• Broadcasting and Media Magazine
• /
• v.25 no.2
• /
• pp.27-35
• /
• 2020

최근 많은 연구 결과물에서 빅데이터를 이용하여 학습된 뉴럴 네트워크가 영상 내 노이즈를 제거하는데 매우 효과적임이 입증되었다. 여기에서 한 걸음 더 나아가, 입력으로 주어진 노이즈가 있는 영상의 특징을 분석하여, 사전에 학습된 네트워크의 파라미터를 테스트 타임에 동적으로 업데이트함으로써 주어진 입력 영상을 더욱 잘 처리할 수 있도록 하는 연구들이 시도되고 있다. 본 원고에서는 이와 같이 테스트 타임에 주어지는 입력 영상을 네트워크 학습에 사용하는(self-supervision) 이미지 복원 기법들을 소개한다. 다음으로, 기존의 self-supervision을 이용하는 기법들 대비 학습 효율성과 정확도를 더욱 향상시킬 수 있는 새로운 형태의 네트워크 파라미터 업데이트 기법을 설명하고, 제안하는 기법의 우수성을 다양한 실험 결과를 통해 분석 및 입증한다.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1061-1069
• /
• 2015

Recently, transportation big data generated in the transportation sector has been widely used in the transportation policies making and efficient system management. Bus passengers' mobility patterns are useful insight for transportation policy maker to optimize bus lines and time intervals in a city. We propose a new methodology to discover mobility patterns by using transportation card data. We first estimate the bus stations where the passengers get-off because the transportation card data don't have the get-off information in most cities. We then applies LDA (Latent Dirichlet Allocation), the most representative topic modeling technique, to discover mobility patterns of bus passengers in Cheong-Ju city. To understand discovered patterns, we construct a data warehouse and perform multi-dimensional analysis by bus-route, region, time-period, and the mobility patterns (get-on/get-off station). In the case of Cheong Ju, we discovered mobility pattern 1 from suburban area to Cheong-Ju terminal, mobility pattern 2 from residential area to commercial area, mobility pattern 3 from school areas to commercial area.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.04a
• /
• pp.244-244
• /
• 2017

Recently, A study is actively underway to apply to various industries, which are one of the major changes in the key drivers of the industry 4.0.. The data generated by the ship include various indicators such as the fuel volume, engine power, ground speed, speed, speed, main engine rpm, DFOC, SFOC, and FOC. This paper analyzes the sensitivity of the Gathering data and analyzes the impact energy efficiency of the vessel operation by analyzing the influence among each parameter, using the mathematical models, you create an surrogate model using the math model, comparative analysis of actual measurement data and predictive results were analyzed. Through the use of big data analysis technology, it is possible to identify the sensitivity between the energy efficiency related variables of the ship, The possibility of utilization of fuel efficiency indicators using of the surrogate model is identified.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.431-431
• /
• 2021

4차 산업혁명의 도래로 사회기반시설물의 계획 및 운영관리에 있어 데이터 분석을 통한 가치추출에 대한 관심은 매우 높은 상황이다. 데이터의 가용성과 접근성, 정부 지원 등을 평가하는 공공데이터 개방지수에서 한국은 1점 만점에 0.93점을 획득하여 경제협력개발기구 회원국 중 1위(2019년 기준)를 할 정도로 매우 높은 수준(평균 0.60점)이다. 그러나 공식적으로 발표 및 배포되는 사회기반시설물 관련 정보와 심도 있는 연구 분석이 필요한 정보는 접근이 여전히 제한적이라 할 수 있다. 특히 대표적인 사회기반시설물인 상수도시스템은 대부분 국가중요시설로 지정되어 있어 다양한 정보를 획득하고 분석하는데 제약이 존재하며, 관련 국가통계인 상수도통계에서는 누수사고 등과 같은 비정상적 상황에 대한 사고지점, 원인 등과 같은 세부정보는 제공하고 있지 않다. 본 연구에서는 웹크롤링 및 빅데이터 분석기술을 활용하여 과거 일정기간 발생한 지자체의 상수도 누수사고 관련 뉴스를 전수조사하고 도출된 사고건수를 국가 공인 정보인 상수도통계자료와 비교·분석하였다. 독립적인 누수사고 기사를 추출하기 위해서 중복기사의 제거, 누수 관련 키워드 정립, 상수도분야 이외의 관련기사 제거 등의 절차가 필요하며, 이와 같은 기법은 R프로그래밍을 통해 구현되었다. 추가적으로 뉴스기사의 자연어 처리기반 정보추출기법을 통해 누수사고 건수 뿐만 아니라 사고발생일, 위치, 원인, 피해정도, 그리고 대상 관로의 크기 등을 획득하여 상수도 통계에서 제시하고 있는 정보보다 많은 가치를 추출하여 연계할 수 있는 방안을 제시하였다. 제시된 방법론을 국내 A광역시에 적용하여 누수사고 건수를 비교한 결과 상수도통계에서 제시하고 있는 누수발생건수와 유사한 규모의 사고건수를 뉴스기사분석을 통해 도출할 수 있었다. 제안된 방법론은 추가적인 정보의 추출이 가능하다는 점에서 향후 활용성이 높을 것으로 기대된다.

