• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.97-100
• /
• 2000

As network resources have become faster and demands for multimedia service through network have increased, the demand for Media server system has increased. These kinds of media server solve their bottle neck problem of internal storage device by using parallel system which takes advantage of fast network resource. Many vendors have suggested each of their media server system to solve these problem radically, but most of them require major modification of infra component and additional drawback has added. For example, storage mechanism for specific media requires new file system which is totally different from traditional one, and algorithm for enhancing performance may not suit for traditional operating system environment. In this paper, we designed a parallel media server based on web interface of traditional system and implemented a program for media server. Implemented server system performs parallel processing through web interface without any modification of traditional system, and controls which is related to merging load by distributed data is charged only to client and control server and consequently load of storage server can be minimized. And also, data transfer protocol for streaming media includes Retransfer algorithm and client Admission control policy relevant to performance of whole system.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.963-973
• /
• 2016

Providing a semantic knowledge system using media ontologies requires not only conventional axiom reasoning but also knowledge extension based on various types of reasoning. In particular, spatio-temporal information can be used in a variety of artificial intelligence applications and the importance of spatio-temporal reasoning and expression is continuously increasing. In this paper, we append the LOD data related to the public address system to large-scale media ontologies in order to utilize spatial inference in reasoning. We propose an RDFS/Spatial inference system by utilizing distributed memory-based framework for reasoning about large-scale ontologies annotated with spatial information. In addition, we describe a distributed spatio-temporal SPARQL parallel query processing method designed for large scale ontology data annotated with spatio-temporal information. In order to evaluate the performance of our system, we conducted experiments using LUBM and BSBM data sets for ontology reasoning and query processing benchmark.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.09a
• /
• pp.111-118
• /
• 2010

최근 IT 분야에서 인터넷을 기반으로 IT 자원들을 서비스 형태로 제공하는 클라우드 컴퓨팅에 대한 연구가 활발히 진행되고 있다. 한편, 효율적인 클라우드 컴퓨팅을 제공하기 위해서는, 막대한 양의 데이터를 수많은 서버들에 분산 처장하고 관리하기 위한 분산 데이터 처장 기법 빛 분산 병렬 처리 기법에 대한 연구가 필수적이다. 이를 위해 본 논문에서는 대표적인 분산 병렬 처리 기법에 대해 살펴보고, 이를 비교 분석한다. 마지막으로 Hadoop 기반 클러스터를 구축하고 이를 통해서 대규모 데이터를 위한 분산 병렬 처리 기법에 대한 성능평가를 수행한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.378-383
• /
• 2001

Intranet 환경에 다수의 유휴 호스트를 이용하여 많은 계산량을 지닌 응용 문제를 분산시켜 병렬 수행함으로써 효율성의 향상이 기대된다. 하지만 유휴 호스트를 이용하는데 있어서 이질성과 가변성 및 자율성으로 인해 요청에 대한 신뢰성을 예측하기가 어렵다. 본 논문에서는 태스크 할당 및 호스트 관리에 있어서 부하 균등을 위한 동적 분산 병렬 스킴인 적응적 태스크 재할당 기법을 제시한다. 또한, 이미지 랜더링 생성과 프랙탈 이미지 처리와 같은 많은 연산량을 지닌 응용 문제를 PDSWeb 시스템에 적용하여 제안 알고리즘의 성능을 분석하고 평가한다.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.434-437
• /
• 1999

본 연구에서는 워크스테이션 상에서 최적조류계산의 효율적인 분산병렬처리 기법을 개발하였다. 본 연구의 결과를 실제로 2587개의 송전선을 포함하는 미국 ERCOT 계통에 대하여 사례 연구한 결과 성능이 뛰어남을 알 수 있었다. 본 연구는 최적 조류계산을 병렬 처리하는 일반적인 방식을 제시해 줄 수 있을 것이라 생각된다.

