• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.1
• /
• pp.43-48
• /
• 2002

This paper discusses the application of fuzzy-ARTMAP neural network to compensate the nonlinearity of satellite communication channel. The fuzzy-ARTMAP is the class of ART(adaptive resonance theory) architectures designed fur supervised loaming. It has capabilities not fecund in other neural network approaches, that includes a small number of parameters, no requirements fur the choice of initial weights, automatic increase of hidden units, and capability of adding new data without retraining previously trained data. By a match tracking process with vigilance parameter, fuzzy-ARTMAP neural network achieves a minimax teaming rule that minimizes predictive error and maximizes generalization. Thus, the system automatically leans a minimal number of recognition categories, or hidden units, to meet accuracy criteria. As a input-converting process for implementing fuzzy-ARTMAP equalizer, the sigmoid function is chosen to convert actual channel output to the proper input values of fuzzy-ARTMAP. Simulation studies are performed over satellite nonlinear channels. QPSK signals with Gaussian noise are generated at random from Volterra model. The performance of proposed fuzzy-ARTMAP equalizer is compared with MLP equalizer.

• Structural Engineering and Mechanics
• /
• v.67 no.3
• /
• pp.277-281
• /
• 2018

The analytical solution of two functionally graded layers with Volterra type screw dislocation is investigated under anti-plane shear impact loading. The energy dissipation of FGM layers is modeled by viscous damping and the properties of the materials are assumed to change exponentially along the thickness of the layers. In this study, the rate of gradual change ofshear moduli, mass density and damping constant are assumed to be same. At first, the stress fields in the interface of the FGM layers are derived by using a single dislocation. Then, by determining a distributed dislocation density on the crack surface and by using the Fourier and Laplace integral transforms, the problem are reduce to a system ofsingular integral equations with simple Cauchy kernel. The dynamic stress intensity factors are determined by numerical Laplace inversion and the distributed dislocation technique. Finally, various examples are provided to investigate the effects of the geometrical parameters, material properties, viscous damping and cracks configuration on the dynamic fracture behavior of the interacting cracks.

• Korean Journal of Ecology and Environment
• /
• v.37 no.3 s.108
• /
• pp.304-312
• /
• 2004

The transient dynamics of three-trophic populations (prey, predator, and super predator) using ratio-dependent models responding to environmental impacts is analyzed. Environmental factors were divided into two parts: periodic factor (e.g., temperature) and general noise. Periodic factor was addressed as a frequency and bias, while general noise was expressed as a Gaussian distribution. Temperature bias ${\varepsilon}$, temperature frequency ${\Omega}$, and Gaussian noise amplitude ${\`{O}}$ accordingly revealed diverse status of population dynamics in three-trophic food chain, including extinction of species. The model showed stable limit cycles and strange attractors in the long-time behavior depending upon various values of the parameters. The dynamic behavior of the system appeared to be sensitive to changes in environmental input. The parameters of environmental input play an important role in determining extinction time of super predator and predator populations.