• The Journal of Bigdata
• /
• v.4 no.1
• /
• pp.73-81
• /
• 2019

With the increase of education data, there have been many studies on the application of various analytics to improve students' performance and educational environments over the past decade. This paper first introduces the cases of universities that successfully utilize the analysis results and, more specifically, examines which data and analytical techniques are used for each analysis purpose. Based on the findings, the limitations of the current analytics and the direction of future analysis are discussed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.17-24
• /
• 2015

With the rapid growth of Information technology and up-to-date wireless network application technologies, huge and various types of data are produced in every moment, the value and significance of the analysis techniques using big data are increased recently. Big data, which were useless since they were too huge to manage in the past, enables us to get new inspirations and values in various practical application areas through the development of big data computing devices and analytic tools. Nowadays, however, it is true that most of the big data are still wasted without properly analyzed and used. In the long run, the preliminary stipulations for finding inspirations and extracting new values from big data are securing big data analysis and application techniques to process big data efficiently. In this paper, we study accurate data analysis techniques and data process technologies those are able to extract needed inspirations and values from big data efficiently, then design the smart application that adopts these techniques practically.

• Journal of the Korean Regional Science Association
• /
• v.39 no.1
• /
• pp.21-36
• /
• 2023

Entering the era of low growth due to changes in social and economic conditions, most cities across the country are actively promoting urban regeneration. Although urban regeneration is a project with huge national finances, a clear evaluation system has not yet been established. In order to ensure the sustainability of urban regeneration, it is necessary to secure the validity of urban regeneration policies and establish a reflux system to supplement the policies. The purpose of this study is to derive the limitations of the existing comprehensive performance evaluation and to develop an improved urban regeneration policy comprehensive performance evaluation technique based on spatial big data. The urban regeneration comprehensive performance evaluation technique differentiated the areas affected by the urban regeneration project and the surrounding areas based on the type of urban regeneration project and the presence or absence of large cities and middle cities. The effects of urban regeneration were quantitatively verified through relative comparison between the areas affected by urban regeneration projects and the surrounding areas of population, society, economy, industry, physical and environmental evaluation indicators.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.19-28
• /
• 2021

Korea is promoting a digital new deal policy for the digital transformation and innovation accelerating of the industry. However, because of the strict existing data-related laws, there are still restrictions on the industry's use of data for the digital new deal policy. In order to solve this issue, a revised bill of the Data 3 Act has been proposed, but there is still insufficient discussion on how it will actually affect the activation of data use in the industry. Therefore, this study aims to analyze the perception of public opinion on the Data 3 Act and the implications of the revision of the Data 3 Act. To this end, the revision of the Data 3 Act and related research trends were analyzed, and the perception of the Data 3 Act was analyzed using a big data analysis technique. According to the analysis results, while promoting the vitalization of the data industry in line with the purpose of the revision, the Data 3 Act has a concern that it focuses on specific industries. The results of this study are meaningful in providing implications for future improvement plans by analyzing online perceptions of the industrial impact of the Data 3 Act in the early stages of implementation through big data analysis.

• Cartoon and Animation Studies
• /
• s.44
• /
• pp.285-306
• /
• 2016

With the increase use of smartphones, users can consume contents such as webtoon, webnovel and TV drama directly provided by the producers. In this Direct-to-Consumer era, webdrama services from the portal websites are increasing rapidly. Webdramas such as , , and can be analyzed in real time using responses such as unique users, likes, and comments. The analyses used in this research were Social Media Big Data Mining Method and Opinion Mining Method. Specific key words from webdrama can be extracted and viewers positive, neutral or negative emotion can be predicted from the words. The analyses of popular webdramas showed that the established K-Pop Idol member appearance and servicing portal site greatly influence the views, traffics, comments, and likes. Also, 'Mobile TV' proved the effectiveness as another platform other than television. Mobile targeted contents and robust business models still to be developed and identified. Overcoming these few tasks, Korea will be proven to be a webdrama content powerhouse.

• Journal of the Korea Society for Simulation
• /
• v.32 no.1
• /
• pp.13-21
• /
• 2023

This paper proposes a method of automatically generating a model through a machine learning technique by setting a hypothetical model in the form of a gray box or black box with unknown parameters, when the big data of the actual system is given. We implements the proposed framework and conducts experiments to find an appropriate model among various hypothesis models and compares the cost and fitness of them. As a result we find that the proposed framework works well with continuous systems that could be modeled with ordinary differential equation. This technique is expected to be used well for the purpose of automatically updating the consistency of the digital twin model or predicting the output for new inputs using recently generated big data.