• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1561-1564
• /
• 1997

In the study, simulation result was studied by connecting PID controller in series to the established Neural Networks Controller. Neural Network model is composed of two layers to evaluate tracking performance improvement. The reqular dynamic characteristics was also studied for the expected error to be minimized by using Widrow-Hoff delta rule. As a result of the study, We identified that tracking performance inprovement was developed more in case of connecting PID than Neural Network Contoller and that tracking plant parameter in 251 sample was approached rapidly case of time variable.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.91-94
• /
• 1998

ATM technology is reaching a certain level of maturity that allow for its deployment in local as well as in wide area networks. Concurrently, audiovisual applications are foreseen as one of the major users of such broadband networks. We present in this paper requriement of real-time multimedia service on B-ISDN networks and simulating the transport of MPEG-2 encoded multimedia data over ATM networks using CBR, VBR, ABR of ATM Traffic Service. We compare each delay time considering network performance and propose need for real-time multimedia service.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.816-819
• /
• 1996

This paper focuses on development of simulation model for SAE J1850 and performance evaluation of a J1850 network. The simulation model has been developed by using discrete event simulation language. SAE J1850 is one of Class B network protocol for general data sharing applications. Through numerous simulation experiments, several important performance factors such as the probability of a successful transmission, average queue delay, and throughput have been evaluated.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.471-476
• /
• 1995

This paper focues on development and implementation of a perfomance management algorithm for IEEE802.4 token bus networks to serve large-scale integrated manufacturing systems. Such factory automation networks have to satisfy delay constraints imposed on time-critical messages while maintaining as much network capacity as possible for non-time-critical messages. This paper presents the structure of a network performance manager that possesses the knowledge about perfomance management in a set of fuzzy rules and deriving its action through fuzzy inference mechanism. The efficacy of the performance management has been demonstrated by a series of simulation experiments.

• Proceedings of the IEEK Conference
• /
• 2002.06a
• /
• pp.105-108
• /
• 2002

This paper analytical models of a centralized approach based on SNMP Protocol, distributed approach based on mobile agent, and mixed model which is tile existing mobile agent model in order to overcome large communication numbers of SNMP and accumulated data of mobile agent. And then, we compare and analyze these analytical models. Performance evaluation results show that performance of mobile agent and the mixed model is less sensitive to the network traffic and more profitable for complex network environment than that of SNMP.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.1
• /
• pp.49-54
• /
• 2019

Since the underwater communication environment, which is used mainly in acoustic channel, is different from terestrial communication, it needs to analyze the appropriate transmission performance in underwater environment to implement the communication services. Appropriate traffic process method for a communication service is required through transmission performance of object traffic for the communication service. In this paper, transmission performance of video traffic on underwater MANET(Mobile Ad-hoc Network) is analyzed and video traffic configuration scheme on underwater MANET with results of performance analysis is suggested, This study is done with computer simulation based on NS(Network Simulator)-3. throughput, transmission delay, packet loss rate is used for transmission performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.186-189
• /
• 1996

In most of the recent research literature, network performance is expressed in terms of network engineering measures such as delay or loss. These performance measures are important to network owners and operators, but it is believed that user preferences should be the primary consideration which drives the resource allocation scheme. A network is only as valuable as its users perceive it to be. Therefore, it is advocated that the users themselves determine relative traffic priorities. This paper describes the role of feedback in network resource allocation, which could be part of a user-oriented framework for network operation and control. Feedback mechanism can also be used to improve the two types of efficiency in the network; network efficiency and economic efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.6B
• /
• pp.523-532
• /
• 2003

GENMET(GEneralized Multihop Network) which is based on Wavelength-Division Multiplexsing(WDM) and can be used in order to construct the next generation lightwave network is a logical(virtual), packet-switched and multihop topology network. GENMET is a regular multihop network which is a generalization of Shuffle network and do Bruijn network As such, it has the advantage of simple routing which is critical in a high speed network Given a physical topology, different logical topologies can be derived for assigning wavelengths to the UserNodes. By appropriately assigning wavelengths, performance of the network, such as mean hop count, maximum throughput and mean packet delay can be improved. In this paper, we propose heuristic algorithms for effectively assigning a limited number of wavelengths to the given UserNodes. The Performance of proposed algorithm is compared with the random assignment and the lower bounds.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.461-472
• /
• 2024

We propose a network traffic prediction model based on linear and nonlinear model combination. Network traffic is modeled by an autoregressive moving average model, and the error between the measured and predicted network traffic values is obtained. Then, an echo state network is used to fit the prediction error with nonlinear components. In addition, an improved slime mold algorithm is proposed for reservoir parameter optimization of the echo state network, further improving the regression performance. The predictions of the linear (autoregressive moving average) and nonlinear (echo state network) models are added to obtain the final prediction. Compared with other prediction models, test results on two network traffic datasets from mobile and fixed networks show that the proposed prediction model has a smaller error and difference measures. In addition, the coefficient of determination and index of agreement is close to 1, indicating a better data fitting performance. Although the proposed prediction model has a slight increase in time complexity for training and prediction compared with some models, it shows practical applicability.