• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.1-7
• /
• 2022

This paper aims to compare the mean object size of M/G/1/PS model with that of M/BP/1 model used in the web service. The mean object size is one of important measure to control and manage web service economically. M/G/1/PS model utilizes the processor sharing in which CPU rotates in round-robin order giving time quantum to multiple tasks. M/BP/1 model uses the Bounded Pareto distribution to describe the web service according to file size. We may infer that the mean waiting latencies of M/G/1/PS and M/BP/1 model are equal to the mean waiting latency of the deterministic model using the round robin scheduling with the time quantum. Based on the inference, we can find the mean object size of M/G/1/PS model and M/BP/1 model, respectively. Numerical experiments show that when the system load is smaller than the medium, the mean object sizes of the M/G/1/PS model and the M/BP/1 model become the same. In particular, when the shaping parameter is 1.5 and the lower and upper bound of the file size is small in the M/BP/1 model, the mean object sizes of M/G/1/PS model and M/BP/1 model are the same. These results confirm that it is beneficial to use a small file size in a web service.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.247-256
• /
• 2000

오늘날의 기업은 상품을 판매하는 것 뿐만 아니라 기업의 신용과 이미지를 위해 그 상품에 대한 사후처리(After Service) 업무에 많은 투자를 하고 있다. 이러한 양질의 사후서비스를 고객에게 공급하기 위해서는 많은 인력을 합리적으로 관리해야 하고 요청되는 고장수리 서비스 업무를 빠르게 해결하기 위해서는 업무를 인력들에게 합리적으로 배정을 하고 회사의 비용을 최소화하면서 정해진 시간에 요청된 작업을 처리하기 위해서는 인력들에게 작업을 배정하고 스케줄링하는 문제가 발생된다. 본 논문에서는 이러한 문제를 해결하기 위해 화학계기의 A/S 작업을 인력에게 합리적으로 배정하는 스케줄링 시스템에 관한 연구이다. 먼저 스케줄링 모델을 HP 사의 화학분석 및 시스템을 판매, 유지보수 해 주는 "영진과학(주)"회사의 작업 스케줄을 분석하여 필요한 도메인과 고객서비스전략과 인력관리전략에서 제약조건을 추출하였고 여기에 스케줄링 문제를 해결하기 위한 방법으로 제약만족문제(CSP) 해결기법인 도메인 여과기법을 적용하였다. 도메인 여과기법은 제약조건에 의해 변수가 갖는 도메인의 불필요한 부분을 여과하는 것으로 제약조건과 관련되어 있는 변수의 도메인이 축소되는 것이다. 또한, 스케줄링을 하는데에 있어서 비용적인 측면에서의 스케줄링방법과 고객 만족도에서의 스케줄링 방법을 비교하여 가장 이상적인 해를 찾는데 트래이드오프(Trade-off)를 이용하여 최적의 해를 구했으며 실험을 통해 인력에게 더욱 효율적으로 작업들을 배정 할 수 있었고 또한, 정해진 시간에 많은 작업을 처리 할 수 있었으며 작업을 처리하는데 있어 소요되는 비용을 감소하는 결과를 얻을 수 있었다. 검증하였다.를, 지지도(support), 신뢰도(confidence), 리프트(lift), 컨빅션(conviction)등의 관계를 통해 다양한 방법으로 모색해본다. 이 연구에서 제안하는 이러한 개념계층상의 흥미로운 부분의 탐색은, 전자 상거래에서의 CRM(Customer Relationship Management)나 틈새시장(niche market) 마케팅 등에 적용가능하리라 여겨진다.선의 효과가 나타났다. 표본기업들을 훈련과 시험용으로 구분하여 분석한 결과는 전체적으로 재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity

• Journal of KIISE:Information Networking
• /
• v.31 no.1
• /
• pp.70-80
• /
• 2004

In order to reduce the increasing packet loss rates caused by an exponential increase in network traffic, the IETF(Internet Engineering Task Force) is considering the deployment of active queue management techniques such as RED(Random Early Detection). But, RED configuration has been a problem since its first proposal. This problem is that proposed configuration is only good for the particular traffic conditions studied, but may have detrimental effects if used in other conditions. While active queue management in routers and gateways can potentially reduce packet loss rates in the Internet, this paper has demonstrated the inherent weakness of current techniques and shows that they are unstable for tile various traffic conditions. The inherent problem with these queue management algorithms is that they all use static parameter setting. In this paper, in order to solve this problem, a new active queue management algorithm called SQM(Stabilized Queue Management) is proposed. This paper shows that it is easy to parameterize SQM algorithm to perform well under different congestion scenarios. This algorithm can effectively reduce packet loss while maintaining high link utilizations and is good for the various traffic conditions.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.25 no.4
• /
• pp.355-362
• /
• 2012

