• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.124-132
• /
• 2022

Recently, due to COVID-19, online remote classes and non-face-to-face exams have made it difficult to manage class attitudes and exam cheating. Therefore, there is a need for a system that automatically recognizes and detects the behavior of students online. Action recognition, which recognizes human action, is one of the most studied technologies in computer vision. In order to develop such a technology, data including human arm movement information and information about surrounding objects, which can be key information in online classes and exams, are needed. It is difficult to apply the existing dataset to this system because it is classified into various fields or consists of daily life action. In this paper, we propose a dataset that can classify attitudes in real-time online tests and classes. In addition, it shows whether the proposed dataset is correctly constructed through comparison with the existing action recognition dataset.

• Journal of the Korean Society of Floral Art and Design
• /
• no.40
• /
• pp.63-75
• /
• 2019

In this study, convergence art education which Based on the overall understanding of color, which is a field of science, the lecture model was constructed in order to operate a fusion curriculum which can be practically expressed by applying it to the artistic field of floral design. The learner was satisfied with the composition of the two lectures (floral design, color) and the way of conducting theory and practice. In addition, they felt that was able to access various areas through one subject. This indicates that learners themselves perceive the purpose and necessity of this study. On the other hand, it is pointed out that the background knowledge level between the majors and the non - majors is different. therefore Continuous feedback and adjustment of the degree of difficulty of the training seems to be necessary to enhance the learner's understanding. In order to develop the floral design, the curriculum development and education model should be built through convergence of various sciences. It is expected that this study will be used as basic data for the development of the curriculum for the artistic design education.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.119-124
• /
• 2023

Deep learning has recently demonstrated conspicuous efficacy across diverse domains than traditional machine learning techniques, as the most popular approach for pattern recognition. The classification problems for tabular data, however, are remain for the area of traditional machine learning. This paper introduces a novel network module designed to tabular data into high-dimensional tensors. The module is integrated into conventional deep learning networks and subsequently applied to the classification of structured data. The proposed method undergoes training and validation on four datasets, culminating in an average accuracy of 90.22%. Notably, this performance surpasses that of the contemporary deep learning model, TabNet, by 2.55%p. The proposed approach acquires significance by virtue of its capacity to harness diverse network architectures, renowned for their superior performance in the domain of computer vision, for the analysis of tabular data.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.36-44
• /
• 2024

This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.

• Korean Security Journal
• /
• no.25
• /
• pp.1-25
• /
• 2010

This research aims to provide a solution for the improvement of private security according to the change in criminal environment. The main cause of crime can be found in the anti-functional dimensions including value set disorder, social phenomenon variation, information-based, globalization and urbanization. In this environment, the private security sector has dramatically increased in a quantitative viewpoint, but it is insufficient in a qualitative viewpoint. This paper recognized this problem and demonstrates a solution for improvement through classifying elements of private security into relevant legislation, education institutions, security companies and security associations. The analysis result is a follows: First, motivation and satisfaction rate of escort and security related major has shown to be high. However, respondents evaluated the guard educational institution negatively. Second, the motivation of entering into the private security sector for internal staffs has shown to be positive and sound. However, the job satisfaction rate has shown to be low due to excessive competition, negative perception of occupation and low earning. Third, respondents gave an average mark to the Security Association's management and operation. In addition, the mutual-aid project received the same mark. Negative feedbacks were given to the protection of member's interest and to association operation and policy, while positive feedbacks were given to the degree of member's cooperation towards association policies.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2018.06a
• /
• pp.116-116
• /
• 2018

