• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9C
• /
• pp.748-755
• /
• 2010

In this paper we propose an improved face recognition method using Gabor tensor. Gabor transform is known to be able to represent characteristic feature in face and reduced environmental influence. It may contribute to improve face recognition ratio. We attempted to combine three-dimensional tensor from Gabor transform with MPCA(Multilinear PCA) and LDA. MPCA with tensor which use various features is more effective than traditional one or two dimensional PCA. It is known to be robust to the change of face expression or light. Proposed method is simulated by MATALB9 using ORL and Yale face database. Test result shows that recognition ratio is improved maximum 9~27% compared with exisisting face recognition method.

• Journal of Korea Spatial Information System Society
• /
• v.7 no.2 s.14
• /
• pp.81-89
• /
• 2005

Declustering and parallel index structures are important research areas to improve a performance of databases. Previous researches proposed several distribution schemes for parallel R-trees, however there is no search schemes to be suitable for the index. In this paper, we propose schemes to improve the performance of range queries for distribute parallel indexes. The proposed schemes use the features that a parallel disk can read multiple nodes from various disks. The proposed schemes are verified using various implementations and performance evaluations. We propose new schemes which can read multiple nodes from multiple disks in contrast that to the previous schemes which can read a node from disk. The experimental evaluation shows that the proposed schemes give us the performance improvement by 40% from the previous researches.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.8
• /
• pp.601-605
• /
• 2009

Recently, photo sharing and publishing based Social Network Sites(SNSs) are increasingly attracting the attention of academic and industry researches. Millions of users have integrated these sites into their daily practices to communicate with online people. In this paper, we propose an efficient face annotation and retrieval system under SNS. Since the system needs to deal with a huge database which consists of an increasing users and images, both effectiveness and efficiency are required, In order to deal with this problem, we propose a face annotation classifier which adopts an online learning and social decomposition approach. The proposed method is shown to have comparable accuracy and better efficiency than that of the widely used Support Vector Machine. Consequently, the proposed framework can reduce the user's tedious efforts to annotate face images and provides a fast response to millions of users.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.419-424
• /
• 2006

대청호로 유입하는 탁수의 감시와 저수지내의 시공간분포를 예측할 수 있는 실시간 탁수감시 및 예측시스템(RTMMS)을 개발하였다. RTMMS는 탁도와 수온 등 실시간 계측자료를 데이터베이스에 저장.조회하는 실시간 감시(Realtime Monitoring), 2차원 탁수예측 수치모델의 입력자료 생성(Input Data), 탁수예측 수치모델의 수행 (W2 Run), 모의결과의 조회 및 저수지 운영 시나리오별 탁수조절 효과분석을 위한 후처리 (Post-Process) 기능을 제공한다. 시스템의 GUI 화면은 개별 기능을 탭 형식으로 제공하여 사용자가 순차적으로 자료조회와 모델수행 그리고 결과분석을 쉽게 수행할 수 있도록 설계하였다. RTMMS는 강우사상 동안 유입하천의 수온예측을 위해 대기기온, 이슬점온도, 하천유량자료를 독립변수로 이용하는 다중회귀모델(DMR)을 사용하며, 탁도 예측은 유량과 SS 부하량의 상관관계를 이용하는 탁도예측모델(QLM)을 사용한다. 저수지로 유입한 탁수의 밀도류 거동과 시공간적인 탁도분포 예측은 2차원 횡방향 평균 수리 수질해석 모형인 CE-QUAL-W2를 채택하였다. 개발된 시스템은 2004년 홍수기를 대상으로 시범적용 하였으며, 그 결과를 실측자료와 비교하여 제시하였다. RTMMS는 저수지 탁수발생 현황조회, 취수원 도달시간 및 지속기간, 밀도류와 전도현상을 고려한 시공간 분포 예측, 발전 및 수문방류, 선택취수 등 다양한 저수지운영 시나리오에 따른 상.하류 영향 분석, 용수 이용자에게 탁도 예측정보의 제공 등 탁수를 고려한 저수지운영 의사결정지원 도구로써 매우 유용하게 활용 될 것으로 기대된다.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.53-61
• /
• 2020

