• 전자공학회논문지C
• /
• 제34C권7호
• /
• pp.70-81
• /
• 1997

In this paper, we propose HMCNN(hybrid multiple component neural networks) that enhance performance of MCNN by adapting new pattern partitioning algorithm which can cluster many input patterns efficiently. Added neural network performs similar learning procedure that of kohonen network. But it dynamically determine it's number of output neurons using algorithms that decide self-organized number of clusters and patterns in a cluster. The proposed network can effectively be applied to problems of large data as well as huge networks size. As a sresutl, proposed pattern partitioning network can enhance performance results and solve weakness of MCNN like generalization capability. In addition, we can get more fast speed by performing parallel learning than that of other supervised learning networks.

• 대한산업공학회지
• /
• 제22권4호
• /
• pp.567-578
• /
• 1996

In relational databases the number of disk accesses depends on the amount of data transferred from disk to main memory for processing the transactions. N-ary vertical partitioning of the relation can often result in a decrease in the number of disk accesses, since not all attributes in a tuple are required by each transactions. In this paper, a 0-1 integer programming model for solving n-ary vertical partitioning problem minimizing the number of disk accesses is formulated and a branch-and-bound method is used to solve it. A preprocessing procedure reducing the number of variables is presented. The algorithm is illustrated with numerical examples and is shown to be computationally efficient. Numerical experiments reveal that the proposed method is more effective in reducing access costs than the existing algorithms.

• 천문학회지
• /
• 제52권2호
• /
• pp.49-55
• /
• 2019

The New Vacuum Solar Telescope (NVST) is the largest solar telescope in China. When using CCDs for imaging, equal-thickness fringes caused by thin-film interference can occur. Such fringes reduce the quality of NVST data but cannot be removed using standard flat fielding. In this paper, a correction method based on multi-scale decomposition and adaptive partitioning is proposed. The original image is decomposed into several sub-scales by multi-scale decomposition. The region containing fringes is found and divided by an adaptive partitioning method. The interference fringes are then filtered by a frequency-domain Gaussian filter on every partitioned image. Our analysis shows that this method can effectively remove the interference fringes from a solar image while preserving useful information.

• 한국통신학회논문지
• /
• 제22권9호
• /
• pp.2080-2089
• /
• 1997

최근 급격히 발전된 컴퓨터 기술에 힘입어 다양한 분야에서의 멀티미디어 데이터 처리가 가능하게 되었다. 그러나, 기존의 디스크 저장 시스템으로 멀티미디어의 특징을 수용하기에는 무리가 있다. 현재, 몇몇의 연구에서 멀티미디어 저장에 관한 향상된 기술을 소개하였고, 그 중 Bocheck는 엑세스 주기와 단위가 동일한 다중스트림의 분할 저장 기법을 제안하였으나, 서로 상이한 주기를 갖는 연속 미디어의 스트림에 관해서는 고려되지 않았다. 이 논문에서는 조회 주기가 서로 상이한 스트림을 고정된 몇 개의 블록으로 할당하는 방안을 제안하고 주어진 다중스트림을 m개의 시퀀스로 스케줄링시 그 가능성을 분석하였으며, 기존의 Scan-EDF와 디스크 분할 저장 방식과 비교하기 위해서 시뮬레이션을 행하였다.

• 한국정보처리학회논문지
• /
• 제6권4호
• /
• pp.901-915
• /
• 1999

분산 메모리 병렬 컴퓨터의 성능을 충분히 활용하고 프로그래밍의 난이도아 기종간 프로그램의 호환성을 해결하기 위하여 시스템 독립적이고 쉽게 프로그래밍 할 수 있는 데이터 병렬 언어에 대한 연구가 최근에 활발히 진행되고 있다. 대표적인 데이터 병렬 언어인 HPF 컴파일러는 사용자가 정의한 정보를 이용하여 데이터와 연산을 프로세서에 분할하여 할당하고, 메시지 패싱을 생성하는 기능을 제공함으로써 프로그램 작성자에게 전역 주소 공간을 이용하여 병렬 프로그램을 쉽게 개발 할 수 있는 기반을 제공한다. 본 논문에서는 데이터 종속성 분석, 데이터 및 연산 분할과 메시지 패싱 코드 생성의 4단계를 통하여, HPf 입력 프로그램을 MPI 메시지 패싱 코드가 삽입된 SPMD 프로그램으로 변환하는 HPF 병렬 프로그래밍 언어 변환기인 PPTran을 구현하고 그 성능을 검증한다.

