• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.47-55
• /
• 2019

The army of republic of korea have been continued to transform their logistics support system structure for better efficient logistics support system in preparation for the future environment. Logistics system has supply network structure which is connected by various units and supply network structure received attention as a factor of success of supply network. Many researchers have continuously researched inventory management, transportation or economy factors for supply network, but such a study on the one in military supply network structure analysis is still slower than the study of analysis of other factors until now. In this study, we identify military supply network structure influence factor by application of social network analysis method which is used broadly and analyze co-relationships between supply network structure influence factor and valued APL(average path length) as a criteria of efficiency of military supply network. By this study it has value of military supply network influence factor identification for the better military supply network fabrication.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1565-1568
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with multi-layer neural network. The structure of modular neural network in researched by Jacobs and Jordan is selected in this paper. Modular network consists of several expert networks and a gating network which is composed of single-layer neural network or multi-layer neural network. We propose modular network structure using recurrent neural network, since the state of the whole network at a particular time depends on an aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.47-54
• /
• 2013

In this paper, the structural design of optical Internet is analyzed and by using UNI (User Network Interface) signaling protocol an optical transmission experiment was performed. The hierarchical structure of the basic optical Internet consists of the backbone network, the service network and the access network. The necessary functions for each layer were described as follows: Control structure of the optical transport layer, network operation and management structure, internetworking technology of sub networks, routing and signaling technology. By using UNI signaling protocol from OIF (Optical Internetworking Forum), the optical transmission in the proposed structure of the optical Internet network was experimented. By the traffic generation of LSP (Label Switched Path) data packets along the route-configuration was delivered to UNI. Finally, by showing the value of TCP (Transmission Control Protocol) packets the optical transmission was completely and successfully demonstrated.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.694-697
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with Multi-Layer Neural Network(MLNN). The structure of Modular Neural Network(MNN) in researched by Jacobs and jordan is selected in this paper. Modular network consists of several Expert Networks(EN) and a Gating Network(CN) which is composed of single-layer neural network(SLNN) or multi-layer neural network. We propose modular network structure using Recurrent Neural Network(RNN), since the state of the whole network at a particular time depends on aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2681-2683
• /
• 2005

In this paper, we present the structure of fuzzy neural network(FNN) based on wavelet function, and apply this network structure to the identification of nonlinear systems. For adjusting the shape of membership function and the connection weights, the parameter learning method based on the gradient descent scheme is adopted. And an approach that uses adaptive learning rates is driven via a Lyapunov stability analysis to guarantee the fast convergence. Finally, to verify the efficiency of our network structure. we compare the Identification performance of proposed wavelet based fuzzy neural network(WFNN) with those of the FNN, the wavelet fuzzy model(WFM) and the wavelet neural network(WNN) through the computer simulation.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• Journal of the Korea Society for Simulation
• /
• v.3 no.1
• /
• pp.75-88
• /
• 1994

Discrete event modeling is finding ever more application to anlysis and design of complex manufacturing, communication, computer systems, etc. This paper shows how packet network systems may be advantageously represented as DEVS (Discrete Event System Specification) models by employing System Entity structure / Model base (SES/MB) framework developed by Zeigler. DEVS models and network structure representations support a strong basis for performance analysis of packet network systems. This approach is illustated in a typical packet network example with several routing strategies.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1299-1303
• /
• 2005

Over the last decade the research of end-to-end behavior on computer network has grown by orders but it has few researching in hop-by-hop behavior. We think if we know hop-by-hop behavior it can make better understanding in network behavior. This paper represent ICMP time stamp request and time stamp reply as tool of network study for learning in hop-by-hop behavior to estimate link bandwidth and link structure. We describe our idea, experiment tools, experiment environment, result and analysis, and our discussion in our observative.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.193-194
• /
• 2006

In this paper, the SPINS, a sensor network security mechanism, was researched to design a system to be applied to home network structure and check the security of which degree was ensured by a virtual network of home networking middleware. Sensor Network security mechanism SPINS provides data confidentiality and authentication by SNEP, and provides authenticated broadcast by ${\mu}TESLA$. We designed the system that applied SPINS to home networking middleware basic structure.