Adaptive Resonance Theory (ART) is an unsupervised neural network. Fuzzy ART (FART) a variation of ART, allows both binary and continuous input patterns. However, has the category proliferation problem. In this study, to solve problem, we propose new algorithm: Combining Overlapped Category in consideration connections (C-FART). C-FART two important features. One make between similar categories. The other combine overlapping categories into with one category. We investigate behavior C-FART,...

This paper proposes an application of the particle swarm optimization (PSO) to analysis switched dynamical systems (SDS). is first PSO bifurcation analysis. We consider example SDS which relates a simplified model photovoltaic such that input single solar cell and converted output via boost converter. Our includes piecewise linear current-controlled voltage source switching rule variant peak-current-controlled switching. derive two equations give period-doubling set maximum power point (MPP)...

This paper focuses on an image sensor communication system that uses LED as the transmitter and a high-speed (camera) receiver. Communication in this scheme depends quality of images transmitted from to sensor. If becomes unfocused way receiver, luminance make up signal cannot be detected, so receiver demodulate data. To overcome problem, study proposes novel demodulation recover data degraded image, based maximum likelihood decoding (MLD) algorithm. The proposed method creates template...

This paper proposes a bifurcation point detection strategy based on nested layer particle swarm optimization (NLPSO). The NLPSO is performed by two (PSO) algorithms with nesting structure. proposed method tested in experiments of period doubling points discrete-time dynamical systems. directly detects the parameters regardless stability periodic point, but require no careful initialization, exact calculation or Lyapunov exponents. Moreover, an effective technique terms accuracy, robustness...

This paper proposes a novel algorithm to accurately calculate the coordinates of homoclinic points observed in discrete-time dynamical systems. The proposed method is based on particle swarm optimization method. Compared with current methods, methodology has advantages not requiring careful selection initial conditions and information related derivative objective function. It shown that can successfully obtain system, even if system parameters are close those describe bifurcation sets...

This study proposes a Batch-Learning Self-Organizing Map with Weighted Connections avoiding false-neighbor effects (BL-WCSOM). We apply BL-WCSOM to several high-dimensional datasets. From results measured in terms of the quantization error, inactive neurons, topographic error and computation time, we confirm that obtain effective map reflecting distribution state input data using fewer neurons less time.

This paper explains a bifurcation parameter detection strategy based on particle swarm optimization (PSO), and it shows application examples of local parameters appearing in discrete-time dynamical systems non-autonomous continuous systems. The algorithm design analysis part that the PSO-based is fairly simple, easily understandable, implementable. method requires no careful initialization, exact calculation, gradient information system, or Lyapunov exponents. However, simulation results...

The class-E amplifier is one of the switching amplifiers, which satisfies conditions. It is, however, difficult to determine values passive elements included in circuit for achieving particle swarm optimization algorithm designing presented this paper. To reduce computational cost and consider nonlinear effects MOSFET amplifier, a simulator finds steady-state solution introduced. Moreover, OpenMP, an API multi-platform shared-memory parallel programming, used developed program accelerate...

Nested-layer particle swarm optimization (NLPSO) is a powerful method to detect bifurcation parameters in discrete-time dynamical systems. Although NLPSO requires no carefully set initial system parameters, Lyapunov exponents or derivation of objective functions, the can quickly and accurately parameter. Previous studies have proven effectiveness for systems, but they not demonstrated continuous This study proposes an NLPSO-based non-autonomous continuous-time systems applies Duffing...

This study proposes a network-structured particle swarm optimizer (NS-PSO), which considers neighborhood distances. All particles of the NS-PSO are connected to adjacent in topological space, and utilizes connections between them not only share local best position but also increase diversification. Each is updated depending on positions current particles. In NS-PSO, distance space from each considered. effect promotes diversification solutions avoids becoming trapped at optima. Simulation...

This study proposes a new network-structured particle swarm optimizer considering neighborhood relationships (NS-PSO). All particles of NS-PSO are connected to adjacent by relation the 2-dimensional network. The directly share information their own best position. Each is updated depending on distance network between it and winner, whose function value among all particles. Simulation results show searching efficiency NS-PSO.

We propose a novel color image arrangement method using an elastic transform based on histogram matching some kinds of axes. The axes include the lightness axis and Principal Component (PC) obtained from Analysis (PCA) in RGB three-dimensional vector space that is attribute image. In this paper, we mainly present principle its automated especially Histogram Matching Gaussian Distribution (HMGD). Then, order to detect single-peak histogram, curvature computation for cumulative histogram....

A virtualized-Elastic-regenerator (VER) is a promising solution for efficiently regenerating various bandwidth super-channels in elastic optical networks (EON). It very important EON to solve an optimization on VER placement, and routing spectrum assignment (VER-PRSA). However, VER-PRSA problem hard obtain the optimum since it complicated problem. In order problem, this study proposes application of binary real coded firefly algorithm (BRCFF) placement. Furthermore, novel method, that...

The class-E amplifier is one of the switching amplifiers, which satisfies conditions. It is, however, difficult to determine values passive elements included in circuit for achieving Recently, Newton type algorithm proposed elements. However, this method requires a good initial estimation. In paper, an using Independent-minded Particle Swarm Optimization (IPSO) introduced estimate To find it efficiently, MOSFET replaced with ideal switch and objective function optimization efficiently...

This paper deals with the optimization of economic load dispatch (ELD) problem; this is to find optimal combination generators in order minimize operating costs system.This done by using particle swarm (PSO) algorithm.PSO applied search for schedule all generator units that can supply required demand at minimum fuel cost while satisfying system constraints.The PSO algorithm has been implemented MATLAB toolbox and was solve ELD problem Nigeria thermal power stations.The results were compared...

Bifurcations and chaos in a network of three identical sigmoidal neurons are examined. The consists two-neuron oscillator the Wilson–Cowan type an additional third neuron, which has simpler structure than chaotic neural networks previous studies. A codimension-two fold-pitchfork bifurcation connecting two periodic solutions exists, is accompanied by Neimark–Sacker bifurcation. stable quasiperiodic solution generated Arnold’s tongues emanate from locus two-dimensional parameter space....

This study proposes the Self-Organizing Map with Weighted Connections avoiding false-neighbor effects (WC-SOM). We investigate effectiveness of WC-SOM in comparison conventional SOM, Growing Grid and FN-SOM. confirm that enables most flexible self-organization among four algorithms can obtain effective map reflecting distribution state input data using fewer neurons.

This paper investigates the Neimark-Sacker bifurcation points derivation method using nested-layer particle swarm optimization (NLPSO) in nonlinear dynamical systems. In systems, occurs when a complex conjugate characteristic multiplier crosses unit circle by changing parameters. NLPSO is not only under no careful initial values and hand calculation but also advantage of deriving regardless stability order to obtain parameters NLPSO, objective function must be set number. derives local such...