• 한국환경보건학회지
• /
• 제47권1호
• /
• pp.101-109
• /
• 2021

Objectives: The objectives of this study are to introduce the development process of work situations and types in the revised regulations on wearing personal protective equipment (PPE) for hazardous chemical handlers, analyze the implementation of the regulations, and then provide basic data for future education strategies. Methods: The development process of work situations for regulation was explained through a flowchart by year. In 2018, a survey of 30 chemical managers and 201 managers and handlers was conducted based on recognition of work situations and the related regulations. In 2019, 91 chemical managers and 204 handlers were surveyed to find the degree of compliance with regulations, direction for improvement of understanding the regulations, and training methods. Results: Only 78.0% of chemical managers and 66.7% of handlers said they were aware of the regulations (p<0.05). Just 79.0% of handlers knowing the regulations said they would wear PPE in compliance with these regulations. Therefore, the best way to make workers wear proper PPE in accordance with regulations is to strengthen the promotion of education on regulations. In order to improve the quality of education, 51.7% of managers and 33.3% of handlers cited educational content (video, ppt, etc.) as the top priority. Conclusion: This study suggested that more educational opportunities should be provided and educational content should be developed in order for workers handling hazardous chemicals to wear PPE as prescribed in regulations.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권1호
• /
• pp.41-50
• /
• 2023

최근에 인공지능 기술발전과 더불어 코로나19 바이러스(COVID-19)가 장기화되면서 비대면 사회가 일상화되었고, 많은 기업들은 이에 대응하기 위한 디지털 트랜스포메이션과 인공지능 도입의 활성화를 촉진시키고 있으며 챗봇의 수요가 급격히 늘어났다. 또한 챗봇은 기존의 단순문의 대응에서 업무 트랜잭션 처리를 하기에 이르렀다. 하지만 기존 시스템과 연계를 위해 API를 개발해야하고 연계 하는데 많은 어려움이 발생하고 있어, 이를 해결하기 위해 RPA연계를 통한 하이브리드 챗봇을 구축하는 것이 점점 중요해지고 있으며, 최근 RPA와 챗봇의 결합이 많은 비즈니스 프로세스를 처리하는 효과적인 도구로 간주되고 있다. 그러나 연계사례 부족과 구축 방법을 찾아보기 힘들어 많은 어려움을 겪고 있다. 본 연구에서는 기존 선행연구 고찰과 하이퍼오토메이션 관점에서 Conversational UX인 챗봇과 Task Automation의 RPA를 연계한 하이브리드 챗봇 구축을 위한 방법을 실제 구현사례를 바탕으로 제시하여, 보다 쉽게 연계방법을 이해하고 구축할 수 있도록 하여 디지털 트랜스포메이션에 적극적으로 AI 챗봇을 활용할 수 있도록 하는데 시사점이 있다.

• KNOM Review
• /
• 제24권1호
• /
• pp.20-28
• /
• 2021

소셜 미디어 애플리케이션 및 모바일 장치의 광범위한 사용으로 인해 데이터 트래픽이 지속해서 증가하고 있다. 소셜 미디어 애플리케이션은 끝없이 많은 양의 멀티미디어 트래픽, 특히 비디오 트래픽을 생성하고 있다. YouTube, Daily Motion 및 Netflix와 같은 많은 소셜 미디어 플랫폼이 생성하는 것이다. 이러한 플랫폼에서는 다른 비디오와 비교하여 몇 개의 인기 비디오가 여러 번 요청된다. 이러한 인기 있는 비디오는 지속적인 사용자 요구 사항을 충족하기 위해 사용자 주변에 캐시해야 한다. MEC는 일관된 사용자 요구와 사용자 근접 캐시를 위한 필수 패러다임으로 부상했다. 시간에 따라 사용자 요구 패턴이 어떻게 달라지는지를 이해하는 것이 과제이다. 본 논문은 공개 데이터셋인 MovieLens 20M, MovieLens 100K, The Movies Dataset 3개를 분석하여 시간에 따른 사용자 요청 패턴을 찾는다. 모든 데이터셋의 시간별, 일별, 월별 및 연간 추세를 확인할 수 있다. MEC 기반 비디오 캐시 시나리오에서 사용자 요청 패턴을 분석 및 생성함으로써, 많은 연구에서 사용될 수 있을 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2257-2285
• /
• 2022

