• 문화기술의 융합
• /
• 제8권6호
• /
• pp.861-866
• /
• 2022

서울시에서는 공유 자전거 시스템, "따릉이"를 2015년부터 도입, 운영하여, 교통량 감축과 대기오염 해소를 위해 노력하고 있다. 하지만 공유 자전거 시스템, "따릉이"의 운영전략 미훕으로 인해 많은 문제가 발생하고 있어 이를 해결하고자 다양한 연구들이 제시되고 있다. 이들 연구의 대다수는 수요와 공급의 불균형을 해결하고자 하는 전략적 "자전거 배치"에 집중되어 있으며 또한 이들 중 다수가 날씨나 계절과 같은 특징을 그룹화함으로써 수요를 예측하고 있다. 그리고 이전에는 이들 예측방법이 주로 시계열 분석을 기반으로 하고 있었으나 최근에는 딥러닝/머신러닝으로 수요를 예측하는 연구들이 속속 등장하고 있다. 본 논문에서는 기존에 제시된 다양한 특징들을 기반으로 하면서, 새로운 특징을 발견하고 선택된 특징들의 중요도를 비교, 이를 순서화함으로써, 보다 정확한 수요 예측이 가능함을 보인다. 그리하여, 우리는 기존의 딥러닝/머신러닝 및 시계열 분석을 그대로 사용하면서 비교적 정확한 결정계수를 획득하고 이를 이용해 개선된 수요예측이 가능하도록 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.549-561
• /
• 2021

Indonesia has policies and strategies for the management of radioactive waste and spent nuclear fuel that arises from the use of nuclear research and development facilities, including three research reactors, and the use of radioisotopes in medicine and industries. The Indonesian government has provided extensive facilities such as an independent regulatory organization (BAPETEN) and a centralized radioactive waste management organization (CRWT-BATAN). Further, the presence of regulations and several international conventions guarantee the protection of the public from all risks due to handling radioactive waste and spent nuclear fuel. However, the sustainability of radioactive waste management in the future faces various challenges, such as disposal issues related to not only to site selection but also financing of radioactive waste management. Likewise, the problem of transportation persists; as an archipelago country, Indonesia still struggles to manage the infrastructure required for the transport of radioactive materials. The waste from the production of the radioisotopes, especially from the production of 99Mo, requires special attention because BATAN has never handled it. Indonesia should also resolve the management of NORM from various activities. In Indonesia, the definition of radioactive waste does not include NORM. Therefore, the management of this waste needs revision and improvement on the regulations, infrastructure, and technology.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.1324-1327
• /
• 2009

Social infrastructure is the basis of public welfare and should be recognized and managed as important assets. Bridge is one of the most important infrastructures to be managed systematically because the impact of the failure is critical. It is essential to monitor the performance of bridges in order to manage them as an asset. But current analytical methods such as predictive modeling and structural analysis are very complicated and difficult to use in practice. To apply these methods, structural and material condition data collection should be performed in each element of bridge. But it is difficult to collect these detailed data in large numbers and various kinds of bridges. Therefore, it is necessary to collect data of major measurement items and predict the life of bridges roughly with advanced information technologies. When certain measurement items reach predefined limits in the monitoring bridges, precise performance measurement will be done by detailed site measurement. This paper describes the selection of major measurement items that can represent the tendency of bridge life and introduces automated bridge data collection test-bed using wireless sensor network technology. The following will be major parts of this paper: 1) Examining the features of conventional bridge management system and data collection method 2) Mileage concept as a bridge life indicator and measuring method of the indicator 3) Test-bed of automated and real-time based bridge life indicator monitoring system using wireless sensor network

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.367-374
• /
• 2013

Underground infrastructure systems provide essential public services and goods through buried structures including water and sewer, gas and petroleum, power and communication pipelines. The majority of existing underground infrastructure systems was installed in green field areas prior to development of complex urban built environments. Currently, there is a global trend to escalate major demand for underground infrastructure system renewal and new installation while minimizing disruption and maintaining functions of existing superstructures. Therefore, Engineers and utility owners are rigorously seeking technologies that minimize environmental, social, and economic impact during the renewal and installation process. Trenchless technologies have proven to be socially less disruptive, more environmentally friendly, energy conservative and economically viable alternative methods. All of those benefits are adequate to enhance overall sustainability. This paper describes effective sustainable solutions using trenchless technologies. Sustainability is assessed by a comparison between conventional open cut and trenchless technology methods. Sustainability analysis is based on a broad perspective combining the three main aspects of sustainability: economic; environmental; and social. Economic includes construction cost, benefit, and social cost analysis. Environmental includes emission estimation and environmental quality impact study. Social includes various social impacts on an urban area. This paper summarizes sustainable trenchless technology solutions and presents a sustainable construction method selection process in a proposed framework to be used in urban underground infrastructure capital improvement projects.

• 한국콘텐츠학회논문지
• /
• 제20권10호
• /
• pp.216-232
• /
• 2020

본 연구는 중국 역사문화도시의 현대 공공조형물의 표현 특성을 분석, 공공조형물이 어떻게 효율적으로 역사 문화 요소에 개입하여, 장소성을 표출할 수 있는가를 파악하고자 함으로서 공공조형물이 지닌 장소적 의미와 적용에 대한 기초자료를 제공하고자 한다. 연구방법은 첫째, 문헌고찰로 역사 문화 도시의 개념, 장소성의 개념 등을 이해하여 이론적 기반을 제공하였다. 둘째, 선행연구 고찰을 통해 공공조형물의 표현특성을 분석하며 10명의 조형 및 디자인 전문가로부터 특성에 대한 평가를 통해 장소성과 관련이 가장 많은 8개 요소를 선정하였다. 셋째, 사례분석으로 중국의 대표적인 도시인 상해, 북경, 광주의 공공조형물 중 발행량이 가장 많은 7개 잡지에서 60개 사례를 선정하여 전문가의 평가를 통해 최종 15개 공공조형물을 선정하였다. 연구 결과에 따르면, 역사 문화 요소의 발굴이나 도시 현대 인문 정취를 표현함에 있어서 세 도시의 공공 조형물 모두 각기 다른 장소성을 구현하였다. 독자적인 선진 기술이 가져온 예술적 독창성과 대중과의 상호작용을 결합하여 도시만의 독특한 역사 인문적 요소를 활용하여 다른 지역과 다른 장소를 만들어내는 것이 공공 조형물의 발전 추세이다.

