• Title/Summary/Keyword: 아키텍처 평가

Search Result 248, Processing Time 0.033 seconds

A Design of Pipeline Chain Algorithm Based on Circuit Switching for MPI Broadcast Communication System (MPI 브로드캐스트 통신을 위한 서킷 스위칭 기반의 파이프라인 체인 알고리즘 설계)

  • Yun, Heejun;Chung, Wonyoung;Lee, Yong-Surk
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.37B no.9
    • /
    • pp.795-805
    • /
    • 2012
  • This paper proposes an algorithm and a hardware architecture for a broadcast communication which has the worst bottleneck among multiprocessor using distributed memory architectures. In conventional system, The pipelined broadcast algorithm is an algorithm which takes advantage of maximum bandwidth of communication bus. But unnecessary synchronization process are repeated, because the pipelined broadcast sends the data divided into many parts. In this paper, the MPI unit for pipeline chain algorithm based on circuit switching removing the redundancy of synchronization process was designed, the proposed architecture was evaluated by modeling it with systemC. Consequently, the performance of the proposed architecture was highly improved for broadcast communication up to 3.3 times that of systems using conventional pipelined broadcast algorithm, it can almost take advantage of the maximum bandwidth of transmission bus. Then, it was implemented with VerilogHDL, synthesized with TSMC 0.18um library and implemented into a chip. The area of synthesis results occupied 4,700 gates(2 input NAND gate) and utilization of total area is 2.4%. The proposed architecture achieves improvement in total performance of MPSoC occupying relatively small area.

A Feature-Oriented Requirement Tracing Method with Value Analysis (가치분석을 통한 휘처 기반의 요구사항 추적 기법)

  • Ahn, Sang-Im;Chong, Ki-Won
    • The Journal of Society for e-Business Studies
    • /
    • v.12 no.4
    • /
    • pp.1-15
    • /
    • 2007
  • Traceability links are logical links between individual requirements and other system elements such as architecture descriptions, source code, and test cases. These are useful for requirements change impact analysis, requirements conflict analysis, and requirements consistency checking. However, establishing and maintaining traceability links places a big burden since complex systems have especially yield an enormous number of various artifacts. We propose a feature-oriented requirements tracing method to manage requirements with cost benefit analysis, including value consideration and intermediate catalysis using features. Our approach offers two contributions to the study of requirements tracing: (1)We introduce feature modeling as intermediate catalysis to generate traceability links between user requirements and implementation artifacts. (2)We provide value consideration with cost and efforts to identify traceability links based on prioritized requirements, thus assigning a granularity level to each feature. In this paper, we especially present the results of a case study which is carried out in Apartment Ubiquitous Platform to integrate and connect home services in an apartment complex in details.

  • PDF

Weakly-supervised Semantic Segmentation using Exclusive Multi-Classifier Deep Learning Model (독점 멀티 분류기의 심층 학습 모델을 사용한 약지도 시맨틱 분할)

  • Choi, Hyeon-Joon;Kang, Dong-Joong
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.19 no.6
    • /
    • pp.227-233
    • /
    • 2019
  • Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

WLAN CR Coexistence Beacon Protocol for Cognitive Radio-Based WLAN Network (무선인지 기술을 이용한 차세대 WLAN 네트워크에서의 WLAN CR 공존 비콘 프로토콜)

  • Kim, Hyun-Ju;Yoo, Sang-Jo
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.32 no.12B
    • /
    • pp.790-799
    • /
    • 2007
  • In this paper, we propose WLAN CR coexistence beacon protocol for thenext WLAN network. This method can provide WLAN with high-speed data rate in new WLAN architecture and network platform based on cognitive radio technology. WLAN CR devices that enter the CR network can know UHF channels by listening CR beacon including the coexistence parameter set and start using CR channel fast. During handover of WLAN device in UHF spectrums, WLAN device that lost their channel can change available channel by obtaining the current CR channel information from the CR beacon. In advance relaying coexistence parameter set to entire CR system, WLAN CR system can prepare own candidate channel set that is different with other CR system. In CR beacon and relay delay, we show the results that WLAN CR coexistence beacon protocol supports spectrum handover efficiently and decreases the probability of collision in candidate channel set.

A Dynamic Resource Allocation Method in Tactical Network Environments Based on Graph Clustering (전술 네트워크 환경에서 그래프 클러스터링 방법을 이용한 동적 자원 할당 방법)

  • Kim, MinHyeop;Ko, In-Young;Lee, Choon-Woo
    • Journal of KIISE:Software and Applications
    • /
    • v.41 no.8
    • /
    • pp.569-579
    • /
    • 2014
  • In a tactical-edge environment, where multiple weapon resources are coordinated together via services, it is essential to make an efficient binding between an abstract service and a resource that are needed to execute composite services for accomplishing a given mission. However, the tactical network that is used in military operation has low bandwidth and a high rate of packet loss. Therefore, communication overhead between services must be minimized to execute composite services in a stable manner in the tactical network. In addition, a tactical-edge environment changes dynamically, and it affects the connectivity and bandwidth of the tactical network. To deal with these characteristics of the tactical network we propose two service-resource reallocation methods which minimize the communication overhead between service gateways and effectively manage neutralization of gateways during distributed service coordination. We compared the effectiveness of these two - methods in terms of total communication overhead between service gateways and resource-allocation similarity between the initial resource allocation and the reallocation result.

