• 대한원격탐사학회지
• /
• 제28권6호
• /
• pp.693-704
• /
• 2012

Space-born remote sensing camera systems tend to be developed to have very high performances. They are developed to provide extremely small ground sample distance, wide swath width, and good MTF (Modulation Transfer Function) at the expense of big volume, massive weight, and big power consumption. Therefore, the camera system occupies relatively big portion of the satellite bus from the point of mass and volume. However, the camera systems for lunar exploration don't need to have such high performances. Instead, it should be versatile for various usages under various operating environments. It should be light and small and should consume small power. In order to be used for national program of lunar exploration, electro-optical versatile camera system, called MAEPLE (Multi-Application Electro-Optical Payload for Lunar Exploration), has been designed after the derivation of camera system requirements. A ground model of the camera system has been manufactured to identify and secure relevant key technologies. The ground model was mounted on an aircraft and checked if the basic design concept would be valid and versatile functions implemented on the camera system would worked properly. In this paper, results of design and functional test performed with the field campaigns and air-born imaging are introduced.

• 대한조선학회논문집
• /
• 제49권6호
• /
• pp.478-483
• /
• 2012

The speed performances of ice sea trial on the Arctic(2010 & 2011) area were shown different results depend on the ice floe size. Penetration phenomena of level ice was not happened on medium ice floe and tore up by the impact force because the mass of medium ice floe is similar to the mass of Araon which is Korean ice breaking research vessel and did not shut up by the ice ridge or iceberg. The sea trial on the Amundsen sea was performed at the big floe which is classified by WMO(World Meteorological Organization). Three measurements of ice properties and five results of speed trial were obtained with different ice thicknesses and engine powers. To evaluate speed of level ice trial and model test results at the same ice thickness and engine power, the correction method of HSVA(Hamburg Ship Model Basin) was used. The thickness, snow effect, flexural strength and friction coefficient were corrected to compare the speed of sea trial. The analyzed speed at 1.03m thickness of big floe was 5.85 knots at 10MW power and it's 6.10 knots at 1.0m ice thickness and the same power. It's bigger than the results of level ice because big floe was also slightly tore up by the impact force of vessel based on the observation of recorded video.

• 한국도서관정보학회지
• /
• 제38권4호
• /
• pp.19-44
• /
• 2007

이 연구에서는 학교도서관이 교육과정과 연계한 정보문해 서비스를 제공하기 위한 장애요인과 해결 방안을 탐색해 보았다. 장애요인으로는 정보문해를 ICT 활용능력으로 잘못 이해하고 있다는 점, 그리고 장서, 도서관 전담인력 등의 미비 등을 들었다. 정보문해에서 문헌정보의 중요성, 온라인을 이용한 도서관 이용지도, 정보문해 수업을 위한 Big6 문제해결 모형 및 교수-학습 과정안, 수업의 실천과정에서 필요한 서식 등을 제시하였다.

• 열처리공학회지
• /
• 제35권6호
• /
• pp.327-336
• /
• 2022

In this study, a model for automatically recognizing several steel parts through a camera before charging materials was developed under the assumption that the temperature distribution in the pre-air atmosphere was known. For model development, datasets were collected in random environments and factories. In this study, the YOLO-v5 model, which is a YOLO model with strengths in real-time detection in the field of object detection, was used, and the disadvantages of taking a lot of time to collect images and learning models was solved through the transfer learning methods. The performance evaluation results of the derived model showed excellent performance of 0.927 based on mAP 0.5. The derived model will be applied to the model development study, which uses the model to accurately recognize the material and then match it with the temperature distribution in the atmosphere to determine whether the material layout is suitable before charging materials.

• 한국엔터테인먼트산업학회논문지
• /
• 제14권4호
• /
• pp.145-153
• /
• 2020

빠르게 변화하고 있는 4차 산업 시대에 빅데이터는 다양한 분야에 활용되고 있다. 최근 문화예술콘텐츠 전반에도 빅데이터의 활용은 급속도로 적용되고 있고, 그중에서도 영화는 자본이 많이 드는 예술장르로서 빅데이터의 활용은 매우 유용한 분석 수단이다. 본 연구는 2019년 제72회 칸 영화제의 황금종려상과 아카데미 시상식에서 4관왕(작품상, 감독상, 각본상, 외국어 영화상)을 차지하며 한국영화의 가치를 보여준 영화 <기생충>을 대상으로 빅데이터 분석기법을 적용하여 실시하였다. 이렇게 분석된 값은 데이터의 주기별 변화량과 감성의 값을 부여하는 오피니언 마이닝을 통해 영화 흥행을 예측하고, 페이스북(Facebook), 트위터(Twitter) 등 SNS의 활용지수와 토픽 키워드를 추출하여 관객들의 관심을 반영하는 영화적 요인들이 무엇인지를 살펴보았다. 이처럼 빅데이터를 활용한 영화흥행 요인분석으로 모델 구축 및 모형 개발로 흥행예측이 가능해지면 영화제작 과정의 효율성을 극대화하면서 제작비용과 영화실패에 따른 리스크를 최소화 할 것이다.

