• 문화기술의 융합
• /
• 제9권3호
• /
• pp.647-654
• /
• 2023

딥러닝은 이미지, 텍스트와 같이 복잡한 데이터를 분류 및 인식하는데 유용한 방법으로 딥러닝 기법의 정확도는 딥러닝이 인터넷상의 AI 기반의 서비스를 유용하게 하는데 기초가 되었다. 그러나 딥러닝에서 훈련에 사용되는 방대한 양의 사용자 데이터는 사생활 침해 문제를 야기하였고 사진이나 보이스와 같이 사용자이 개인적이고 민감한 데이터를 수집한 기업들이 데이터들을 무기한으로 소유한다. 사용자들은 자신의 데이터를 삭제할 수 없고 사용되는 목적도 제한할 수 없다. 예를 들면, 환자 진료기록에 대한 딥러닝 기술을 적용하기 원하는 의료기관들과 같은 데이터소유자들은 사생활과 기밀유지 문제로 환자의 데이터를 공유할 수 없고 딥러닝 기술의 혜택을 받기 어렵다. 우리는 멀티 파티 시스템에서 다수의 작업자들이 입력 데이터집합을 공유하지 않고 신경망 모델을 공동으로 사용할 수 있는 프라이버시 보존 기술을 적용한 딥러닝 방법을 설계한다. 변형된 확률적 경사 하강에 기초한 최적화 알고리즘을 이용하여 하위 집합을 선택적으로 공유할 수 있는 방법을 이용하였고 결과적으로 개인정보를 보호하면서 학습 정확도를 증가시킨 학습을 할 수 있도록 하였다.

• Safety and Health at Work
• /
• 제14권3호
• /
• pp.303-308
• /
• 2023

Background: Occupational workers at altitudes are more prone to falls, leading to catastrophic outcomes. Acrophobia, height-related anxiety, and affected executive functions lead to postural instabilities, causing falls. This study investigated the effects of repeated virtual height exposure and training on cognitive processing and height-related anxiety. Methods: Twenty-eight healthy volunteers (age 20.48 ± 1.26 years; mass 69.52 ± 13.78 kg) were recruited and tested in seven virtual environments (VE) [ground (G), 2-story altitude (A1), 2-story edge (E1), 4-story altitude (A2), 4-story edge (E2), 6-story altitude (A3), and 6-story edge (E3)] over three days. At each VE, participants identified occupational hazards present in the VE and completed an Attitude Towards Heights Questionnaire (ATHQ) and a modified State-Trait Anxiety Inventory Questionnaire (mSTAIQ). The number of hazards identified and the ATHQ and mSTAIQ scores were analyzed using a 7 (VE; G, A1, A2, A3, E1, E2, E3) x 3 (DAY; DAY 1, DAY 2, DAY 3) factorial repeated measures analysis of variance. Results: The participants identified the lowest number of hazards at A3 and E3 VEs and on DAY 1 compared to other VEs and DAYs. ATHQ scores were lowest at G, A1, and E1 VEs. Conclusion: Cognitive processing is negatively affected by virtual altitudes, while it improves with short-term training. The features of virtual reality, such as higher involvement, engagement, and reliability, make it a better training tool to be considered in ergonomic settings. The findings of this study will provide insights into cognitive dual-tasking at altitude and its challenges, which will aid in minimizing occupational falls.

• 한국산업보건학회지
• /
• 제33권3호
• /
• pp.265-272
• /
• 2023

Objectives: Since the material safety data sheets(MSDS) submission and non-disclosure review system was introduced in January 2021, the implementation status of MSDS for chemical manufacturing and importing workplaces being supervised for the first time. Methods: A supervisory team consisting of two labor inspectors and one from the Korea Occupational Safety and Health Agency directly visited the selected workplaces to check compliance with the MSDS system as a whole. Results: As a result of supervising 214 chemical substance manufacturing/importing workplaces, a total of 241 violations of the law were found in 121 workplaces, or 57% of them. In response, the Ministry of Employment and Labor took legal action on 8 cases in 6 locations, imposed a fines totaling of 249.69 million won on 120 chemical handling workplaces, and took action to correct the violations immediately. Conclusions: Major violations were in the order of non-request for warning signs, non-submission of MSDS, non-execution of MSDS training, and non-posting of MSDS. This shows the reality that employers who handle chemical substances are sufficiently communicating chemical information to workers. In the future, the government will actively implement preparation and submission support and system guidance for the implementation of the MSDS system, while making efforts to ensure that the MSDS system works well in the field through thorough on-site supervision in the future.