• Genomics & Informatics
• /
• 제1권1호
• /
• pp.20-24
• /
• 2003

The analysis of DNA microarry data is one of the most important things for functional genomics research. The matrix representation of microarray data and its successive 'optimal' incisional hyperplanes is a useful platform for developing optimization algorithms to determine the optimal partitioning of pairwise proximity matrix representing completely connected and weighted graph. We developed Deterministic Annealing (DA) approach to determine the successive optimal binary partitioning. DA algorithm demonstrated good performance with the ability to find the 'globally optimal' binary partitions. In addition, the objects that have not been clustered at small non­zero temperature, are considered to be very sensitive to even small randomness, and can be used to estimate the reliability of the clustering.

• 인터넷정보학회논문지
• /
• 제18권6호
• /
• pp.47-53
• /
• 2017

Recently, huge datasets have been generating rapidly in a variety of fields. Then, there is an urgent need for technologies that will allow efficient and effective processing of huge datasets. Therefore the problems of partitioning a huge dataset effectively and alleviating the processing overhead of the partitioned data efficiently have been a critical factor for scalability and performance in distributed database system. In our work we utilized multicore servers to provide scalable service to our distributed system. The partitioning of database over multicore servers have emerged from a need for new architectural design of distributed database system from scalability and performance concerns in today's data deluge. The system allows uniform access through a web service interface to concurrently distributed databases over multicore servers, using SQMD (Single Query Multiple Database) mechanism based on publish/subscribe paradigm. We will present performance results with the distributed database system built on multicore server, which is time intensive with traditional architectures. We will also discuss future works.

• Journal of the Korean Data and Information Science Society
• /
• 제14권4호
• /
• pp.725-736
• /
• 2003

To provide the information needed to make a decision, it is important to know the relationship or pattern between variables in database. Grouping objects which have similar characteristics of pattern is called as cluster analysis, one of data mining techniques. In this study, it is compared with several partitioning clustering algorithms, based on the statistical distance or total variance in each cluster.

• 한국물환경학회지
• /
• 제36권3호
• /
• pp.229-244
• /
• 2020

Hydrologic models, as a useful tool for understanding the hydrologic phenomena in the watershed, have become more complex with the increase of computer performance. The hydrologic model, with complex configurations and powerful performance, facilitates a broader understanding of the effects of climate and soil in hydrologic partitioning. However, the more complex the model is, the more effort and time is required to drive the model, and the more parameters it uses, the less accessible to the user and less applicable to the ungauged watershed. Rather, a parsimonious hydrologic model may be effective in hydrologic modeling of the ungauged watershed. Thus, a semi-distributed hydrologic partitioning model was developed with minimal composition and number of parameters to improve applicability. In this study, the validity and performance of the proposed model were confirmed by applying it to the Namgang Dam, Andong Dam, Hapcheon Dam, and Milyang Dam watersheds among the Nakdong River watersheds. From the results of the application, it was confirmed that despite the simple model structure, the hydrologic partitioning process of the watershed can be modeled relatively well through three vertical layers comprising the surface layer, the soil layer, and the aquifer. Additionally, discussions were conducted on antecedent soil moisture conditions widely applied to stormwater estimation using the soil moisture data simulated by the proposed model.

• 한국공간정보시스템학회 논문지
• /
• 제12권1호
• /
• pp.37-48
• /
• 2010

본 논문에서는 그리드 분할과 매핑함수에 기반하여 영역질의 성능향상을 위해서 기존에 제시된 디클러스터링 방법들을 다차원 공간에 대해서 적용할 때의 문제점을 분석하고 해결법을 제시한다. 다차원 공간에 대해서 기존에 제시된 방법들을 적용할 때의 문제점은 각 차원의 분할 횟수가 적고(대부분 이진 분할이 발생함) 극히 작은 선택률에 대해서도 영역질의 각 차원의 길이가 커지기 때문에 발생한다. 본 논문에서는 이를 해결하기 위하여 다차원 공간의 다양한 그리드 분할방법에 대해서 수학적으로 성능을 예측하는 모델을 제시한다. 제시한 수학 모델을 이용하여 가능한 다양한 그리드 분할 방법들 가운데 영역질의와 겹치는 그리드 셀의 수를 감소시키는 분할 방법을 선택할 수 있으며, 이는 디클러스터링 알고리즘의 전체 성능향상으로 귀결된다. 다양한 실험결과, 본 논문에서 제시한 분할 방법을 적용할 때, 기존에 제시된 디클러스터링 알고리즘의 성능을 최대 2.7배까지 향상시킬 수 있음을 알 수 있었다.