부식은 재료와 사용 환경과의 상호작용에 의한 결과로서 일반적으로 두께의 감소와 균열의 발생 및 파손 등의 문제로 나타난다. 특히 사용환경 중에서 해수 분위기는 금속의 부식에 가장 유리한 조건이다. 따라서 해양환경 중 항만이나 조선 및 해양 산업 등에 많이 이용되는 강 구조물은 이에 대응하기 위하여 도장방식이나 음극방식을 사용하고 있다. 여기서 음극방식은 피방식체를 일정전위로 음극 분극하는 원리로써 외부전원을 인가하거나 비전위의 금속을 전기적으로 연결하여 방식하는 방법이다[1]. 한편, 해수 중에서 이와 같은 원리로 음극방식 할 경우에는 피방식체인 강재표면에 부분적으로 칼슘 또는 마그네슘 화합물 등의 생성물이 부착하는 현상을 볼 수 있게 된다. 이와 같이 수산화마그네슘($Mg(OH)_2$)및 탄산칼슘($CaCO_3$)을 주성분으로 하여 석출되는 석회질 피막(calcareous deposits)은 피방식체에 유입되는 음극방식 전류밀도를 감소시켜 주거나 물리적 장벽의 역할을 함으로써 외부의 산소와 물 등 부식환경으로부터 소지금속을 보호한다[2]. 그러나 석회질 피막은 소지금속과의 결합력, 막의 균일한 분포, 내식성 및 제작시간의 단축 등 해결해야 할 과제가 있다. 또한 여러 가지 환경 조건 등의 영향을 받아 그 피막의 형성 정도도 가늠하기 어렵기 때문에 음극방식 설계 시 그 정도에 따른 영향을 고려-반영하기가 곤란하다. 따라서 본 연구에서는 석출속도, 밀착성 및 내식특성을 향상시키기 위해 전착프로세스를 통해 해수 중 기체를 용해시켜 석회질 피막을 제작하고 막의 결정구조 제어 및 특성을 분석-평가하였다. 본 연구에 사용된 강 기판(Steel Substrate)은 일반구조용강(KS D 3503, SS400)을 사용하였으며, 외부전원은 정류기(Rectifier, xantrex, XDL 35-5T)를 사용하여 3 및 $5A/m^2$의 조건으로 인가하였다. 양극의 경우에는 해수에 녹아있는 이온 이외에 다른 성분들이 환원되는 것을 방지하기 위해 불용성 양극인 탄소봉(Carbon Rod)을 사용하였다. 이때 석출속도, 밀착성 및 내식특성 향상을 위해 해수에 주입한 기체의 양은 0.5 NL/min였으며, 기판 근처에 고정하여 음극 부근에서의 반응을 유도하였다. 각 조건별로 제작된 막의 표면 모폴로지, 조성원소 및 결정구조 분석을 실시하였으며, 석회질 피막의 밀착성과 내식특성을 평가하기 위해 규격에 따른 테이핑 테스트(Taping Test, ISO 2409)와 3 % NaCl 용액에서 전기화학적 양극 분극 시험을 진행하여 제작된 막의 내구성과 내식성을 분석-평가하였다. 시간에 따른 전착막의 외관관찰 결과 전류밀도의 증가와 함께 상대적으로 많은 피막이 형성되었고, 용해시킨 기체에 의해 더 치밀하고 두터운 피막이 형성됨을 확인할 수 있었다. 성분 및 결정구조 분석 결과 $Mg(OH)_2$ 성분의 Brucite 및 $CaCO_3$ 성분의 Calcite 및 Aragonite 구조를 확인하였으며, 용해시킨 기체의 영향으로 $CaCO_3$ 성분의 Aragonite 구조가 상대적으로 많이 검출되었다. 밀착성 및 내식성 평가를 실시한 결과 해수 중 용해시킨 기체에 의해 제작한 시편의 경우 견고하고 화학적 친화력이 높은 Aragonite 결정이 표면을 치밀하게 덮어 전해질로부터 산소와 물의 침입을 차단하는 역할을 하여 기체를 용해시키지 않은 3 및 $5A/m^2$ 보다 비교적 우수한 밀착성 및 내식 특성을 보이는 것으로 사료된다.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2016.11a
• /
• pp.164-164
• /
• 2016