Remaining useful life(RUL) prediction of a system is important in the prognostics field since it is directly linked with safety and maintenance scheduling. In the physics-based prognostics, accurately estimated model parameters can predict the remaining useful life exactly. It, however, is not a simple task to estimate the model parameters because most real system have multivariate model parameters, also they are correlated each other. This paper presents representative methods to estimate model parameters in the physics-based prognostics and discusses the difference between three methods; the particle filter method(PF), the overall Bayesian method(OBM), and the sequential Bayesian method(SBM). The three methods are based on the same theoretical background, the Bayesian estimation technique, but the methods are distinguished from each other in the sampling methods or uncertainty analysis process. Therefore, a simple physical model as an easy task and the Paris model for crack growth problem are used to discuss the difference between the three methods, and the performance of each method evaluated by using established prognostics metrics is compared.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1021-1028
• /
• 2005

The general solution for classification and regression problems can be found by matching and modifying matrices with the information in real world and then these matrices are teaming in neural networks. This paper treats primary space as a real world, and dual space that Primary space matches matrices using kernel. In practical study, there are two kinds of problems, complete system which can get an answer using inverse matrix and ill-posed system or singular system which cannot get an answer directly from inverse of the given matrix. Further more the problems are often given by the latter condition; therefore, it is necessary to find regularization parameter to change ill-posed or singular problems into complete system. This paper compares each performance under both classification and regression problems among GCV, L-Curve, which are well known for getting regularization parameter, and kernel methods. Both GCV and L-Curve have excellent performance to get regularization parameters, and the performances are similar although they show little bit different results from the different condition of problems. However, these methods are two-step solution because both have to calculate the regularization parameters to solve given problems, and then those problems can be applied to other solving methods. Compared with UV and L-Curve, kernel methods are one-step solution which is simultaneously teaming a regularization parameter within the teaming process of pattern weights. This paper also suggests dynamic momentum which is leaning under the limited proportional condition between learning epoch and the performance of given problems to increase performance and precision for regularization. Finally, this paper shows the results that suggested solution can get better or equivalent results compared with GCV and L-Curve through the experiments using Iris data which are used to consider standard data in classification, Gaussian data which are typical data for singular system, and Shaw data which is an one-dimension image restoration problems.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.86-94
• /
• 2012

In this paper we propose a hardware architecture of high-speed CGH (computer generated hologram) generation processor, which particularly reduces the number of memory access times to avoid the bottle-neck in the memory access operation. For this, we use three main schemes. The first is pixel-by-pixel calculation rather than light source-by-source calculation. The second is parallel calculation scheme extracted by modifying the previous recursive calculation scheme. The last one is a fully pipelined calculation scheme and exactly structured timing scheduling by adjusting the hardware. The proposed hardware is structured to calculate a row of a CGH in parallel and each hologram pixel in a row is calculated independently. It consists of input interface, initial parameter calculator, hologram pixel calculators, line buffer, and memory controller. The implemented hardware to calculate a row of a $1,920{\times}1,080$ CGH in parallel uses 168,960 LUTs, 153,944 registers, and 19,212 DSP blocks in an Altera FPGA environment. It can stably operate at 198MHz. Because of the three schemes, the time to access the external memory is reduced to about 1/20,000 of the previous ones at the same calculation speed.

• Journal of IKEEE
• /
• v.5 no.1 s.8
• /
• pp.100-110
• /
• 2001

In this paper, we investigated several buffer management schemes for the design of shared-memory type ATM switches, which can enhance the utilization of switch resources and can support quality-of-service (QoS) functionalities. Our results show that dynamic threshold (DT) scheme demonstrate a moderate degree of robustness close to pushout(PO) scheme, which is known to be impractical in the perspective of hardware implementation, under various traffic conditions such as traffic loads, burstyness of incoming traffic, and load non-uniformity across output ports. Next, we considered buffer management strategies to support QoS functions, which utilize parameter values obtained via connection admission control (CAC) procedures to set tile threshold values. Through simulations, we showed that the buffer management schemes adopted behave well in the sense that they can protect regulated traffic from unregulated cell traffic in allocating buffer space. In particular, it was observed that dynamic partitioning is superior in terms of QoS support than virtual partitioning.