• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.1-7
• /
• 1995

In sample survey for the estimation of low proportion, usually a large size of sample is required for a meaningful estimator. If the cost of a sample unit is high, we have to make every effort to improve the precision of the estimator. In this study, a new efficient allocation method of sample size in stratified sampling is proposed provided we have some prior information for the stratification.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.235-245
• /
• 2011

Early criticality prediction models that determine whether a design entity is fault-prone or not are becoming more and more important as software development projects are getting larger. Effective predictions can reduce the system development cost and improve software quality by identifying trouble-spots at early phases and proper allocation of effort and resources. Many prediction models have been proposed using statistical and machine learning methods. This paper builds a prediction model using Support Vector Machine(SVM) which is one of the most popular modern classification methods and compares its prediction performance with a well-known prediction model, BackPropagation neural network Model(BPM). SVM is known to generalize well even in high dimensional spaces under small training data conditions. In prediction performance evaluation experiments, dimensionality reduction techniques for data set are not used because the dimension of input data is too small. Experimental results show that the prediction performance of SVM model is slightly better than that of BPM and polynomial kernel function achieves better performance than other SVM kernel functions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.7B
• /
• pp.1313-1319
• /
• 2000

MPLS에서 ATM의 스위칭 기능은 인터넷 백본망에 대해 효율적인 전송을 제공할 것이다. 특히, VC merging은 다수의 IP 경로와 한 VC 레이블간의 대응을 가능케 함으로써 망의 확장 시에도 유연하게 대처 할 수 있다. 이미 VC merge 관련 메커니즘들이 제안되어 있으나 단지 best-effort 트래픽에 대해서만 가능하며 다중 클래스 트래픽에 대해 각 QoS를 충족시키는 구체적인 방안은 제시되어 있지 않다. 따라서, 본 논문에서는 각 클래스의 VC merge시, 동적 대역폭 할당을 적용해 merge된 트래픽의 QoS를 만족시키는 메커니즘 및 ATM-LSR의 구조를 제안한다. 아울러, 시뮬레이션을 통해 제안된 동적 VC 대역폭 할당 방안에 대한 성능 평가를 수행하였다.

• Asia pacific journal of information systems
• /
• v.16 no.2
• /
• pp.143-158
• /
• 2006

This paper considers probable determinants of the application software outsourcing costs and focuses on the service level agreement (SLA) influence. Recently, outsourcing clients and vendors have contracted SLA and tried to reflect them on outsourcing prices. While application software maintenance has been one of the most frequently outsourced functions, its cost did not reflect the service level requirements by the client. This paper empirically shows that the service urgency requirement on SLA increases the maintenance programmers' effort and thus increases the vendor's cost. This result can be used by vendors for program allocation purposes.

• Proceedings of the IEEK Conference
• /
• 2003.07a
• /
• pp.406-409
• /
• 2003

본 논문에서는 인터넷 QoS(Quality of Service)보장을 위하여 제안된 Diff-Serv(Differentiated Service)모델을 구현하고, QoS 를 보장하지 않는 BE(Best Effort)서비스와 우선 순위가 높은 패킷을 처리하여 QoS 를 보장하는 EF(Expedited Forwarding) 서비스의 차이를 통하여 Diff-Serv 망의 우수성을 입증하고자 한다. Diff-Serv 망은 BB(Bandwidth Broker)와 에지라우터 그리고 다수의 코어라우터로 구성된다. BB 로부터 라우터에 QoS Policy를 전송하기 위하여 COPS(Common Open Policy Service) 프로토콜을 구현하였으며, 사용자와 BB 사이의 SLAT/RAR(Service Level Agreement/Resource Allocation Request)를 처리하기 위하여 Admission Control 이라는 명명한 자체 프로토콜을 개발하였다. 구현된 Diff-Serv 망에서 QoS 보장 테스트를 위하여 19.2Mbps 대역폭이 요구되는 HDTV 스트리밍 서비스를 이용하여 인위적으로 Background Traffic 을 발생시켰을 때, BE 서비스만을 지원하는 망에서는 현저하게 서비스의 질이 떨어지는 반면에 Diff-Serv 망에서는 QoS가 보장됨을 알 수 있었다.