항만 및 해양 구조물은 육상과는 비교할 수 없을 정도로 가혹한 해수 환경에서 사용되며 계속적으로 부식 손상을 받는다. 따라서 강구조물이 장기적으로 안전하게 사용되기 위해서는 적절한 방식은 물론 철저한 유지관리가 필수적이다. 한편, 현재 해양환경 중 항만, 조선, 해양산업 등에 많이 이용되는 강구조물은 이에 대응하기 위하여 일반적으로 도장방식이나 음극방식이 사용되고 있다. 음극방식은 피방식체를 일정전위로 음극 분극하는 원리로써 외부전원을 인가하거나 비전위의 금속을 희생양극으로 연결하여 방식하는 방법이다. 이와같이 해수 중 음극방식을 실시할 경우 해수 중 용존하는 많은 이온들 중에서 특히 $Ca^{2+}$ 이나 $Mg^{2+}$ 이온이 탄산칼슘, 수산화마그네슘을 주성분으로하는 화합물로 형성된다. 이렇게 생성된 전착막은 산소 확산을 방지하는 물리적 장벽을 형성하고 부식율을 감소시키는 것으로 보고되고 있다. 그러나 전착막은 소지 금속과의 결합력이 불균일 함은 물론 막을 형성하는데 있어서 장시간이 소요된다는 단점이 있다. 따라서 본 연구에서는 해수 중 음극방식 응용 원리에 의해 전착막을 형성하고, 석출속도, 밀착성 및 내식특성을 향상시키기 위해 해수 중 기체를 용해시켜 제작한 막의 특성을 분석-평가하였다. 본 연구에 사용된 기판(substrate)은 일반구조용 강(SS400)을 사용하였으며, 면적은 $70mm{\times}30mm$, 두께는 1 mm로 제작하여 실험을 진행하였다. 외부전원은 정류기(Rectifier, xantrex, XDL 35-5T)를 사용하여 3 및 $5A/m^2$ 의 조건으로 인가하였고, 양극은 Carbon Rod를 사용하였다. 이때 해수에 주입한 이산화탄소의 양은 0.5 NL/min 였다. 각 조건별로 제작된 전착막에 대해 외관관찰, 석출량, 모폴로지, 조성원소 및 결정구조 분석을 실시하였고, 밀착성 및 내식특성을 평가하기 위해 테이핑 테스트(Taping Test, JIS K 5600-5-6)와 3.5 % NaCl 용액에서 전기화학적 양극 분극 시험을 진행하였다. 시간에 따른 전착막의 외관관찰 결과 전류밀도의 증가와 함께 상대적으로 많은 피막이 형성되었고, 용해시킨 기체에 의해 더 치밀하고 두터운 피막이 형성됨을 확인할 수 있었다. 성분 및 결정구조 분석 결과 $Mg(OH)_2$ 성분의 Brucite 및 $CaCO_3$ 성분의 Calcite 구조 및 Aragonite 구조를 확인하였으며, 용해시킨 기체의 영향으로 $CaCO_3$ 성분의 Aragonite 구조가 상대적으로 많이 검출되었다. 이는 해수 중 용해된 이산화탄소의 영향으로 인해 풍부한 ${CO_3}^{2-}$ 이온이 형성되고 용액 pH를 낮게 유지시켜 Ca 화합물 형성이 용이한 환경이 조성되는 것으로 판단된다. 밀착성 및 내식성 평가를 실시한 결과 해수중 용해시킨 기체에 의해 제작한 시편의 경우 견고하고 화학적 친화력이 높은 Aragonite 결정이 표면을 치밀하게 덮어 전해질로부터 산소와 물의 침입을 차단하는 역할을 하여 기체를 용해시키지 않은 $3A/m^2$ 및 $5A/m^2$ 보다 비교적 우수한 밀착성 및 내식 특성을 보이는 것으로 사료된다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.3
• /
• pp.73-97
• /
• 2013

This study examined Records Management(RM) practice of public enterprises supervised by National Archives of Korea(NAK). These enterprises are included among public institutions mandated to perform RM according to Public Records Management Act of 2006. The study performed telephone interviews of 8 records managers employed in public enterprises and investigated current status of RM practices, perception of the practices and records managers within the enterprises and treatment to them, as well as opinions of the NAK's assessment of RM in public institutions, While non-electronic records were managed in an appropriate manner, electronic records needed to be transferred, disposed of, and preserved properly. The majority of interviewees expressed positive opinions on the contribution of RM to effectiveness and transparency of the enterprises. However, RM was perceived as irksome work conducted by those in a low position. More interviewees were permanent contract workers or contract personnel than regular employees. They felt a sense of deprivation due to the discrepancy of annual incomes among public enterprises and the differences in treatment and attitude toward between contract workers and regular workers. Interviewees suggested that NAK's assessment of RM was useful since it provided a basis for RM in their institutions. Yet, they pointed out that its measurements were lack of consistency and relevance to public enterprises because those focused on RM in governmental organizations. They also noted that RM practices that the assessment do not cover might be ignored.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.5
• /
• pp.48-59
• /
• 2021

In this study, experiments were conducted to investigate the compressive·flexural performances of single fiber-reinforced mortar (FRM) using only steel fiber or carbon fiber which has different material properties as well as hybrid FRM using a mixture of steel and carbon fibers. The mortar specimens incorporated steel and carbon fibers in the mix proportions of 1+0%, 0.75+0.25%, 0.5+0.5%, 0.25+0.75% and 0+1% by volume at a total volume fraction of 1.0%. Their mechanical performance was compared and examined with a plain mortar without fiber at 28 days of age. The experiments of mortar showed that the hybrid FRM using a mixture of 0.75% steel fibers + 0.25% carbon fibers had the highest compressive and flexural strength, confirming by thus the synergistic reinforcing effect of the hybrid FRM. On the contrast, in the case of hybrid FRM using a mixture of 0.5% steel fibers + 0.5% carbon fibers witnessed the highest flexural toughness, suggesting as a result the optimal fiber mixing ratio of hybrid FRM to improve the strength and flexural toughness at the same time. Moreover, the fracture surface was observed through a scanning electron microscope (SEM) for image analysis of the FRM specimen. These results were of great help for images analysis of hybrid reinforcing fibers in cement matrix.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.6
• /
• pp.175-181
• /
• 2022

The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built during the period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safety accidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for research to detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomous inspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular, the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026 damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04% and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the near future.