• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.739-742
• /
• 1997

This paper proposes the structure and parameter optimization technique of fuzzy neural networks using genetic algorithm. Fuzzy neural network has advantages of both the fuzzy inference system and neural network. The determination of the optimal parameters and structure of the fuzzy neural networks, however, requires special efforts. To solve these problems, we propose a new learning method for optimization of fuzzy neural networks using genetic algorithm. It can optimize the structure and parameters of the entire fuzzy neural network globally. Numerical example is provided to show the advantages of the proposed method.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.294-301
• /
• 2004

This paper presents a combination of optimization concept and congestion control for multicast communications to bring best benefit for the network. For different types of Internet services, there will be different utility functions and so there will be different ways to choose on how to control the congestion, especially for real time multicast traffic. Our proposed algorithm OMCC brings the first implementation experiment of utility-based Multicast Congestion Control. Simulation results show that OMCC brings better network performances in multicast session throughput while it still keeps a certain fairness of unicast and multicast sessions, and thus, provides better benefit for all network participants.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.12
• /
• pp.1184-1190
• /
• 2006

Most chemical companies try to maximize their energy efficiencies due to high oil price and reinforcement of environmental regulation. An individual factory continuously has tried to reduce energy consumption or carbon dioxide discharge for high profit. Nevertheless, it is found that waste heat is disposed with forms of low or medium pressure steams. It can be improved by the aspect of entire industrial complex. Therefore, we have developed a steam network optimization method using Steam Networking Matrices(SNMs) in this research. Results from an illustrative example show that energy consumption can be reduced by optimizing steam exchange networks.

• Journal of Electrical Engineering and Technology
• /
• v.5 no.1
• /
• pp.45-53
• /
• 2010

This paper presents an improved parallel particle swarm optimization approach (IPPSO) based decomposed network for economic power dispatch with discontinuous fuel cost functions. The range of partial power demand corresponding to the partial output powers near the global optimal solution is determined by a flexible decomposed network strategy and then the final optimal solution is obtained by parallel Particle Swarm Optimization. The proposed approach tested on 6 generating units with smooth cost function, and to 26-bus (6 generating units) with consideration of prohibited zone effect, the simulation results compared with recent global optimization methods (Bee-OPF, GA, MTS, SA, PSO). From the different case studies, it is observed that the proposed approach provides qualitative solution with less computational time compared to various methods available in the literature survey.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.381-385
• /
• 2004

In this paper, We consider various service models and mechanisms as a part of study for offering QoS with the requirement of user and discuss genetic algorithm and hybrid genetic algorithm for routing optimization in broa㏈and convergence network. If routing optimization based on OSPF is not sufficient, a number of MPLS paths can be set up to further improve QoS. We propose two mixed-integer programming models for the complementary MPLS problem, and consider the maximum link utilization within the network as the relevant network QoS measure

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.1007-1017
• /
• 1997

The existing survivability measure is defined as the only ratio of survival traffic volume on the given traffic demand. In this paper we suggest a new network survivability evaluation model. Sinceit depends on the importance of traffic, we can evaluatethe affect of telecommunication disaster. With the suggested evaluation model we formulate optimization models for restoration paths and traffic assinment on them. The optimization models are represented as mixed integer programming problems, which are difficult to find exact solutions. We develop heuristic algorithms according to the optimization models and apply them to an example network with 10 nodes and 17 links.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.173-183
• /
• 2021

As low-power wide-area network (LPWAN) end devices (EDs) are deployed in massive scale, their economic and environmental costs of operation are becoming too significant to ignore and too difficult to estimate. While LPWAN architectures and protocols are designed to primarily save energy, this study shows that energy saving does not necessarily lead to lower cost or environmental footprint of the network. Accordingly, a theoretical framework is proposed to estimate the operational expenditure (OpEx) and environmental footprint of LPWAN EDs. An extended constrained optimization model is provided for the ED link assignment to gateways (GWs) based on heterogeneous ED configurations and hardware specifications. Based on the models, a simulation framework is developed which demonstrates that OpEx, energy consumption, and environmental footprint can be in conflict with each other as constrained optimization objectives. We demonstrate different ways to achieve compromises in each dimension for overall improved network performance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.131-138
• /
• 2022

Soft sensors are used to anticipate complicated model parameters using data from classifiers that are comparatively easy to gather. The goal of this study is to use artificial intelligence techniques to design and build soft sensors. The combination of a Long Short-Term Memory (LSTM) network and Grey Wolf Optimization (GWO) is used to create a unique soft sensor. LSTM is developed to tackle linear model with strong nonlinearity and unpredictability of manufacturing applications in the learning approach. GWO is used to accomplish input optimization technique for LSTM in order to reduce the model's inappropriate complication. The newly designed soft sensor originally brought LSTM's superior dynamic modeling with GWO's exact variable selection. The performance of our proposal is demonstrated using simulations on real-world datasets.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.221-230
• /
• 2020

Used optimization techniques as solution for mobile network have been implemented as a reference systems for various applications against fading and signals perturbation, in addition each transition to 5th generation telecommunication standards require a deep studies in order to park an applied instantaneous process. The paper describes a preliminary planning and a careful preparation to update both subscriber radio access network as well as data transmission network this approach conducts to make network resource updates invisible for customers and with minimal costs for mobile operators basically in terms of delay. In addition, network operators transit to mobile networks, multimedia services efficient delivery are considered the challenging application and the most promising for mobile network operators today, this work conduct to optimize video consumption of mobile users which are exponentially increasing. The interference is a complex phenomenon in mobile radio telecommunication system, and a mobile phone can be a source of interference to another one. Actual advances in technology necessitate the need for the complicated software solution that can take several unexpected phenomena in consideration to rise to a level higher than ever. The capability needs today require the use of Drive test which is used to take the performance of network in the field by using a special software called TEMS investigation, it have been implemented as standalone systems for various applications. The paper focuses on considering as the best technical for optimization of mobile networks, analysis and processing of signal, a Drive Test is the method used to take the performance of network in the field by using a special software called TEMS investigation. Most used in the world, this software is reputed to detect and analyze many problems of mobile network between the mobile phone and the transmitter: BTS in case of GSM and Node B for UMTS. An example of that is interference in radio communication. It exists permanently and it degrades considerably the quality of received signal when it exceeds certain levels.