Real-Time Support on Multi-Processor for Windows (멀티프로세서 윈도우즈 상에서 실시간성 지원)

  • Song, Chang-In;Lee, Seung-Hoon;Ju, Min-Gyu;Lee, Cheol-Hoon
    • The Journal of the Korea Contents Association
    • /
    • v.12 no.6
    • /
    • pp.68-77
    • /
    • 2012
  • As the system development environment moves from single core to multi core-based platforms, it becomes more important to maintain compatibility between single core-based implementations and multi core-based implementations. Moreover, it is very important to support real-time on multi core platforms especially in cases of embedded software or test equipments which need real-time as well as correctness. Since Windows operating system dopes not support real-time in itself, it has been supporting real-time using expensive third-party solutions such as RTX or INtime. So as to reduce this kind of development expenses, in this paper, we propose RTiK-MP(Real-Time implant Kernel-Multi Processor) which supports real-time on Windows using the Local APIC of x86 architectures, and evaluate the performance of the proposed RTiK-MP after deploying it on portable missile test equipments.

Two-Dimensional Grouping Index for Efficient Processing of XML Filtering Queries (XML 필터링 질의의 효율적 처리를 위한 이차원 그룹핑 색인기법)

  • Yeo, Dae-Hwi;Lee, Jong-Hak
    • Journal of Information Technology and Architecture
    • /
    • v.10 no.1
    • /
    • pp.123-135
    • /
    • 2013
  • This paper presents a two-dimensional grouping index(2DG-index) for efficient processing of XML filtering queries. Recently, many index techniques have been suggested for the efficient processing of structural relationships among the elements in the XML database such as an ancestor- descendant and a parent-child relationship. However, these index techniques focus on simple path queries, and don't consider the path queries that include a condition value for filtering. The 2DG-index is an index structure that deals with the problem of clustering index entries in the twodimensional domain space that consists of a XML path identifier domain and a filtering data value domain. For performance evaluation, we have compared our proposed 2DG-index with the conventional one dimensional index structure such as the data grouping index (DG-index) and the path grouping index (PG-index). As the result of the performance evaluations, we have verified that our proposed 2DG-index can efficiently support the query processing in XML databases according to the query types.

CTQ Table Extraction Method Using Social Network Analysis (사회연결망분석을 활용한 CTQ(Critical-To-Quality) 테이블 추출 기법)

  • Kim, Seung Hee;Cho, Nam Wook;Kim, Woo Je
    • Journal of Information Technology and Architecture
    • /
    • v.10 no.3
    • /
    • pp.347-359
    • /
    • 2013
  • The quality control of data is important element in data usage activations and decision makings. This paper is on how to extract the major critical data by each institution or organization selves. It proposes a social network analysis as a way to extract a table of high influence degree from a dynamic meta-data. The proposed CTQ data extraction method using SNA proved the fact that it is possible to extract highly accurate CTQ data by scientific measures of three-dimensional approach to real business situations without professional technicians. It is a new way that will change the goings on CTQ data management in IT sector and will improve the quality management level of an organization when applied to the real world.

A Study of Establishment of Softwaresystem Configuration for Improving Health Information Sharing (의료정보 공유기능 향상을 위한 소프트웨어시스템 기반구성 방법에 관한 연구)

  • Han, Soon-Hwa;Ju, Se-Jin
    • Journal of Digital Contents Society
    • /
    • v.15 no.1
    • /
    • pp.11-18
    • /
    • 2014
  • The strength of our country is based on high-speed networks to build a nationwide health information network to improve the quality of health care is needed. However, nature of the medical services in the hospital medical record form, so that all departments characterize each medical department, a common format that can be used for all disease is a very difficult challenge. This study is one of the ways to improve this priority issue on health information sharing medical information system(PACS/HIS) information linkage between the problem of information, compatibility and security issues derived. The problem is derived from the requirements of theorem 3 to 6 items. This is effective in order to improve sharing of medical information for the purpose of designing the software system. Sharing of medical information software system design are derived from stakeholders, requirements analysis, architecture design, software framework, configuration, architecture evaluation process. This study is based on the medical information standardization environmental diagnosis of a medical information system design. Software design philosophy is based on a new framework for deriving the function and mechanism made up.

Case Study on EA Performance in Total Reconstruction Project of Korean National Customs Information Network (국가관세종합정보망 전면재구축 사업을 통한 EA 성과연구)

  • Park, Sungsik;Shin, Hyosang;Lee, Seogjun
    • Journal of Information Technology and Architecture
    • /
    • v.10 no.4
    • /
    • pp.479-496
    • /
    • 2013
  • Today, a corporate and the government is making significant investments in informatization in order to enhance competitiveness however, question on the outcome of information-oriented investment has continuously been posed and in order to resolve such problems, the technique of Enterprise Architecture (EA) Despite such fact, in the case of the central administrative institute, even if the EA maturity standard has continuously improved through continuous investment when compared to the past without deviation between institutes, the establishment of EA and the work utilization of EA compared to the management competence still is analyzed to be relatively weak. This study completed the preliminary feasibility study in 2012 for Korea Customs Service which has been appointed as the representative institute that best utilizes EA in the field of information operation and evaluation field in the 2010 EA Maturity Evaluation and it can become a case study that can contribute to more continuous development and improvement of other public institute EA by introducing the performance of EA-based 4th Korean National Customs Information Network which has entered into total reconstruction in 2013 and by identifying the implications of EA performance arising from such.