• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.72-75
• /
• 2020

조립 부품 이미지에 해당하는 3D CAD 모델 매칭 기술은 최근 로봇 조립 기술의 발전으로 필요성이 대두되고 있다. 이미지 기반 3 차원 모델 매칭 연구는 진행되어 왔지만 가구 부품 이미지와는 특성이 다른 RGB[5] 이미지나 스케치 이미지를 다루는[1] 접근들이었다. 딥러닝을 사용하는 스케치 이미지 기반 3 차원 물제 검색 연구에서는 대부분 3 차원 이미지를 다각도에서 렌더링한 view 이미지들에서 feature를 추출하고 pooling 하여 하나의 feature를 출력한다. 그러나 기존의 view pooling 방식은 단순한 평균 방식으로, 부품 이미지에 따른 view를 반영하기에는 한계가 있었다. 따라서 본 논문에서는 조립 부품 이미지 기반 3 차원 물체 검색을 위해 query 부품 이미지에 따라 다른 view 이미지에 집중할 수 있는 방식의 attentional view pooling을 제안한다. 또한 조립 부품 데이터의 특성 상 class 당 CAD 모델이 하나인 상황이므로 학습 데이터가 터무니없이 부족하여 이를 해결하기 위한 학습 데이터 증강 방법을 제안한다. 실험은 의자 부품 11가지에 대해 진행하였고 이를 통해 제안하는 방식의 성능을 입증하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.228-232
• /
• 2006

Ontology를 이용한 분산 시각미디어 검색 프레임워크인 HERMES(The Retrieval Framework for Visual Media Service)[1][2]는 보다 정확한 시각미디어 정보를 제공하고 웹서비스(Web Services)를 적용하여 HERMES/Provider[1][2]의 자율성을 보장한다. 웹기반의 분산 환경에서 Visual Media Data에 대한 지능적인 검색을 위하여 Meta Data와 Ontology를 이용하고 이기종간 통신을 위한 웹서비스를 제공하는 HERMES/ Broker[1][2]에서 예상치 못한 문제가 발생할 경우 문제를 해결할 수 있는 방법이 제시되지 않았다. 일반적으로 웹 서비스를 제공하는 서버에서 발생되는 결함은 해당 웹 서비스를 이용하여 개발되는 어플리케이션의 갑작스런 중단이나 오류의 원인이 된다. 따라서 결함을 해결할 수 있는 대책이 필요하며 HERMES의 Broker 서버 또한 웹 서비스의 결함이 발생하더라고 이를 효과적으로 해결하여 클라이언트에게 웹 서비스를 정상적으로 제공할 수 있는 결함허용 시스템 도입이 매우 중요하다. 때문에 HERMES 프레임워크가 클라이언트에게 신뢰성과 안정성이 보장된 웹 서비스의 제공을 위해서 Broker 서버에서 발생할 수 있는 결함을 효과적으로 극복할 수 있는 메커니즘이 필요하다. 본 논문에서는 Broker 서버 에서 웹 서비스와 관련된 결함이 발생하더라고 올바르게 운영될 수 있으며 분산 이미지 검색 프레임워크인 HERMES의 구조적 특성에 적합한 결함허용 시스템 설계 기법을 제안하여 HERMES 프레임워크가 클라이언트에게 투명성 있는 서비스를 제공하고 높은 신뢰성과 안정성이 확보될 수 있도록 구성하고자 한다. Query 수행을 여러 서버로 분산처리하게 함으로써 성능에 대한 신뢰성을 향상 시킬 수 있는 Load Balancing System을 제안한다.할 때 가장 효과적인 라우팅 프로토콜이라고 할 수 있다.iRNA 상의 의존관계를 분석할 수 있었다.수안보 등 지역에서 나타난다 이러한 이상대 주변에는 대개 온천이 발달되어 있었거나 새로 개발되어 있는 곳이다. 온천에 이용하고 있는 시추공의 자료는 배제하였으나 온천이응으로 직접적으로 영향을 받지 않은 시추공의 자료는 사용하였다 이러한 온천 주변 지역이라 하더라도 실제는 온천의 pumping 으로 인한 대류현상으로 주변 일대의 온도를 올려놓았기 때문에 비교적 높은 지열류량 값을 보인다. 한편 한반도 남동부 일대는 이번 추가된 자료에 의해 새로운 지열류량 분포 변화가 나타났다 강원 북부 오색온천지역 부근에서 높은 지열류량 분포를 보이며 또한 우리나라 대단층 중의 하나인 양산단층과 같은 방향으로 발달한 밀양단층, 모량단층, 동래단층 등 주변부로 NNE-SSW 방향의 지열류량 이상대가 발달한다. 이것으로 볼 때 지열류량은 지질구조와 무관하지 않음을 파악할 수 있다. 특히 이러한 단층대 주변은 지열수의 순환이 깊은 심도까지 가능하므로 이러한 대류현상으로 지표부근까지 높은 지온 전달이 되어 나타나는 것으로 판단된다.의 안정된 방사성표지효율을 보였다. $^{99m}Tc$-transferrin을 이용한 감염영상을 성공적으로 얻을 수 있었으며, $^{67}Ga$-citrate 영상과 비교하여 더 빠른 시간 안에 우수한 영상을 얻을 수 있었다. 그러므로 $^{99m}Tc$-transierrin이 감염 병소의 영상진단에 사용될 수

