• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.836-845
• /
• 2017

Due to the development of endoscopic technology, endoscopic diagnosis and procedures have been actively performed. However, due to the increase in colorectal cancer and the effect of government's early cancer screening project, the number of endoscopic diagnosis and procedures has increased, thus medical accidents such as perforation and bleeding are increasing. Therefore, efforts to reduce such medical accidents are needed. In this paper, we propose a method to provide the direction information of the endoscope and the force applied to the probe in real time. We also propose and evaluate an interpolated complementary filter considering the very slow movement of the endoscope probe. The proposed interpolated complementary filter showed 34.6% and 27.6% performance improvement. The expected user interface for applying the proposed method to the endoscopic system is also presented. This shows that the proposed method is applicable to endoscopy system.

• Informatization Policy
• /
• v.19 no.4
• /
• pp.83-104
• /
• 2012

Information sharing is one of the key factors enhancing government efficiency and public convenience. However, critics argue that Korean government is now facing various kinds of barriers such as insufficient collaboration among agencies, inappropriate statutes, and technical problems. Thus, this study aims to develop policy alternatives that help resolve the existing problems suggested above. In order to achieve research objectives, this study employs both quantitative and qualitative methods as ways to investigate different dimensions of information sharing in government. Both survey and interview include six dimensions such as organization, technology, culture, management, policy and law. The results show that Korean government needs to implement following alternatives; developing its own database that helps support government decision making, changing organizational culture, continuous extension in terms of the number of object information and affiliated agency, and developing a statute dealing with government information sharing.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.87-94
• /
• 2021

This study is to analyze the performance of the reformed liberal arts curriculum based on the core competencies of A University and use it as basic data for evaluation and feedback. To this end, students who took courses opened in the second semester of 2020 were surveyed using the liberal arts curriculum competency diagnosis tool developed by A University. Depending on the purpose of the study, descriptive statistics and t-test were performed to analyze the results. As a result of the study, communication (t=-9.839, p<.01), learning (t=-4.707, p<.01), thinking (t=-9.992, p<.01), cooperation (t=-2.061, p<.01) was significantly improved, and sharing (t=-.550) was improved, but it was not significant. These results are meaningful in providing the basis for examining and judging the operation of subjects by competency.

• Tunnel and Underground Space
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2019

This study investigated use cases of machine learning technology in domestic medical, manufacturing, finance, automobile, urban sectors and those in overseas mining industry. Through a literature survey, it was found that the machine learning technology has been widely utilized for developing medical image information system, real-time monitoring and fault diagnosis system, security level of information system, autonomous vehicle and integrated city management system. Until now, the use cases have not found in the domestic mining industry, however, several overseas projects have found that introduce the machine learning technology to the mining industry for improving the productivity and safety of mineral exploration or mine development. In the future, the introduction of the machine learning technology to the mining industry is expected to spread gradually.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.119-119
• /
• 2022

인위적, 자연적 요인에 의한 물순환 왜곡과 물순환 건전성 저하는 이수, 치수, 환경 등 다양한 물 관리 분야의 문제를 일으키고 있다. 이에 건전한 유역 물순환 관리에 관한 사회적 요구가 증대되고 있다. 유역의 물순환 관리를 위해서는 유역 전반의 물 이동과 물 이용에 관한 정량적인 평가가 선행되어야 하고, 유역의 물순환 건전성을 평가할 수 있는 체계가 필요하다. 이 연구에서 물순환 정량화를 위해 자연계 및 인공계 물순환 요소를 반영한 유역 유출 모형을 구축하였고, 관측 자료와 모형을 통해 분석된 결과를 이용하여 물순환을 정량화하였다. 한편, 물순환 건전성 평가를 위해 물환경, 물이용, 물안전의 3가지 범주 내에 수질 관리, 비점오염 관리, 수생태 관리, 하천유지기능, 지하수 보전, 치수 관리, 이수 관리의 7가지 항목에 대한 건전성을 평가할 수 있는 평가지표와 기준을 제시하였다. 그리고 계층 분석적 의사결정 기법에 따른 가중치를 이용하여 7개의 평가항목을 종합한 물순환 건전성 지수(hydrologic soundness index; HSI)를 도입하였다. 구성된 물순환 정량화 및 건전성 평가체계를 경안천과 남강, 미호천, 황룡강 중권역에 적용하여 중권역별로 필요한 물순환 개선 사업과 투자 우선순위가 높은 표준유역을 식별하였다. 이 연구에서 제시한 물순환 정량화 및 건전성 평가체계는 유역의 다양한 물 문제를 객관적으로 진단하는 한 가지 방편으로서, 유역의 물 문제 해결을 위한 기술적 정보 제공에 이바지할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.685-686
• /
• 2023