• 한국환경보건학회지
• /
• 제50권3호
• /
• pp.169-180
• /
• 2024

Background: CAPSS missing evaporate emissions of volatile organic compounds (VOCs) from liquid cargo loading and unloading at ports. It needs to be supplemented to improve air quality management and allow more effective policy formulation. Objectives: In this study, the VOC emissions from the loading and unloading of liquid cargo at ports, which are not included in CAPSS, were estimated. The results of this study were compared and analyzed with the emission levels as described by CAPSS, confirming the need for managing VOC emissions from the loading and unloading of liquid cargo. Methods: Methodology provided by the U.S. Environmental Protection Agency (EPA) was applied to estimate the VOC emissions from the loading and unloading of liquid cargo at ports. The types of liquid cargo loaded at unloaded at ports are diverse, but for this study emissions were estimated for 37 VOCs designated by the Ministry of Environment. Results: The estimated results for VOC emissions from liquid cargo loading and unloading at domestic ports was 112,079 tons/yr, which was confirmed to be 11% of the known CAPSS emissions. The highest emissions were found from the loading and unloading of naptha, and the port with the highest emissions was Ulsan Port. Conclusions: The results of the estimated VOC emissions from liquid cargo loading and unloading at ports confirmed the high emission levels. To protect the health of port workers and nearby residents, it is essential to manage the emission sources and undertake continuous research.

• Safety and Health at Work
• /
• 제15권1호
• /
• pp.87-95
• /
• 2024

Background: This study focuses on assessing occupational risk for the health hazards encountered during maintenance works (MW) in semiconductor fabrication (FAB) facilities. Objectives: The objectives of this study include: 1) identifying the primary health hazards during MW in semiconductor FAB facilities; 2) reviewing the methods used in evaluating the likelihood and severity of health hazards through occupational health risk assessment (OHRA); and 3) suggesting variables for the categorization of likelihood of exposures to health hazards and the severity of health effects associated with MW in FAB facilities. Methods: A literature review was undertaken on OHRA methodology and health hazards resulting from MW in FAB facilities. Based on this review, approaches for categorizing the exposure to health hazards and the severity of health effects related to MW were recommended. Results: Maintenance workers in FAB facilities face exposure to hazards such as debris, machinery entanglement, and airborne particles laden with various chemical components. The level of engineering and administrative control measures is suggested to assess the likelihood of simultaneous chemical and dust exposure. Qualitative key factors for mixed exposure estimation during MW include the presence of safe operational protocols, the use of air-jet machines, the presence and effectiveness of local exhaust ventilation system, chamber post-purge and cooling, and proper respirator use. Using the risk (R) and hazard (H) codes of the Globally Harmonized System alongside carcinogenic, mutagenic, or reprotoxic classifications aid in categorizing health effect severity for OHRA. Conclusion: Further research is needed to apply our proposed variables in OHRA for MW in FAB facilities and subsequently validate the findings.

• Safety and Health at Work
• /
• 제14권4호
• /
• pp.375-383
• /
• 2023

Background: Working despite feeling ill - presenteeism - is a widespread behavioral phenomenon. Previous research has shown that presenteeism is influenced by various work-related and personal factors. It's an illness behavior leading to a range of negative but also positive consequences. Due to coronavirus disease 2019 (COVID-19) pandemic, remote work has become the "new normal" for many employees. But so far, little is known about presenteeism in remote work. This study aims to investigate presenteeism in remote work by looking at the extent of remote presenteeism, differences to presenteeism in on-site work, and associated factors. Methods: A nationwide cross-sectional online survey was conducted in Germany with N = 233 participants. Data were analyzed using descriptive statistics, t-tests, and correlation analysis. Results: The results reveal that presenteeism is prevalent in remote work x = 4.13 days (Md = 3; D = 2; s = 4.95). A low ability to detach from work (r = -.17; p = .005) and low supervisor support (r = -.14; p = .02) is associated with more remote presenteeism days. Remote working conditions seem to facilitate presenteeism. Conclusion: This study provides empirical insights into a subject area of great societal relevance. The results show that awareness should be raised for presenteeism in remote work. It should be regarded as a behavior that can be functional or dysfunctional, depending on the individual situation. Supervisor support and detachment should be fostered to help reduce dysfunctional presenteeism. Promotion of health literacy might help remote workers to decide on a health-oriented illness behavior. Further research is vital to analyze to what extent and under which circumstances presenteeism in remote work is (dys)functional and to derive clear recommendations.