Recently, as the uncontact service is activated in earnest due to the Corona 19 virus, the necessity of system development to provide non-face-to-face contact remote medical service has increased. In this study, we propose a smart healthcare system, Rm_She(Remote Medical Smart Healthcare System). Rm_She can collect and manage various vital signs information by connecting various healthcare products that detect bio-signals based on IoT to one application. The health check app (HC_app) is used to connect vital sign measurement devices to a wireless LAN and receive vital sign values from the HC_app. Then, the vital signs are output to the user on the smartphone, and the corresponding information is transmitted to the healthcare management server. The healthcare server receives the measured values and stores them in a database, and the stored measured values are provided as a web service so that medical staff can remotely monitor them in real time.

• Progress in Medical Physics
• /
• v.6 no.2
• /
• pp.93-101
• /
• 1995

In this paper, we implemented a digital medical image management and a remote monitor display system for a personal computer. The designed system can display up to a 1280${\times}$1024 image which can accomodate eight images with a 256${\times}$256${\times}$8bits. When one of these images is clicked by the mouse, the selected image can be displayed with 256${\times}$256${\times}$8bits or 1024${\times}$1024${\times}$8bits. For the selected image, we can use one of the image processing functions in this system and send it to a remote monitor for the close examinations. To search and store digital images effectively, we constructed and image database management system with the B＋TREE structure. This system can be operated in an IBM-PC 386 or higher and all the function are performed easily with a mouse to provide a user firendly environment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.2
• /
• pp.145-150
• /
• 2004

A protocol for the web-based GPS data processing system has been developed. The system is developed following the typical ASP system, in which the GPS data acquired by various users can be uploaded through the web and the data is processed with data processing components selected by the users. After the processing, the results are also transported to the users through the web. The developed system is designed for easy software upgrade and it is an synchronous process mode so that the multiple accesses can be handled with high user flexibility. The database components for the efficient GPS data maintenance are developed so that the data from CORS can be used for the data processing. Currently, the absolute and relative positioning algorithms using code measurements are integrated and much more algorithms such as the data quality control, absolute and relative positioning using phases will be integrated in near future.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.81-92
• /
• 2003

A protocol for the web-based GPS data processing system has been developed. The system is developed following the typical ASP system, in which the GPS data acquired by various users can be uploaded through the web and the data is processed with data processing components selected by the users. After the processing, the results are also transported to the users through the web. The developed system is designed for easy software upgrade and it is an asynchronous process mode so that the multiple accesses can be handled with high user flexibility. The database components for the efficient GPS data maintenance are developed so that the data from CORS can be used for the data processing. Currently, the absolute and relative positioning algorithms using code measurements are integrated and much more algorithms such as the data quality control, absolute and relative positioning using phases will be integrated in near future.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1753-1762
• /
• 1996

Since the number of spatial objects go easily into millions, they are stored on a secondary storage. In order to speed up accessing the geometric objects, we investigate spatial database system. The spatial objects are organized and accessed by spatial access methods(SAMs). But, SAMs are not able to organize polygons directly The most popular approach for handing polygon in SAMs is to use MBR apporximaotion as a geometric key. MBR provides a fast but inaccurate answers to approximation-based query processing. The performance of approximation-based spatial query processing depends on which type of approximation is chosen for the spatial objects. A suitable approximation is crucial for reducing the size of the candidate set. The better the approxmation quality, the fewer accesses to the exact object are necessary. In this paper, I proposed a new multicontainer approximation named Slice decomposition. The performance of proposed method is compared with other method.

• The KIPS Transactions:PartD
• /
• v.11D no.2
• /
• pp.259-268
• /
• 2004

For supporting Interoperability among heterogeneous data sources in different geographic information systems, it is required to use open API like OGIS OLE DB Proposed in OGC. The OLE/COM Implementation Specification of OGIS only provides interfaces to discover and access spatial data, but does not support interfaces for updating distributed spatial data. To solve this problem, we propose and add interfaces for updating spatial objects distributed over heterogeneous data sources and examining the consistency of spatial relationships between updated objects. We also devise a 2-phase commit protocol based on spatial relationships in order to guarantee the consistency of updated objects. To justify the update scheme using the proposed Interfaces and 2-phase commit prototype we design and implement a prototype system for updating distributed spatial objects.