• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.656-659
• /
• 2014

오픈소스로부터 촉발된 분산 시스템의 보편화로 기존 상용 시스템으로는 제공하지 못한 다양한 종류의 서비스가 각광받고 있다. 특히, 테라바이트 단위를 넘어 페타바이트 단위의 데이터를 다루는 서비스의 등장으로 드러난 오픈소스 분산 시스템의 문제를 개선하기 위한 시도가 학계 및 업계에서 다각적으로 이뤄지고 있다. 이러한 시도는 새로운 방법론을 제시하는 것에서부터 기존 분산 데이터베이스 관리 시스템(Distributed DBMS)에서 사용된 방법론들을 적용하는 것까지 다양하게 이뤄지고 있다. 본 논문에서는 특정 키 값(Key Value)에 불균등 분포된 데이터에 대한 조인 연산의 탐색 공간을 밀집 인덱스를 통해 줄여 비교적 높은 시간 복잡도를 완화하는 방법론을 제시하고자 한다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.21 no.8
• /
• pp.1024-1033
• /
• 1997

The past several years have witnessed an ever-increasing acceptance and adoption of parallel processing, both for high performance scientific computing as well as for more general purpose applications. Furthermore with increasing needs to perform the complex flow calculations in an efficient manner, the use of the message passing model on distributed networks has emerged as an important alternative to the expensive supercomputers. This work attempts to provide a generic framework to enable the parallelization of all CFD-related works using the master-slave model. This framework consists of (1) input geometry, (2) domain decomposition, (3) grid generation, (4) flow computations, (5) flow visualization, and (6) output display as the sequential components, but performs computations for (2) to (5) in parallel on the workstation clustering. The flow computations are parallized by having multiple copies of the flow-code to solve a PDE on different spatial regions on different processors, while their flow data are exchanged across the region boundaries, and the solution is time-stepped. The Parallel Virtual Machine (PVM) is used for distributed communication in this work.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.160-163
• /
• 2015

워크플로우 매니지먼트시스템은 오늘날의 어플리케이션들의 처리를 위한 효율적인 워크플로우 설계와 수행을 가능하게 한다. 그러나 전체물리학, 생물학, 지질학과 같이 과학탐구에 목적을 둔 어플리케이션들의 경우 대용량의 데이터를 연산해야 하기 때문에 단일 컴퓨팅 자원으로는 단 시간내에 작업을 완료하기 어렵다. 클라우드 환경에서 워크플로우를 효율적으로 수행하기 위해서는 여러 자원을 효율적으로 활용하기 위한 분산 병렬처리가 필수적이다. 일반적으로 시스템의 마스터노드에서는 클러스터의 원격노드들에게 어플리케이션 수행을 위해 설계된 워크플로우에 맞게 작업들을 분배하게 되는데 이때 마스터노드와 원격노드의 큐에서의 대기시간과 원격노드에서 할당된 작업들을 위한 스케줄링 시간은 성능을 좋지 않게 만드는 원인이 된다. 따라서 본 논문은 클라우드 환경에서 원격노드에서 작업수행이전까지의 지연시간을 줄이기 위한 최적화 방법으로 컴퓨팅 자원 활용도를 고려한 작업들의 병합 기법을 적용해서 워크플로우의 처리 속도를 향상시킨다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.73-78
• /
• 2019

This paper proposes polynomial-time rule for maximum weighted independent set(MWIS) problem that is well known NP-hard. The well known distributed algorithm selects the maximum weighted node as a element of independent set in a local. But the merged independent nodes with less weighted nodes have more weights than maximum weighted node are frequently occur. In this case, existing algorithm fails to get the optimal solution. To deal with these problems, this paper constructs maximum weighted independent set in local area. Application result of proposed algorithm to various networks, this algorithm can be get the optimal solution that fail to existing algorithm.

• Journal of Internet Computing and Services
• /
• v.16 no.6
• /
• pp.23-30
• /
• 2015

As BigData is issued, many applications that operate based on the results of data analysis have been developed, typically applications are products recommend service of e-commerce application service system, search service on the search engine service and friend list recommend system of social network service. In this paper, we suggests a decision frequent pattern tree that is combined the origin frequent pattern tree that is mining similar pattern to appear in the data set of the existing data mining techniques and decision tree based on the theory of computer science. The decision frequent pattern tree algorithm improves about problem of frequent pattern tree that have to make some a lot's pattern so it is to hard to analyze about data. We also proposes to model for a Mapredue framework that is a programming model to help to operate in distributed environment.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.439-448
• /
• 2006

Previous recognition/clustering algorithms such as Kohonen SOM(Self-Organizing Map), MLP(Multi-Layer Percecptron) and SVM(Support Vector Machine) might not adapt to unexpected input pattern. And it's recognition rate depends highly on the complexity of own training patterns. We could make up for and improve the weak points with lowering complexity of original problem without losing original characteristics. There are so many ways to lower complexity of the problem, and we chose a kernel concepts as an approach to do it. In this paper, using a kernel concepts, original data are mapped to hyper-dimension space which is near infinite dimension. Therefore, transferred data into the hyper-dimension are distributed spasely rather than originally distributed so as to guarantee the rate to be risen. Estimating ratio of recognition is based on a new similarity-probing and learning method that are proposed in this paper. Using CEDAR DB which data is written in cursive letters, 0 to 9, we compare a recognition/clustering performance of kSOM that is proposed in this paper with previous SOM.