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.45-52
• /
• 2004

According tothe development of digital media technologies various algorithms for video sequence matching have been proposed to match the video sequences efficiently. A large number of video sequence matching methods have focused on frame-wise query, whereas a relatively few algorithms have been presented for video sequence matching or video shot matching. In this paper, we propose an efficientalgorithm to index the video sequences and to retrieve the sequences for video sequence query. To improve the accuracy and performance of video sequence matching, we employ the Cauchy function as a similarity measure between histograms of consecutive frames, which yields a high performance compared with conventional measures. The key frames extracted from segmented video shots can be used not only for video shot clustering but also for video sequence matching or browsing, where the key frame is defined by the frame that is significantly different from the previous fames. Several key frame extraction algorithms have been proposed, in which similar methods used for shot boundary detection were employed with proper similarity measures. In this paper, we propose the efficient algorithm to extract key frames using the cumulative Cauchy function measure and. compare its performance with that of conventional algorithms. Video sequence matching can be performed by evaluating the similarity between data sets of key frames. To improve the matching efficiency with the set of extracted key frames we employ the Cauchy function and the modified Hausdorff distance. Experimental results with several color video sequences show that the proposed method yields the high matching performance and accuracy with a low computational load compared with conventional algorithms.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.31-39
• /
• 2014

Seasonal influenza epidemics cause 3 to 5 millions severe illness and 250,000 to 500,000 deaths worldwide each year. To prepare better controls on severe influenza epidemics, many studies have been proposed to achieve near real-time surveillance of the spread of influenza. Korea CDC publishes clinical data of influenza epidemics on a weekly basis typically with a 1-2-week reporting lag. To provide faster detection of epidemics, recently approaches using unofficial data such as news reports, social media, and search queries are suggested. Collection of such data is cheap in cost and is realized in near real-time. This research aims to develop regression models for early detecting the outbreak of the seasonal influenza epidemics in Korea with keyword query information provided from the Naver (Korean representative portal site) trend services for PC and mobile device. We selected 20 key words likely to have strong correlations with influenza-like illness (ILI) based on literature review and proposed a logistic regression model and a multiple regression model to predict the outbreak of ILI. With respect of model fitness, the multiple regression model shows better results than logistic regression model. Also we find that a mobile-based regression model is better than PC-based regression model in estimating ILI percentages.

• Spatial Information Research
• /
• v.20 no.5
• /
• pp.99-109
• /
• 2012

Recently, due to the growth of social media and spread of smart-phone, the amount of data has considerably increased by full use of SNS (Social Network Service). According to it, the Big Data concept is come up and many researchers are seeking solutions to make the best use of big data. To maximize the creative value of the big data held by many companies, it is required to combine them with existing data. The physical and theoretical storage structures of data sources are so different that a system which can integrate and manage them is needed. In order to process big data, MapReduce is developed as a system which has advantages over processing data fast by distributed processing. However, it is difficult to construct and store a system for all key words. Due to the process of storage and search, it is to some extent difficult to do real-time processing. And it makes extra expenses to process complex event without structure of processing different data. In order to solve this problem, the existing Complex Event Processing System is supposed to be used. When it comes to complex event processing system, it gets data from different sources and combines them with each other to make it possible to do complex event processing that is useful for real-time processing specially in stream data. Nevertheless, unstructured data based on text of SNS and internet articles is managed as text type and there is a need to compare strings every time the query processing should be done. And it results in poor performance. Therefore, we try to make it possible to manage unstructured data and do query process fast in complex event processing system. And we extend the data complex function for giving theoretical schema of string. It is completed by changing the string key word into integer type with filtering which uses keyword set. In addition, by using the Complex Event Processing System and processing stream data at real-time of in-memory, we try to reduce the time of reading the query processing after it is stored in the disk.