• Safety and Health at Work
• /
• 제14권4호
• /
• pp.467-475
• /
• 2023

Background: To mitigate the spread of Covid-19, nurses infected with the virus were required to isolate themselves from their families and community. Isolated patients were reported to have experienced mental distress, posttraumatic stress disorder symptoms, and suicide. Though studies have reported the psychological impact of the Covid-19 pandemic, less is known about the lived experiences of nurses who survived Covid-19 infection in sub-Saharan Africa. Methods: A descriptive phenomenological approach was used to study the lived experiences of registered nurses who survived Covid-19 disease. In-depth interviews were conducted among nurses diagnosed with Covid-19 from two hospitals in Kenya between March and May, 2021. Purposive and snowball sampling were used to recruit registered nurses. Data were analyzed using Giorgi's steps of analysis. Results: The study included ten nurses between 29 and 45 years of age. Nurses' experiences encompassed three themes: diagnosis reaction, consequences, and coping. Reactions to the diagnosis included fear, anxiety, and sadness. The consequence of the diagnosis and isolation was stigma, isolation, and loneliness. Nurses coping mechanisms included acceptance, creating routines, support, and spirituality. Conclusion: Our findings aid in understanding how nurses experienced Covid-19 infection as patients and will provide evidence-based content for supporting nurses in future pandemics. Moreover, as we acknowledge the heroic contribution of frontline healthcare workers during the Covid-19 pandemic, it is prudent to recognize the considerable occupational risk as they balance their duty to care, and the risk of infection to themselves and their families.

• 문화기술의 융합
• /
• 제10권3호
• /
• pp.801-807
• /
• 2024

선형 로봇은 자동화 시스템에서 부품의 이송이나 위치 결정에 널리 사용되며 보통 높은 정밀도가 요구된다. 선형 로봇을 응용한 시스템의 제작회사에서는 로봇의 이상 유무를 작업자가 판단하는데, 작업자의 숙련도에 따라 이상 상태를 판단하는 정확도가 달라진다. 최근에는 인공지능 등의 기술을 사용하여 로봇 스스로 이상을 검출하는 방법에 관한 연구가 진행되고 있다. 본 논문에서는 전이 학습을 이용하여 선형 로봇의 볼 스크류 정렬 이상과 선형 레일 정렬 이상을 검출하는 시스템을 제안하고 가속도 센서와 토크 센서 정보를 이용한 별개의 실험을 통해 제안한 시스템의 이상 검출 성능을 검증 및 비교한다. 센서로부터 얻어진 신호를 스펙트로그램 이미지로 변환한 후, 영상 인식 인공지능 분류기를 사용하여 이상의 종류를 진단하였다. 제안한 방법은 선형 로봇뿐만 아니라 일반적인 산업용 로봇에도 적용할 수 있을 것으로 기대한다.

• 미래기술융합논문지
• /
• 제3권3호
• /
• pp.47-56
• /
• 2024

본 연구는 사회복지학과 성인학습자의 사회복지현장실습경험을 분석하고 개선점을 논의하는 것을 목적으로 한다. 사회복지현장실습은 사회복지사가 되기 위한 필수과정이다. 사회복지현장실습을 통해 성인학습자들은 이론적으로 배운 교육을 실제 현장에서 적용하고 예비사회복지사로서 미래의 역할을 이해할 수 있는 소중한 기회를 얻을 수 있다. 그러나 사회복지현장실습이 성인학습자의 특성을 적절하게 반영하지 못한다면 성공적인 사회복지현장실습 경험을 보장하기 어려울 수 있다. 성인학습자가 사회복지실습을 성공적으로 마무리 짓기 위해서는 대학과 실습기관의 통합적이고 일관된 지원이 필수적이다. 성인학습자의 실습경험에서 직면할 수 있는 어려움은 시간 관리의 힘듦, 심리적 스트레스, 이론과 실제의 간극 등이 있는데 이러한 문제를 해결하는 것이 필요하며, 가장 중요한 것은 실습 전 철저한 준비가 선행되어야 하겠다.

• 문화기술의 융합
• /
• 제10권4호
• /
• pp.367-372
• /
• 2024

발달장애는 전체 장애인 수 중에 비교적 낮은 수치에 해당되지만 장애의 정도에서 전반적으로 중증 장애로 분류되고 있다. 이러한 발달장애는 초기에 발견이 된다면 적응력과 초기 대응에 의한 치료 효과가 향상될 수 있지만, 대부분의 부모들은 자신의 아이에게서 징후를 발견하지 못하거나 치료시기를 놓치는 경우가 대다수이다. 본 논문에서는 특이적 행동특성을 기반으로 하는 초기 발달장애 징후를 객관적으로 볼 수 없는 부모나 유아기관 관계자들을 위해 발달장애 초기 특이행동 중 손 퍼덕대기(Hand-Flapping)를 인식할 수 있는 발달장애 진단 알고리듬개발의 선행연구를 수행하였다. 인지영역과 손가락을 정확하게 인식하여, 손퍼덕임 수를 정확하게 카운트하는 것을확인할 수 있었다. 빅데이터를 활용한 알고리듬의 고도화 및 기능적 성능 확장을 통해 다양한 행동패턴의 진단이 가능한 알고리듬 연구가 지속적으로 수행 및 확대될 것으로 전망된다.