• Journal of Korean Society of Transportation
• /
• v.17 no.2
• /
• pp.127-135
• /
• 1999

Most existing progression bandwidth models maximize the single or multi weighted sum of bandwidths in the both directions to improve traffic mobility on an arterial, but they cannot be applied to general networks. Even though a few models formulating a looped network problem cannot be applied to networks have not loops. Also they have some defects in optimizing phase sequences. Therefore, the objective of this study is to develope a mathematical formulation of the synchronization problem for a general traffic network. The goal is achieved successfully by introducing the signal phasing for each movement and expanding the mixed integer linear programming of MAXBAND. The experiments indicate that the proposed model can formulate the general traffic network problem mere efficiently than any other model. In conclusion, this model may optimize signal time to smooth progression in the general networks.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.30-33
• /
• 2001

The number of hidden neurons of the feed-forward neural networks is generally decided on the basis of experience. The method usually results in the lack or redundancy of hidden neurons, and causes the shortage of capacity for storing information of learning overmuch. This research proposes a new method for optimizing the number of hidden neurons bases on information entropy, Firstly, an initial neural network with enough hidden neurons should be trained by a set of training samples. Second, the activation values of hidden neurons should be calculated by inputting the training samples that can be identified correctly by the trained neural network. Third, all kinds of partitions should be tried and its information gain should be calculated, and then a decision-tree correctly dividing the whole sample space can be constructed. Finally, the important and related hidden neurons that are included in the tree can be found by searching the whole tree, and other redundant hidden neurons can be deleted. Thus, the number of hidden neurons can be decided. In the case of building a neural network with the best number of hidden units for tea quality evaluation, the proposed method is applied. And the result shows that the method is effective

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1230-1237
• /
• 2009

In this paper, we develop a design methodology of Granular-based Radial Basis Function Neural Networks(GRBFNN) by context-based clustering. In contrast with the plethora of existing approaches, here we promote a development strategy in which a topology of the network is predominantly based upon a collection of information granules formed on a basis of available experimental data. The output space is granulated making use of the K-Means clustering while the input space is clustered with the aid of a so-called context-based fuzzy clustering. The number of information granules produced for each context is adjusted so that we satisfy a certain reconstructability criterion that helps us minimize an error between the original data and the ones resulting from their reconstruction involving prototypes of the clusters and the corresponding membership values. In contrast to "standard" Radial Basis Function neural networks, the output neuron of the network exhibits a certain functional nature as its connections are realized as local linear whose location is determined by the values of the context and the prototypes in the input space. The other parameters of these local functions are subject to further parametric optimization. Numeric examples involve some low dimensional synthetic data and selected data coming from the Machine Learning repository.

• Journal of Electrical Engineering and Technology
• /
• v.4 no.4
• /
• pp.457-466
• /
• 2009

This paper presents efficient parallel genetic algorithm (EPGA) based decomposed network for optimal power flow with various kinds of objective functions such as those including prohibited zones, multiple fuels, and multiple areas. Two coordinated sub problems are proposed: the first sub problem is an active power dispatch (APD) based parallel GA; a global database generated containing the best partitioned network: the second subproblem is an optimal setting of control variables such as generators voltages, tap position of tap changing transformers, and the dynamic reactive power of SVC Controllers installed at a critical buses. The proposed approach tested on IEEE 6-bus, IEEE 30-bus and to 15 generating units and compared with global optimization methods (GA, DE, FGA, PSO, MDE, ICA-PSO). The results show that the proposed approach can converge to the near solution and obtain a competitive solution with a reasonable time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2441-2446
• /
• 2009

Wireless Sensor Network collects a data from the specific area and the control is composed of small sensor nodes. Like this sensors to after that is established at the beginning are operated with the battery, the operational duration until several years must be continued from several months and will be able to apply the resources which is restricted in efficiently there must be. In this paper RHC (rounting history cache) applies in Directed Diffusion which apply a data central concept a reliability and an efficiency in data transfer course set. RHC algorithms which proposes each sensor node updated RHC of oneself with periodic and because storing the optimization course the course and, every event occurrence hour they reset the energy is wasted the fact that a reliability with minimization of duplication message improved.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.57-71
• /
• 2009