• The Journal of Bigdata
• /
• v.1 no.2
• /
• pp.79-89
• /
• 2016

News organizations are looking for a way that can be reused accumulated intellectual property in order to find a new insights. BBC is a worldwide media that continually enhances the value of the news articles by using Linked Data model. Thus, utilizing the Linked Data model, by reusing the stored articles, can significantly improve the value of news articles. In this paper, we conducted a study of Linked Data construction for the healthcare news from a newspaper company. The object names associated with medical description or connected to other published information have been constructed into Linked Open Data service. The results of the study are to systematically organize the news data that were accumulated rashly, and to provide the opportunity to find new insights that could not be found before by connecting to other published information. It may be able to contribute to reused news data. Finally, using SPARQL query language can contribute to interactively searched news data.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.1
• /
• pp.101-115
• /
• 2010

The main difference between web searching and traditional searching is that the web provides and supports multimedia searching. This study aims to investigate the multimedia searching behavior of users of NAVER, a major Korean search portal. In conducting this study, the query logs and click logs of a unified search service were analyzed. The results of this study show that among the multimedia queries submitted by users, audio searches are the dominant media type, followed similarly by video and image searches. On the other hand, among the multimedia documents clicked on, video is the most popular collection type followed by image and audio collections. Entertainment is the most popular topic in both multimedia queries and clicks. The results of this study can be implemented for the portal's development of multimedia content and searching algorithms.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.553-564
• /
• 2014

In this paper, we propose the system for automatic generation of issue analysis report based on social big data mining, with the purpose of resolving three problems of the previous technologies in a social media analysis and analytic report generation. Three problems are the isolation of analysis, the subjectivity of experts and the closure of information attributable to a high price. The system is comprised of the natural language query analysis, the issue analysis, the social big data analysis, the social big data correlation analysis and the automatic report generation. For the evaluation of report usefulness, we used a Likert scale and made two experts of big data analysis evaluate. The result shows that the quality of report is comparatively useful and reliable. Because of a low price of the report generation, the correlation analysis of social big data and the objectivity of social big data analysis, the proposed system will lead us to the popularization of social big data analysis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.4
• /
• pp.663-670
• /
• 2017

The purpose of this study is to define On-line Video Syllabus Template which is based on adaptive mode with interaction.A syllabus has the significance as a teaching and learning plan. However, it has not only been considered as a formal document, has also been limited into a simple query since it has been made into a fragmentary structure, lacking of link between other services and reuse. Additionally, this paper is aimed to design three-dimensional syllabus which makes it possible to provide students with practical information related to teaching and learning and share it with teachers and students. The following is the technique proposed in this paper. It is made to be served for the Syllabus centered on teaching and learning, which is including the definition of hierarchy structure, the media contents application according to the learner's preference and real-time variation function. On-line Video Syllabus provided through LMS has availability and credibility of teaching and learning, in that it enable increased utilization by strengthening convenience.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.35-44
• /
• 2004

With increase in digitalmedia data, various video indexing and video sequence matching algorithms have been proposed to efficiently manage and utilize digital media. In this paper, we propose a robust video indexing algorithm to detect scene changes for video sequences with abrupt luminance variations and an efficient video sequence matching algorithm for video sequence query. To improve the accuracy and to reduce the computational complexity for video indexing with abrupt luminance variations, the proposed algorithm utilizes edge features as well as color features, which yields a remarkably better performance than conventional algorithms. In the proposed algorithm first we extract the candidate shot boundaries using color histograms and then determine using edge matching and luminance compensation if they are shot boundaries or luminance changes. If the scene contains trivial brighness variations, the edge matching and luminance compensation are performed only for shot boundaries. In experimental results, the proposed method gives remarkably a high performance and efficiency than the conventional methods with the similar computational complexity.