• Journal of Internet Computing and Services
• /
• v.10 no.1
• /
• pp.101-110
• /
• 2009

Multi-agent systems are mostly used to integrate the intelligent and distributed approaches to various systems for effective sharing of resources and dynamic system reconfigurations. Object replication is usually used to implement fault tolerance and solve the problem of unexpected failures to the system. This paper presents the intelligent multi-agent distributed platform based on the dynamic object group management and proposes an object search technique based on the proposed filtered k-means (Fk-means). We propose Fk-means for the search mechanism to find alternative objects in the event of object failures and transparently reconnect client to the object. The filtering range of Fk-means value is set only to include relevant objects within the group to perform the search method efficiently. The simulation result shows that the proposed mechanism provides fast and accurate search for the distributed object groups.

• The Korean Journal of Malacology
• /
• v.12 no.1
• /
• pp.1-17
• /
• 1996

Morphological and histochemical characteristics of the cells in posterior tentacle antenna of Korean slug, Incilaria fruhstorferi were observed with light microscope. The epithelium of the posterior tentacle antenna was composed of supporting cells, sensory neurons and type-a clear cell. The columnar supporting epithelium was widely distributed in the posterior tentacle antenna, and the upper end of the cell was covered with acidic mucopolysaccharide. Nerve endings of the sensory neuron were distributed between type-a clear cells. It was usually located in tentacular knob, and the number of them gradually decrdased as close as tentacular stalk. Several cilia were observed on the nerve ending. Type-a clear cells were very brightly stained with all staining used, and the neutral mucous guanules distributed in the cytoplasm. Collar cells, type-b clear cell and various types of secrdtory cells distributed in the connective tissue. The collar cells were clustering in connective tissue, and the cytoplasm were filled with neutral mucous guanules. The cells and granules were stained with dark brown by silver nitrate stain. Type-b clear cells were irregular in shape and their cytoplasms were brightly stained wth many stains used. Ten types of secretory cells evenly distributed in the connective tissue and muscle layers of the posterior tentacle antenna. The five types of the secretory cells(A, B, E, J and L)seemed to secrete acidic mucopolysaccharide, and the other five type of the cell(C, D, F, H, and L)seemed to secrete neutral mucopolysaccharide. Muscular tissue composed of well-developed thick longitudinal muscle layers and thin circular muscle layers. Type-L secretory cells clustered only in muscular layers and they contained acidic mucopolysaccharides.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2488-2511
• /
• 2015

Data redundancy has high impact on Wireless Sensor Network's (WSN) performance and reliability. Spatial and temporal similarity is an inherent property of sensory data. By reducing this spatio-temporal data redundancy, substantial amount of nodal energy and bandwidth can be conserved. Most of the data gathering approaches use either temporal correlation or spatial correlation to minimize data redundancy. In Collective Prediction exploiting Spatio Temporal correlation (CoPeST), we exploit both the spatial and temporal correlation between sensory data. In the proposed work, the spatial redundancy of sensor data is reduced by similarity based sub clustering, where closely correlated sensor nodes are represented by a single representative node. The temporal redundancy is reduced by model based prediction approach, where only a subset of sensor data is transmitted and the rest is predicted. The proposed work reduces substantial amount of energy expensive communication, while maintaining the data within user define error threshold. Being a distributed approach, the proposed work is highly scalable. The work achieves up to 65% data reduction in a periodical data gathering system with an error tolerance of 0.6℃ on collected data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.413-417
• /
• 2007

Ad hoc 센서 네트워크에서 노드는 제한된 에너지를 가지며, 에너지의 사용률은 토폴로지 구조나 센서 노드의 동작에 의존한다. 본 논문에서는 low power distributed MAC을 개량 하여, MANET에서 clustering 구조의 네트워크를 위한 효율적인 에너지 절약을 위한 새로운 구조를 제안한다. 본 제안된 구조의 특징은 Ad hoc 네트워크에서 에너지에 관련된 배터리 파워나, 노드의 거리, 전송 전력 등의 정보를 활용한 상황 인식을 사용하였다. 에너지 상황 인식을 적용한 제안된 망의 구조는 clustering 형상과 메시지 전송의 성능 및 데이터의 도달 인식을 향성 시킨다. 또한 context aware computing을 이용함으로써, 상황과 정의된 rule에 따라서 노드의 동작과 네크워크 라우팅의 상황에 적응하도록 노드를 조정 할 수 있는 구조이다.