Cyber-physical systems (CPS) have been growing exponentially due to improved cloud-datacenter infrastructure-as-a-service (CDIaaS). Incremental expandability (scalability), Quality of Service (QoS) performance, and reliability are currently the automation focus on healthy Tier 4 CDIaaS. However, stable QoS is yet to be fully addressed in Cyber-physical data centers (CP-DCS). Also, balanced agility and flexibility for the application workloads need urgent attention. There is a need for a resilient and fault-tolerance scheme in terms of CPS routing service including Pod cluster reliability analytics that meets QoS requirements. Motivated by these concerns, our contributions are fourfold. First, a Distributed Non-Recursive Cloud Model (DNRCM) is proposed to support cyber-physical workloads for remote lab activities. Second, an efficient QoS stability model with Routh-Hurwitz criteria is established. Third, an evaluation of the CDIaaS DCN topology is validated for handling large-scale, traffic workloads. Network Function Virtualization (NFV) with Floodlight SDN controllers was adopted for the implementation of DNRCM with embedded rule-base in Open vSwitch engines. Fourth, QoS evaluation is carried out experimentally. Considering the non-recursive queuing delays with SDN isolation (logical), a lower queuing delay (19.65%) is observed. Without logical isolation, the average queuing delay is 80.34%. Without logical resource isolation, the fault tolerance yields 33.55%, while with logical isolation, it yields 66.44%. In terms of throughput, DNRCM, recursive BCube, and DCell offered 38.30%, 36.37%, and 25.53% respectively. Similarly, the DNRCM had an improved incremental scalability profile of 40.00%, while BCube and Recursive DCell had 33.33%, and 26.67% respectively. In terms of service availability, the DNRCM offered 52.10% compared with recursive BCube and DCell which yielded 34.72% and 13.18% respectively. The average delays obtained for DNRCM, recursive BCube, and DCell are 32.81%, 33.44%, and 33.75% respectively. Finally, workload utilization for DNRCM, recursive BCube, and DCell yielded 50.28%, 27.93%, and 21.79% respectively.

• 지능정보연구
• /
• 제29권1호
• /
• pp.203-214
• /
• 2023

우리나라 관세청은 효과적인 원스톱(One-stop) 업무 처리가 가능한 전자통관 시스템으로 효율적으로 업무처리를 하고 있지만 기술의 발달과 비대면 서비스의 증가로 매년 수출입건수가 증가하고 있으며 그에 따른 업무량도 폭증하고 있는 실정으로 이에 따른 보다 효과적인 방법이 매우 필요하다. 수입과 수출은 모든 물품에 대한 분류 및 세율 적용을 위한 HS Code(Harmonized system code)가 필요하고 해당 HS Code를 분류하는 품목 분류는 전문지식과 경험이 필요한 업무 난이도가 높고 관세 통관절차에서 중요한 부분이다. 이에 본 연구는 품목 분류 의뢰서의 물품명, 물품상세설명, 물품 이미지 등의 다양한 유형의 데이터 정보를 활용하여 멀티모달 표현 학습(Multimodal representation learning) 기반으로 정보를 잘 반영할 수 있도록 딥러닝 모델을 학습 및 구축하여 HS Code를 분류 및 추천해 줌으로써 관세 업무 부담을 줄이고 신속한 품목 분류를 하여 통관절차에 도움을 줄 것으로 기대한다.

• 한국보건간호학회지
• /
• 제37권2호
• /
• pp.247-260
• /
• 2023

Purpose: The purpose of this study was to gain an in-depth understanding of the characteristics and competencies of practice experienced by public health center nurses(PHNs) during the early response phase of the coronavirus disease 2019(COVID-19) pandemic. Methods: PHNs were recruited from public health centers(PHC) in ten cities in Korea, using purposive sampling. They participated in semi-structured, in-depth interviews from December 21, 2020, to February 18, 2021. The interviews were transcribed verbatim and analyzed using qualitative content analysis. Results: Three themes and nine categories were drawn from the findings. The three themes that emerged from the data analysis were as follows: 'Handling expanding work scope and overwhelming workload beyond prepared competencies, willing to go anywhere.', 'Performing tasks of cooperation and communication required in the disaster management administrative system.', 'Demonstrated proficiency in clinical nursing practices, but recognized the need for further development of leadership and administrative capabilities.' Conclusions: The experiences of the subjects' have implications for the development of content for community nursing education that cultivates basic competencies to respond to real pandemic situations during undergraduate education. It is proposed that it would be necessary to establish a support system for developing specialized competencies in public health nursing.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.190-203
• /
• 2023