Networking together hundreds or thousands of cheap sensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. As sensor nodes are typically battery operated, it is important to efficiently use the limited energy of the nodes to extend the lifetime of the wireless sensor network (WSN). One of the fundamental issues in WSNs is the coverage problem. In this paper, the border coverage problem in WSNs is rigorously analyzed. Most existing results related to the coverage problem in wireless sensor networks focused on planar networks; however, three dimensional (3D) modeling of the sensor network would reflect more accurately real-life situations. Unlike previous works in this area, we provide distributed algorithms that allow the selection and activation of an optimal border cover for both 2D and 3D regions of interest. We also provide self-healing algorithms as an optimization to our border coverage algorithms which allow the sensor network to adaptively reconfigure and repair itself in order to improve its own performance. Border coverage is crucial for optimizing sensor placement for intrusion detection and a number of other practical applications.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• Annual Conference of KIPS
• /
• 2003.05b
• /
• pp.1117-1120
• /
• 2003

DWDM(DensedWavelengthDivisionMultiplexing)은 광 파이버를 이용하여 기존의 통신보다 높은 대역폭(B/W)을 얻기 위한 기술로 여러 신호를 각각 다른 파장으로 변조해 하나의 Fiber 를 통해 전송하는 방식이며, 기본적으로 EDFA(Erbium Doped Fiber Amplifier), AWG(Arrayed Wave guide Grating), OADM(Optical Add/Drop Multiplexer) 등의 주요 부품과 여러 광 관련 부품들로 구성돼 있으며, 다수의 파장을 MUX(AWG)에서 다중화하고, 장거리 전송을 위해 OA(EDFA)에서 광신호를 증폭하게 된다 그리고 일부 특정 파장만 Add/Drop하기 위해 OADM이 놓이게 되며, 또한 선로(광섬유)의 손실을 보상하기 위해 필요한 구간에 리피터(EDFA)를 두어 광신호를 증폭 송신하며 수신단에서는 들어오는 여러 파장을 OA(EDFA)를 통해 증폭한 후 DEMUX(AWG)에서 역 다중화해 수신하게 된다. 이와 같은 DWDM방식을 이용한 Network는 Star, Mesh, Ring 등의 다양한 형태로 구성될 수 있으며, 초기에는 Point-to-Point 방식의 장거리 전송에 주로 사용돼 왔으나 Metro 구간의 Traffic 이 급격히 증가하면서 Metro- DWDM Network 이 부각되고 있어 본 논문에서는 현재 SK Telecom에서 상용화되고 있는 1,600G DWDM과 Metro-DWDM간의 망 구축의 최적화 방안을 연구해 본다.

• Proceedings of the KOR-KST Conference
• /
• 1995.05a
• /
• pp.51-59
• /
• 1995

It is an objective of Shanghai urban development to quickly build Shanghai into one of the international centres of economy, finance and trade. To fulfil the objective, a rational urban general layout and a satisfactory traffic network are needed. As a metropolis with complete urban functions and specified geographical position, Shanghai must develop a perfect citytown system that best suits its composite urban distribution. In planning the central city, the principle of "open and multi-centred" and "optimization of land use" should be taken into consideration. To build a satisfactory urban traffic network, emphasis should be laid upon the construction of deefwater wharf, air-field and inforation centre. In addition, determination should be made to build a high-speed traffic means including high speed railroad and express highway so that a public traffic network is realised on and above ground, and underground. A solution of traffic preblem in Shanghai lies in good understanding of traffic policy and strenthening of strategic management combined with a rational layout of traffic circulation.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.227-236
• /
• 2005

Hierarchical Prefix Delegation (HPD) protocol refers to a type of solution to problems inherent in non-optimal routing which occurs with Network Mobility (NEMO) basic solution. However, because HPD cannot improve the micro-mobility Problems, Problem surfaces each time Mobile Network Node (MNN) changes the attachment point; as happens also in a Mobile IPv6 (MIPv6) protocol in sen야ng Binding Update (BU) messages to Home Agent (HA) / Correspondent Nodes(CNs) By applying Hierarchical Mobile IPv6 protocol concept to HPD, this study Proposes an algorithm for effectively handling micro-mobility problems which occur with HPD in a nested NEMO environment. By sending BU only to nearby Mobility Anchor Point(MAP) during MNN location change within a MAP's domain, the proposed protocol will alleviate service disruption delays and signaling loads during the handover process, overcoming the limitations of HPD.