• 인터넷정보학회논문지
• /
• 제20권6호
• /
• pp.73-84
• /
• 2019

최근 서비스로서의 머신러닝(MLaaS) 개념은 데이터 자체를 제외하고 네트워크 서버, 스토리지 또는 데이터 과학자 없이도 생산적인 서비스 모델을 구축할 수 있다는 점에서 기계학습을 다루는 대부분의 산업 분야와 연구 그룹들의 많은 관심을 받고 있다. 그러나 과학 분야에서는 양질의 빅데이터를 확보하는 가정 자체가 커다란 도전이 된다. 즉, 연구자 간 연구 결과물의 공유가 쉽지 않을 뿐 아니라 과학기술 데이터의 비정형성 문제를 해결해야하는 문제가 선행된다. 본 논문에서 제안된 KISTI-ML 플랫폼은 과학기술 데이터를 위한 AI 모델 고속 개발 도구로서, 머신러닝에 익숙하지 않은 연구자들을 위해 웹 기반 GUI 인터페이스를 제공하고 연구자는 자신의 데이터를 이용하여 머신러닝 코드를 손쉽게 생성하고 구동할 수 있다. 또한 승인된 커뮤니티 멤버들을 중심으로 데이터셋 및 특징 추출에 사용되는 데이터전처리, 학습 네트워크 설계 등이 포함되는 프로그래밍 코드를 공유할 수 있는 환경을 제공한다.

• 한국안전학회지
• /
• 제31권6호
• /
• pp.121-128
• /
• 2016

Social Media transformed the mass media based information traffic, and it has become a key resource for finding value in enterprises and public institutions. Particularly, in regards to disaster management, the necessity for public participation policy development through the use of social media is emphasized. National Disaster Management Research Institute developed the Social Big Board, which is a system that monitors social Big Data in real time for purposes of implementing social media disaster management. Social Big Board collects a daily average of 36 million tweets in Korean in real time and automatically filters disaster safety related tweets. The filtered tweets are then automatically categorized into 71 disaster safety types. This real time tweet monitoring system provides various information and insights based on the tweets, such as disaster issues, tweet frequency by region, original tweets, etc. The purpose of using this system is to take advantage of the potential benefits of social media in relations to disaster management. It is a first step towards disaster management that communicates with the people that allows us to hear the voice of the people concerning disaster issues and also understand their emotions at the same time. In this paper, Korean language text mining based Social Big Board will be briefly introduced, and disaster issue detection model, which is key algorithms, will be described. Disaster issues are divided into two categories: potential issues, which refers to abnormal signs prior to disaster events, and occurrence issues, which is a notification of disaster events. The detection models of these two categories are defined and the performance of the models are compared and evaluated.

• 한국산업융합학회 논문집
• /
• 제25권6_2호
• /
• pp.1083-1090
• /
• 2022

Since renal cell carcinoma(RCC) has various examination and treatment methods according to clinical stage and histopathological characteristics, it is required to determine accurate and efficient treatment methods in the clinical field. However, the process of collecting and processing RCC medical data is difficult and complex, so there is currently no AI-based clinical decision support system for RCC treatments worldwide. In this study, we propose a clinical decision support system that helps clinicians decide on a precision treatment to each patient. RCC standard big database is built by collecting structured and unstructured data from the standard common data model and electronic medical information system. Based on this, various machine learning classification algorithms are applied to support a better clinical decision making.

• 한국인터넷방송통신학회논문지
• /
• 제16권6호
• /
• pp.287-294
• /
• 2016

APT(Advanced Persistent Threat)공격은 기관, 기업의 정보통신 설비에 대한 중단 또는 핵심정보의 획득을 목적으로 장기간 IT인프라, 업무환경, 임직원 정보 등의 다양한 정보를 수집하고, 이를 바탕으로 제로데이 공격, 사회공학적기법 등을 이용하여 공격을 실행한다. 악성 시그니처 탐지 등의 단편적인 사이버 위협대응 방법으로는 APT 공격과 같이 고도화된 사이버 공격에 대응하기 어렵다. 본 논문에서는 APT 공격 대응 방안 중 하나로 이종 시스템 로그(Heterogeneous System Log)를 빅데이터로 활용하고, 패턴기반 탐지 방법과 이상 징후 탐지 방법을 병합하여 사이버 침해시도를 탐지하는 모델을 제시하고자 한다.

• 농촌지도와개발
• /
• 제17권3호
• /
• pp.475-504
• /
• 2010

This study focuses on the discovering problems which have been encountered while the farm company grew from one-man business to big company. We divide a growth process of farm company into 7 phases, and analyze the problems of each phase of growth process of farm company by theoretically and empirically. The logical model methodology is selected to test the basic model, and we use 6 cases to test suggested basic model. The results of this study are as follows. It suggests that the CEO of farm enterprise or its policy maker can understand what kinds of problem they meet while the farm enterprise grew from one-man business to big company, and they can make better strategies or better support policies.