The purpose of this study is to provide basic data to ensure the safety and essential performance of a Lower Extremity robotic assisted gait training system and to provide advanced technology and technical basis to the industry handling the system. Based on IEC 60601-1:2012/AMD2:2020 (Medical Electrical Equipment - General requirements for basic safety and essential performance of medical electrical equipment), IEC 62366-1:2015/AMD1:2020 (Medical devices - Part 1: Application of usability engineering to medical devices) and EN ISO 14971:2019 (Medical devices - Application of risk management to medical devices), the requirements for ensuring the safety and essential performance of the Lower Extremity robotic assisted gait training system were derived. Through the Delphi survey method and scenario analysis, which reflects the opinions and knowledge of experts in the fields of development, testing and review of technical documents, and quality assurance of medical devices, validity and reliability were conducted and obtained results with adequate content validity ratio (CVR; 0.7≤) and excellent reliability (Cronbach's α; 0.9≤). As a result, it was confirmed that the reliability and validity of the risk management process to ensure the safety and essential performance of the Lower Extremity robotic assisted gait training system are required a model can be established to provide measures to reduce risks according to the level of risk exposure caused by usage.

• Journal of Trauma and Injury
• /
• 제36권1호
• /
• pp.15-21
• /
• 2023

Purpose: Dental avulsion injuries have a poor prognosis that largely depends on the immediate steps taken to manage the avulsed tooth. A lack of knowledge about the initial management can lead to tooth loss, with further adverse implications for esthetics, phonetics, and overall growth and function. Hence, the present study aimed to assess parents' knowledge regarding dental avulsion and the variables associated with their knowledge of avulsion injuries. Methods: A series of closed-ended questions on parents' knowledge regarding avulsion, such as immediate management, storage media, handling, and urgency of visiting the dentist, was asked. Univariate associations between the outcomes were assessed using the Pearson chi-square test. The chisquare goodness-of-fit test was used to check whether the sample data were representative of the population. Results: In total, 211 mothers and 149 fathers were included, of whom 46.7% had experienced dental trauma during their own childhood. Sixty-one percent of mothers believed that they knew everything necessary about tooth avulsion and its management. A significant number of participants who thought that they had a good level of knowledge about avulsion chose water, tissue, or paper wrap to transport the tooth, and preferred tap water, alcohol, or antiseptic to clean the avulsed tooth. Conclusions: Both mothers and fathers had poor knowledge about tooth avulsion, indicating that there is an immediate need for educational programs focusing on this issue. Since a substantial proportion of participants believed incorrect information, it is vital to disseminate accurate information.

• 대한방사선기술학회지:방사선기술과학
• /
• 제46권2호
• /
• pp.131-139
• /
• 2023

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R² to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R² 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R² 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R² 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R² 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

• 한국학교수학회논문집
• /
• 제26권1호
• /
• pp.1-19
• /
• 2023

본 연구는 최근 교육 분야에서 인공지능을 활용한 연구 동향을 파악하기 위해 관련 연구 논문을 대상으로 텍스트 마이닝 기법 중 토픽모델링과 시계열 기반 트렌드 분석 기법을 활용하여 분석을 실시하였다. 분석 대상으로는 다양한 학문 영역에서 컴퓨터 활용 교육 연구에 초점을 두는 '교육에서의 인공지능 국제학회(International Society of Artificial Intelligence in Education)'에서 발행하는 SCOPUS 저널에 2003년부터 2020년까지 게재된 총 352편의 논문을 사용하였다. 분석 결과 빈도수가 높은 단어들을 조합하여 8개의 토픽을 추출하였으며, 이를 통해 인공지능을 활용한 교육 연구에서 중요시 여기는 관점을 파악해 나감과 동시에 교과별로 인공지능을 교육에서 활용하는 내용과 목적에 차이점이 있음을 알 수 있었다. 또, 학습 시스템에서 학생 행동 모델을 분석하고 학생 응답 및 반응에 대한 피드백을 개발하는 연구는 점차 증가한 반면, 데이터 처리 방법에 대한 연구는 최근 들어 감소하는 경향이 나타났다. 연구 결과를 토대로 향후 교육에서 인공지능을 활용한 연구에 필요한 주제 및 방향에 대한 시사점을 제공하였다.