• Journal of Korean Society for Quality Management
• /
• v.25 no.4
• /
• pp.168-184
• /
• 1997

The primary objective of this paper is to develop an interactive computer graphic aided decision su, pp.rt system for the design of inspection plans for complex production systems. This research first develops a computer simulator, called Simulator for Inspection Systems(SIS), in order to represent the production system as a network model. The simulator elicits fundamental information about the system from the decision maker(DM) in an interactive manner. A decision su, pp.rt system is then proposed by combining SIS and Compromise Programming. The system simulates a set of possible inspection strategies implicitly, observes all the important measurements about the inspection system, and employs the compromise programming a, pp.oach to help the DM determine the best compromising allocation of inspection effort considering his/her preferences. Finally, the performance of the proposed system is evaluated using two test cases. The pros and cons of the system are also discussed.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.260-262
• /
• 2000

현재의 인터넷망을 이용하여 음성, 화상 정보를 실시간으로 이용하고자 하는 다양한 응용이 시도되어 왔다. 인터넷망이 최선의 노력(best effort)만을 제공하기 때문에 발생되는 신뢰성과 지연의 문제는 이미 많은 연구가 있어왔고 현재 어느 정도의 서비스 품질을 획득하여 인터넷폰과 같은 서비스가 실제로 이용되고 있다. 그러나 무선 통신의 경우는 이에 더하여 무선 구간에서의 자원 할당의 문제가 남아 있다. 본 연구에서는 코어 망으로 인터넷 프로토콜을 사용하는 차세대 망에서, 무선 이동단말 간의 멀티미디어 서비스가 가능하도록 효율적인 주파수 할당을 지원하는 QoS 관리자를 설계하였다. 제안한 QoS(Quality of Service) 관리자는 요구 대역폭이 다른 멀티미디어 호 요청에 대해 융통성 있는 주파수 할당이 가능하도록 대국의 QoS 관리자와의 협상을 통해 제한된 범위 내에서 서비스 품질을 조절하여 보다 높은 서비스 수준을 유지할 수 있도록 한다.

• Proceedings of the IEEK Conference
• /
• 2003.11c
• /
• pp.121-124
• /
• 2003

Passive optical networks (PONs) will be the pervasive choice in the design of next-generation access networks. One possible solution to implementing Passive optical access network is to rely on wavelength-division multiplexing (WDM). In this paper, we solve the problem of providing real-time service to both hard and soft real-time messages in conjunction with a conventional vest-effort service in WDM. we propose an adaptive scheduling algorithm to schedule and manage the message transmissions in the optical access network. Proposed algorithm is MLF-MQF. Also, we suggest dynamic bandwidth algorithm(DBA) in Loop-back WDM-PON (LPB-PON).our mechanism based on bandwidth reservation protocol.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.66-69
• /
• 2011

Many international organizations build a global communications network called the GMDSS by close cooperation, and ITU-R, IMO and IEC apply it for the modernization of the international marine radiocommunication system, but a modernization study of the GMDSS to reflect such a technique by the rapidly development of the wireless communication technology recently progresses. Such effort was submitted for adoption with WRC-12 held in 2012. This paper analyzed standardization trends for marine radiocommunication modernization discussed around ITU-R recently and analyzed research activities for frequency allocation for new technical introduction and described it.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6A
• /
• pp.910-917
• /
• 2000

Because the random early detection(RED) algorithm deals all flows with the same best-effort traffic characteristic, it can not correctly control the output link bandwidth for the flows with different traffic characteristics. To remedy this problem, several per-flow algorithms have been proposed. In this paper, we propose a new per-flow type Fair Droptail algorithm which can fairly allocate bandwidth among flows over a shared output link. By evenly allocating buffers per flow, the Fair Droptail can restrict a flow not to use more bandwidth than others. In addition, it can be simply implemented even if it employs the per-flow state mechanism, because the Fair Droptail only keeps each information of flow in active state.