• Journal of Broadcast Engineering
• /
• v.22 no.1
• /
• pp.51-61
• /
• 2017

This paper proposes a method to generate panoramic images by combining conventional feature extraction algorithms (e.g., SIFT, SURF, MPEG-7 CDVS) with sensed data from an inertia sensor to enhance the stitching results. The challenge of image stitching increases when the images are taken from two different mobile phones with no posture calibration. Using inertia sensor data obtained by the mobile phone, images with different yaw angles, pitch angles, roll angles are preprocessed and adjusted before performing stitching process. Performance of stitching (e.g., feature extraction time, inlier point numbers, stitching accuracy) between conventional feature extraction algorithms is reported along with the stitching performance with/without using the inertia sensor data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.539-541
• /
• 2016

In this paper, we proposed real time free-length monitoring systems interlocking with the spring free-length sorter which shows the state of production connected to the spring production device. This systems enable the administrator to check the quality or quantity of product and the defect rate, etc., in the remote place. The proposed systems are comprised of the wireless device interlocking with PLC device, the server program, and user GUI program. The wireless device transmits the received data from PLC device to server program using Wi-Fi. Server program represents the data from the wireless device on the screen and insert those data into database. User GUI program shows data stored in database and supports the function which converts the stored data in DB to excel file.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• Journal of Digital Convergence
• /
• v.15 no.4
• /
• pp.91-105
• /
• 2017

Korea is rapidly becoming a multicultural society in recent years, and the number of multicultural families in 2015 exceeds 3.5% and 800,000. Also, as international marriage rate exceeds 10% by 2016, the number of multicultural families is expected to steadily increase. This study is a design of a metadata application profile as part of the foundation for providing learning resources and content tailored to the needs and preferences of married immigrant women and multicultural family members who need to adapt to Korean society. In order to verify the necessity of the research, we conducted an in-depth interview by screening consumer groups, and analyzed the relevant international and Korean national standards as de-jure standards for the design of metadata standard profiles. Then, we analyzed the contents characteristics for multicultural members, and organized the necessary metadata elements into profiles. We defined the mandatory/optional conditions to reflect the needs of content providers. This study is meaningful in that the study analyzes the educational needs of married immigrant women and presents the necessary metadata standards to develop and service effective educational content, such as korean-to-korean conversion system, personalized learning contents recommendation service, and learning management system.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1397-1407
• /
• 2015

Individual phenotype is mostly influenced by genetic factors as well as the effects of environmental factors. Therefore, adjustment of environmental factors are needed in order to see more clearly the effects of genetic factors that we are interested in gene screening study related to Hanwoo's economic trait. The purpose of this study is to propose new statistical model that was adjusted environmental factor and identify adjustment effect in a superior gene marker screening study for producing high quality Hanwoo. First, statistical model including both genetic factor and environmental factor establishes and adjusted value of economic trait find by removing effect of environmental factor such as age, breeding farm. Finally, we identify superior gene marker combination and compare accuracy by applying MDR to data of before and after adjustment. Economic trait is used C18:1, SFA, MUFA, MS, CWT, BFT and SNP marker is used 6 markers of LPL that were identified as more excellent SNP marker than the others among 49 markers through fatty acid composition and economic trait performance test.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.22 no.5
• /
• pp.110-118
• /
• 2018

Due to recent earthquakes, there is a growing awareness that Korea is not a safe zone for earthquakes any more. Therefore, the review of various aspects of the seismic safety of the infrastructures are being carried out. Because of the characteristics of the underground structure buried in the ground, the electric power utility tunnels must be considered not only for the inertia and load capacity of the structure itself but also the characteristics of the surrounding soils. An extensive and accurate numerical analysis is inevitably required in order to consider the interaction with the ground, but it is difficult to apply the soil-structure interaction analyses, which generally requires high cost and extensive time, to all electric power utility tunnel structures. In this study, the major design variables including soil characteristics are considered as independent variables, and the seismic safety factor, which is the result of the numerical analysis, is considered as a dependent variable. Thus, a method is proposed to select vulnerable electric power utility tunnels with low seismic safety factor while excluding costly and time-consuming numerical analyses through the direct correlation analysis between independent and dependent variables. Equations of boundary limits were derived based on the distribution of the seismic safety factor and the cover depth and rebar amounts with high correlation relationship. Consequently, a very efficient and simple approach is proposed to select vulnerable electric power utility tunnels without intensive numerical analyses. Among the 108 electric power utility tunnels that were investigated in this paper, 30% were screened as fragile structures, and it is confirmed that the screening method is valid by checking the safety factors of the fragile structure. The approach is relatively very simple to use and easy to expand, and can be conveniently applied to additional data to be obtained in the future.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.09a
• /
• pp.102-107
• /
• 2010