• 정보화정책
• /
• 제30권2호
• /
• pp.22-45
• /
• 2023

AI 기반 음성비서 서비스 이용에 관한 연구에서는 서비스 이용 경험으로 인한 이용자의 신뢰 및 프라이버시 보호와 관련된 문제가 지속적으로 제기되고 있다. 본 연구의 목적은 AI에 대한 개인의 신뢰와 온라인 프라이버시 염려가 AI 기반 음성비서의 지속적인 사용에 미치는 영향, 특히 상호 작용의 영향을 실증적으로 분석하는 것이다. 본 연구에서는 선행연구를 바탕으로 설문문항을 구성하고 응답자 405명을 대상으로 온라인 설문조사를 실시하였다. 인공지능에 대한 사용자의 신뢰와 개인정보보호 관심이 인공지능 기반 음성비서 서비스 도입 및 지속 이용의도에 미치는 영향을 Heckman 선택모형을 이용하여 분석하였다. 연구의 주요 결과로 첫째, 인공지능 기반 음성비서 서비스 이용행태는 기술수용 촉진요인인 지각된 유용성, 지각된 이용편의성, 사회적 영향에 의해 긍정적인 영향을 받았다. 둘째, 인공지능에 대한 신뢰는 인공지능 기반 음성비서 서비스 이용행태에 통계적으로 유의한 영향을 미치지 않았으나 지속 이용의도에는 정(+)의 영향을 미쳤다. 셋째, 프라이버시 염려 수준은 AI에 대한 신뢰와의 상호작용을 통해 지속적인 이용의도를 억제하는 효과(β=-0.153)가 있음을 확인하였다. 이러한 연구 결과는 디지털 정부를 구현하기 위한 거버넌스로서 기술에 대한 신뢰를 높이고 프라이버시에 대한 사용자의 우려를 완화할 수 있는 이용자 의견수렴과 조치를 통한 이용자 경험을 강화할 필요가 있음을 시사한다. 이러한 수단으로서 인공지능 기반의 정책서비스를 도입할 때, 인공지능 기술의 적용 범위를 공론화 과정을 통해 투명하게 공개하고, 프라이버시 문제가 사후적으로 추적 및 평가될 수 있는 제도의 마련과 프라이버시의 보호를 고려한 알고리즘의 개발이 필요하다.

• Korean Journal of Health Education and Promotion
• /
• 제2권1호
• /
• pp.1-19
• /
• 2000

With rapid economic development, the emphasis of the public health movement in Korea has shifted towards addressing the burden of chronic disease. With this shift in direction comes a greater focus on health behaviour and the need for planning models to assist in lifestyle modification programs. The Health Belief Model (HBM), which originated in the US, has generated more research than any other theoretical approach to describe and predict the health behaviour of individuals. In recent years it has been applied in many different cultures and modifications have been suggested to accommodate different cultures. Given the centrality of language and culture, any attempts to use models of health behaviour developed in a different culture, must be studied and tested for local applicability. The paper reviews the applicability and suitability of the HBM in Korea, in the context of the Korean language and culture. The HBM has been used in Korea for almost three decades. The predictability of the HBM has varied in Korean studies as in other cultures. Overall, this literature review indicates that the HBM has been found applicable in predicting health and illness behaviours by Korean people. However if the HBM is used in a Korean context, the acquisition of health knowledge is an important consideration. Most new knowledge in the health sciences is originally published in English and less frequently in another foreign language. Most health knowledge in Korea is acquired through the media or from health professionals and its acquisition often involves translation from the original. The selection of articles for translation and the accuracy of translation into language acceptable in the Korean culture become important determinants of health knowledge. As such translation becomes an important part of the context of the HBM. In this paper modifications to the HBM are suggested to accommodate the issues of language and knowledge in Korea.

• KIEAE Journal
• /
• 제14권4호
• /
• pp.53-60
• /
• 2014

Current supervision systems have been changed by the demands of social, physical and institutional environment, and have a role of preventing safety accident and in improving the construct ability through the analysis of issues in quality, time, construction, safety, and environmental management. The public sector "Construction Technology Management Act", a general and private sector "Building Act" and "Certified Architects Act", the residential building "Housing Act" are dealt with supervision systems, respectively, but private small building construction is excluded from the discussion of the main targets because of their relatively small scale and the lack of social interests, Thus, this study focused on the small buildings for improving the non-resident supervision systems. Survey results revealed that the non-resident supervisor needs to be selected not by clients but by officers in order to obtain its publicity. Based on the proper selection and execution of the supervision system suggested in this study, the potential effects can be summarized as 1) recovering of publicity, 2) correcting abnormal practice, and 3) realizing design intention for increasing the public value of buildings. In addition, findings in this study will be effective to amend current non-resident supervision systems for improving the quality of buildings and communities as well as for adopting the environmental-friendly energy-efficient smart building technologies.

• Journal of Animal Science and Technology
• /
• 제66권1호
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.