상수도관의 수질 및 부식도 검사에는 파이프에 손상을 입히지 않고 지속적인 방법이 필요하다. 초음파는 이를 만족하면서 상태를 확인할 수 있고 주파수가 높을수록 해상도가 좋아져 정밀한 측정이 가능하다는 장점이 있다. 이러한 특성을 이용해 상수도관 모니터링 시스템으로 초음파 기반의 Scanning Acoustic Microscopy(SAM)과 Convolutional Neural Network(CNN)을 사용하는 새로운 방법을 제안한다. 기존의 Non-Destructive Testing(NDT)방식의 단점을 보완하면서 더 높은 해상도로 상수도관을 점검하는 방식으로, SAM 을 이용하여 부식으로 인한 파이프 두께 변화와 부유물의 여부 및 수질을 동시에 감지하고 얻은 데이터를 CNN 으로 분석했다. CNN 의 높은 정확도 결과로 이 시스템의 파이프 부식도 및 수질 모니터링에 대한 적합성을 보여주었다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.2
• /
• pp.60-66
• /
• 2019

Many researches have been performed on hybrid fiber reinforced concrete for years, which is to improve some of the weak material properties of concrete. Researches on characteristics of hybrid fiber reinforced concrete using amorphous steel fiber and organic fiber, however, yet remain to be done. Therefore, the purpose of this research is to estimate the compressive strength, long term drying shrinkage, and resistance to freezing and thawing of hybrid fiber reinforced concrete(HFRC) using amorphous steel fiber and polyamide fiber as one of organic fibers. For this purpose, HFRCs containing amorphous steel fiber and polyamide fiber were made according to their total volume fraction of 1.0% for target compressive strength of 40 and 60 MPa, respectively, and then the compressive strength, length change, and resistance to freezing and thawing of these were evaluated. As a result, the long term length change ratio of HFRC used in this study decreased by more than 30%, 25% than plain concrete at 365 and 730 days, respectively, and the durability factor of HFRC was very excellent as more than 90%.

• Journal of the Korean Society of Radiology
• /
• v.16 no.2
• /
• pp.169-175
• /
• 2022

In this study, envisioned a laboratory equipped with virus blocking equipment for chest X-ray examinations of respiratory or droplet-transmitted virus-infected patients, and the material with the least deterioration in X-ray output and image quality among the proven blocking materials that block viruses in the design process. and experimented to find the thickness. As a result, when 1 cm of acrylic was applied, the X-ray output was reduced by only about 3.27 % compared to the absence of the barrier material, the SNR was 40.7 and CNR was 30.9, which was the best. The SSIM index result was analyzed as 0.891, which was analyzed to be implemented as the most similar image compared to the original image. The barrier material applied in the research method was objective in that it used a product approved by the Ministry of Food and Drug Safety. the results of this study are expected to provide useful information when installing X-ray examination facilities for the diagnosis and treatment of respiratory-related virus-infected patients in the future.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.2
• /
• pp.1-11
• /
• 2021

Lately, the Korean Government has gradually expanded participation by local residents who are users of the area in the smart city project for the construction of region specialization smart city service (hereinafter called "Smart Service") and the enhancement in the citizen's awareness. However, due to the lack of information on smart service-related technology, there has been a limitation in getting the specific opinion of citizens in the process of designing the Smart Service. In this study, reports made by 4 four local governments which were selected for implementation of 2019 "Smart Town Challenge Projects" were reviewed to diagnose the actualization level of the smart service suggested by citizens through the living lab. The analysis results show that though the smart service plan was established by using diverse design thinking methodology through the living lab, there was a limitation in having citizens design the specific functions of the smart service. So, this study suggests the function issue card technique which can be used by modulating and freely combining four elements such as information collection, processing, supplying method and technique of the smart service and the service contents. This function issue card technique was directly applied to the living lab of the smart city project to verify its effectiveness. It was found that through this technique, citizens can combine the functions and contents of the smart service to materialize smart services at the level of detailed functions. The function issue card technique suggested in this study is expected to contribute to the actualization of opinions for the role of citizens as co-creators in solving local problems in the citizen participation type smart city plan in the future, thus helping the design of the regional specialization smart service.