본 연구에서는 2009년 강원도 읍면동 주민등록 데이터와 탐구적 공간데이터 분석 방법의 하나인 Getis - Ord $Gi^*$를 이용하여 강원도 남녀 장수인구의 공간적 분포패턴을 분석하였다. 분석결과는 강원도의 남성인구와 여성인구의 지역적 장수도에 공간적 군집이 존재하며 장수도가 높은 지역의 군집의 경우 남성과 여성 사이에 커다란 차이가 존재함을 보이고 있다. 남성의 경우 장수도가 높은 지역이 영서지역의 접경지역을 중심으로 군집하는 반면 여성의 경우 장수도가 높은 지역이 영동 해안지역 중심으로 군집하여 분포하였다. 이 결과는 장수에 영향을 미치는 환경적(자연환경적, 사회적) 요인이 남녀에 선별적으로 작용하고 있음을 암시한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.169-171
• /
• 2016

본 논문에서는 최근 빅데이터 처리 방법으로 각광을 받고 있는 딥러닝 알고리즘을 스마트교육에 적용하는 방안을 제안한다. 디지털 교과서의 사용과 함께 교육 빅데이터가 발생하는 스마트교육의 특성 상 빅데이터를 효과적으로 처리하고 활용할 수 있는 방법이 필요하다. 따라서 그 방법으로 딥러닝을 적용하고, 이를 활용한 교육을 한다면 개별화 교육의 실현, 감성 교육에의 활용, 수업 개선에의 도움, 양질의 학습자료 선별 등의 효과를 거둘 수 있을 것이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.279-282
• /
• 2006

데이터베이스는 매우 복잡한 성격을 지니고 있으며, 일반적으로 한 조직의 모든 데이터를 모아놓으므로 대형화되는 것이 보통이다. 따라서 데이터베이스는 항시 많은 데이터들이 생성 및 갱신을 반복한다. 이에 데이터베이스의 구성요소인 객체 또한 생성 및 변경을 거듭한다. 즉, 이러한 데이터의 증가 및 갱신으로 인하여 처음 생성되었을 때의 객고의 성능 및 저장 공간에 대한 이용은 향후 지속적인 관리가 없이는 보장받지 못한다. 이에 데이터베이스를 관리하는 사람들은 많은 인적 물적 자원을 할애하여 객체를 관리하고 최적의 상태로 만들기 위하여 노력한다. 본 논문에서는 이러한 일련의 행위들들 시스템에서 자동으로 자원을 수집하고 수집된 자원을 분석하여 시스템 특성을 반영한 관리기준에 부합하는 객체를 선별하여, 온라인 REORG(on-line reorganization) 작업을 통한 객체의 관리를 자동화 하여 보다 안정적인 데이터베이스 관리 및 데이터베이스의 관리의 효율성을 높이고. 데이터베이스 관리자의 생산성을 향상시키는데 기여 하고자 한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.308-313
• /
• 2001

최근 인터넷의 급속한 성장과 빠른 보급, 정보통신 분야의 기술퓨전 현상들은 인터넷을 이용한 다양한 컨텐츠의 개발을 가속화시키고 있다. 특히 멀티미디어 스트리밍 기술은 일반 사용자들에게 동영상은 물론 풍부한 멀티미디어 데이터 전송을 통하여 능동적인 대화형 서비스를 제공할 수 있는 장점들을 가지고 있다. 본 논문에서는 사용자의 접속 횟수 및 접속시간 등의 빈도수에 따른 사용자 개인 가중치를 이용하여 사용자에게 보다 친숙하고 흥미를 유발할 수 있는 비디오 데이터 서비스를 제공하고자 하였으며, 카테고리 기반 및 키워드 기반에 따른 사용자 접근 정보를 이용하여 비디오 데이터를 분류하고 선별한 검색 서비스를 제공하고자 하였다. 또한 비디오 브라우징 시스템을 이용하여 사용자가 원하는 항목에 대한 비디오 검색을 장면 검색에서 샷 검색까지 프레임단위로 동영상을 이용하여 브라우징 할 수 있도록 하였으며, 해당 영역의 텍스트 및 관련 정보를 보다 세밀하고 정확하게 브라우징 할 수 있도록 정보를 제공하고자 하였다.