• Proceedings of the KIEE Conference
• /
• 2001.07e
• /
• pp.67-71
• /
• 2001

Nowdays, we can communicate using Information Technology such as internet, personal computer, mobile phone etc. To protect global environment, it is also reqired to invent products efficiently reduce energy consumption. here, I studied organic EL and inorganic EL because organic EL display is appropriate device as light, thin, energy-saying display following CRT, LCD. As a result, I realized that we are supposed to study more on invention, efficiency and mass-production of materials. Comparing with another display, however, it would be marketable in few years, considering short history of its full-scaled studies.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.533-540
• /
• 2006

This paper describes the design and implementation of a grid system META (Metacomputing Environment using Test-run of Application) which facilitates the execution of a CFD (Computational Fluid Dynamics) analysis program on distributed environment. The grid system META allows the CFD program developers can access the computing resources distributed over the network just like one computer system. The research issues involved in the grid computing include fault-tolerance, computing resource selection, and user-interface design. In this paper, we exploits an automatic resource selection scheme for executing the parallel SPMD (Single Program Multiple Data) application written in MPI (Message Passing Interface). The proposed resource selection scheme is informed from the network latency time and the elapsed time of the kernel loop attained from test-run. The network latency time highly influences the executional performance when a parallel program is distributed and executed over several systems. The elapsed time of the kernel loop can be used as an estimator of the whole execution time of the CFD Program due to a common characteristic of CFD programs. The kernel loop consumes over 90% of the whole execution time of a CFD program.

• Sleep Medicine and Psychophysiology
• /
• v.4 no.1
• /
• pp.15-28
• /
• 1997

Longterm memory is encoded in the neuronal connectivities of the brain. The most successful models of human memory in their operations are models of distributed and self-organized associative memory, which are founded in the principle of simulaneous convergence in network formation. Memory is not perceived as the qualities inherent in physical objects or events, but as a set of relations previously established in a neural net by simultaneousy occuring experiences. When it is easy to find correlations with existing neural networks through analysis of network structures, memory is automatically encoded in cerebral cortex. However, in the emergence of informations which are complicated to classify and correlated with existing networks, and conflictual with other networks, those informations are sent to the subcortex including hippocampus. Memory is stored in the form of templates distributed across several different cortical regions. The hippocampus provides detailed maps for the conjoint binding and calling up of widely distributed informations. Knowledge about the distribution of correlated networks can transform the existing networks into new one. Then, hippocampus consolidats new formed network. Amygdala may enable the emotions to influence the information processing and memory as well as providing the visceral informations to them. Cortico-striatal-pallido-thalamo-cortical loop also play an important role in memory function with analysis of language and concept. In case of difficulty in processing in spite of parallel process of informations, frontal lobe organizes theses complicated informations of network analysis through temporal processing. With understanding of brain mechanism of memory and information processing, the brain mechanism of mental phenomena including psychopathology can be better explained in terms of neurobiology and meuropsychology.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.96-106
• /
• 2009

Extending the scale of the distributed processing in a single Ethernet cluster is physically restricted by maximum ports per switch. This paper presents an implementation of MPI-based multicluster consisting of multiple Ethernet switches for extending the scale of distributed processing, and a asymptotical analysis for communication overhead through execution-time analysis model. To determine an optimum task partitioning, we analyzed the processing time for various partitioning schemes, and AAP(accumulator array partitioning) scheme was finally chosen to minimize the overall communication overhead. The scope of data partitioned in AAP was modified to fit for incremented nodes, and suitable load balancing algorithm was implemented. We tried to alleviate the communication overhead through exploiting the pipelined broadcast and flat-tree based result gathering, and overlapping of the communication and the computation time. We used the linear pipeline broadcast to reduce the communication overhead in intercluster which is interconnected by a single link. Experimental results shows nearly linear speedup by the proposed parallel distributed GHT implemented on MPI-based Ethernet multicluster with four 100Mbps Ethernet switches and up to 128 nodes of Pentium PC.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.443-450
• /
• 2009

Purpose: Conventional image reconstruction uses simplified physical models of projection. However, real physics, for example 3D reconstruction, takes too long time to process all the data in clinic and is unable in a common reconstruction machine because of the large memory for complex physical models. We suggest the realistic distributed memory model of fast-reconstruction using parallel processing on personal computers to enable large-scale technologies. Materials and Methods: The preliminary tests for the possibility on virtual manchines and various performance test on commercial super computer, Tachyon were performed. Expectation maximization algorithm with common 2D projection and realistic 3D line of response were tested. Since the process time was getting slower (max 6 times) after a certain iteration, optimization for compiler was performed to maximize the efficiency of parallelization. Results: Parallel processing of a program on multiple computers was available on Linux with MPICH and NFS. We verified that differences between parallel processed image and single processed image at the same iterations were under the significant digits of floating point number, about 6 bit. Double processors showed good efficiency (1.96 times) of parallel computing. Delay phenomenon was solved by vectorization method using SSE. Conclusion: Through the study, realistic parallel computing system in clinic was established to be able to reconstruct by plenty of memory using the realistic physical models which was impossible to simplify.