• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11S
• /
• pp.3190-3198
• /
• 1999

Because of the rapid growth of the mobile communication, the need for the mobile internet access has grown up as well. since the current mobile communication network, however, is optimized for a voice communication system, which exclusively occupies a channel for a given time, it is not suitable for variable rate packet data. In order to support the mobile internet access, it is essential do design a reasonable packet switching network which supports the mobility. Since mobile packet network has longer latency, high speed switching and QoS are required to meet the user's requirements. In this paper, we suggest an resonable way to construct a network and its operation procedures utilizing GPRS(General Packet Radio Service) network and MPLS(Multi Protocol Label Switching) to provide a high speed switching and QoS mobile internet access. GPRS is used as a network which supports the mobility and MPLS guarantees the QoS and high speed IP protocol transmission based on the ATM switching technology.

• Journal of KIISE:Information Networking
• /
• v.37 no.3
• /
• pp.198-203
• /
• 2010

In this paper, a new routing protocol is proposed to manage selfish nodes which make a strategic choice to maximize only their own profits. To provide incentives to nodes on the path, VCG mechanism is introduced. Therefore, based on the collaborative actions among nodes, the entire network performance can be improved. With a simulation study, the proposed scheme can approximate an optimized solution while ensuring a well-balanced network performance under widely diverse network environments.

• Proceedings of the KWS Conference
• /
• 2000.04a
• /
• pp.251-255
• /
• 2000

Recently, the improvement of computer capacities and artificial intelligence ware caused to employ for prediction of residual stresses and strength evaluation. There are a lot of researches regarding the measurement and prediction of residual stresses for weldment using a neural network in the advanced countries, but in our country, a neural network as a technical part, has only been used on the possibilities of employment for welding area. Furthermore, the relationship between residual stress and process parameters using a neural network was wholly lacking. Therefore development of a new technical method for the optimized process parameters on the reduction of residual stress and applyment of real-time production line should be developed. The objectives of this paper is to measure the residual stress of butt welded specimen using strain gage sectioning method and to apply them to a neural network for prediction of residual stresses on a given process parameter. Also, the assessment of the developed system using a neural network was carried out

• Journal of Fisheries and Marine Sciences Education
• /
• v.26 no.4
• /
• pp.760-768
• /
• 2014

Yet logistics base in China has a refrigerated storage facilities installed areas, the number of those is very limited and is generally insufficient. According to these especial points, a new construction cold chain logistics network design strategy is required from how to use the existing refrigerated warehouses to new issue. For example, however refrigerated storage facility is supplied, can it satisfy all demand of this area? Then does it have optimized location of this area? If future demand expansion, adding that already other refrigerated storage facilities matter? Or, add another refrigerated facilities, optimum cold chain established a network matter? So on. Above problems can be occurred. In order to solve facing many of these issues of distribution network, northeast area in China has been selected as a subject, and we designed a new cold chain distribution network.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2490-2492
• /
• 2002

Design of controller of nonlinear systems is an important part of control research. In this paper, a controller for nonlinear plants using a neural network is presented. The controller is a combination of an approximate PID controller and a neural network controller. The PID controller be used for stabilizing the process and for compensating for possible disturbances, a neural network act as feedforward controller. In this method, a RBF neural network is trained and the system has a stable performance for the inputs it has been trained for. Simulation results show that it is very effective and can realize a satisfactory control of the nonlinear system and meets the demands of the system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.374-386
• /
• 2022

Nowadays, research in deep learning leveraged automated computing and networking paradigm evidenced rapid contributions in terms of Software Defined Networking (SDN) and its diverse security applications while handling cybercrimes. SDN plays a vital role in sniffing information related to network usage in large-scale data centers that simultaneously support an improved algorithm design for automated detection of network intrusions. Despite its security protocols, SDN is considered contradictory towards DDoS attacks (Distributed Denial of Service). Several research studies developed machine learning-based network intrusion detection systems addressing detection and mitigation of DDoS attacks in SDN-based networks due to dynamic changes in various features and behavioral patterns. Addressing this problem, this research study focuses on effectively designing a multistage hybrid and intelligent deep learning classifier based on modified deep forest classification to detect DDoS attacks in SDN networks. Experimental results depict that the performance accuracy of the proposed classifier is improved when evaluated with standard parameters.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.131-138
• /
• 2022

A Mobile Ad-hoc Network (MANET) is a collection of moving nodes that communicate and collaborate without relying on a pre-existing infrastructure. In this type of network, nodes can freely move in any direction. Routing in this sort of network has always been problematic because of the mobility of nodes. Most existing protocols use simple routing algorithms and criteria, while another important criterion is path selection. The existing protocols should be optimized to resolve these deficiencies. 'Particle Swarm Optimization (PSO)' is an influenced method as it resembles the social behavior of a flock of birds. Genetic algorithms (GA) are search algorithms that use natural selection and genetic principles. This paper applies these optimization models to the OLSR routing protocol and compares their performances across different metrics and varying node sizes. The experimental analysis shows that the Genetic Algorithm is better compared to PSO. The comparison was carried out with the help of the simulation tool NS2, NAM (Network Animator), and xgraph, which was used to create the graphs from the trace files.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.42-47
• /
• 2022

As smart factory is the factory which produces the products according to the customer's diverse demand and the changing conditions in it, it can be characterized by flexible production, dynamic reconstruction, and optimized production environment. To implement these characteristics, many kind of configuration elements in the smart factory should be connected to and communicated with each other. So the network is responsible for playing this role in the smart factory. As SDN (Software Defined Network) is the technology that can dynamically cope with the explosive increasing data amount and the hourly changing network condition, it is one of network technologies that can be applied to the smart factory. In this paper, we address SDN function and operation, SDN model suitable for the smart factory, and then performs the simulation for measuring this model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3474-3497
• /
• 2016

Network Function Virtualization (NFV) and Software Defined Networking (SDN) are recently considered as very promising drivers of the evolution of existing middlebox services, which play intrinsic and fundamental roles in today's networks. To address the virtual service deployment issues that caused by introducing NFV or SDN to networks, this paper proposes an optimal solution by combining quantum genetic algorithm with cooperative game theory. Specifically, we first state the concrete content of the service deployment problem and describe the system framework based on the architecture of SDN. Second, for the service location placement sub-problem, an integer linear programming model is built, which aims at minimizing the network transport delay by selecting suitable service locations, and then a heuristic solution is designed based on the improved quantum genetic algorithm. Third, for the service amount placement sub-problem, we apply the rigorous cooperative game-theoretic approach to build the mathematical model, and implement a distributed algorithm corresponding to Nash bargaining solution. Finally, experimental results show that our proposed method can calculate automatically the optimized placement locations, which reduces 30% of the average traffic delay compared to that of the random placement scheme. Meanwhile, the service amount placement approach can achieve the performance that the average metric values of satisfaction degree and fairness index reach above 90%. And evaluation results demonstrate that our proposed mechanism has a comprehensive advantage for network application.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.