialized and clinically implemented in Korea. Several important issues need to be considered for AI-based detection assistant tools to be applied in clinical practice: the evaluation of performance and efficacy prior to implementation; the determination of the target application, range, and method of delivering results; and monitoring after implementation and legal liability issues. Appropriate decision making regarding these devices based on the situation in each institution is necessary. Radiologists must be engaged as medical assessment experts using the software for these devices as well as in medical image interpretation to ensure the safe and efficient implementation and operation of AI-based detection assistant tools.

• Review of KIISC
• /
• v.34 no.1
• /
• pp.27-32
• /
• 2024

블록체인 기반 NFT(Non-Fungible Token)는 자산 디지털화 및 소유권을 위한 독특한 기회를 제공하면서 디지털 경제를 변화시키는 원동력으로 등장했다. 블록체인 생태계 내에서 NFT의 급속한 출현은 디지털 자산 관리 및 소유권에 있어 중요한 발전을 의미한다. 본 연구는 기술 혁신, 시장 역학 및 규제 프레임워크의 역할을 강조하면서 블록체인 기반 NFT 서비스의 운영 전략을 검토하였다. 본 연구는 기술과 시장 역학의 교차점을 강조하면서 이더리움 블록체인에서 NFT의 기술적 토대, 확장성과 상호 운용성의 과제, 다양한 시장 관행의 의미를 연구한다. 디지털 경제에서 기능을 향상하는 것에 중점을 두고 NFT 표준화, 확장성 및 사용자 참여의 과제와 기회를 조사하여 다양한 시장 애플리케이션에 맞게 NFT 플랫폼을 최적화하는 데 대한 통찰력을 제공하는 것을 목표로 한다.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.259-278
• /
• 2022

With the spread of Artificial Intelligence (AI), various AI-based services are expanding in the financial sector such as service recommendation, automated customer response, fraud detection system(FDS), credit scoring services, etc. At the same time, problems related to reliability and unexpected social controversy are also occurring due to the nature of data-based machine learning. The need Based on this background, this study aimed to contribute to improving trust in AI-based financial services by proposing a checklist to secure fairness in AI-based credit scoring services which directly affects consumers' financial life. Among the key elements of trustworthy AI like transparency, safety, accountability, and fairness, fairness was selected as the subject of the study so that everyone could enjoy the benefits of automated algorithms from the perspective of inclusive finance without social discrimination. We divided the entire fairness related operation process into three areas like data, algorithms, and user areas through literature research. For each area, we constructed four detailed considerations for evaluation resulting in 12 checklists. The relative importance and priority of the categories were evaluated through the analytic hierarchy process (AHP). We use three different groups: financial field workers, artificial intelligence field workers, and general users which represent entire financial stakeholders. According to the importance of each stakeholder, three groups were classified and analyzed, and from a practical perspective, specific checks such as feasibility verification for using learning data and non-financial information and monitoring new inflow data were identified. Moreover, financial consumers in general were found to be highly considerate of the accuracy of result analysis and bias checks. We expect this result could contribute to the design and operation of fair AI-based financial services.