Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Exploration of Neural Networks in the Design of Microwave Structures
Z. Raida
Radioengineering , 1999,
Abstract: Artificial neural networks can be used for modeling microwave structures in order to obtain computationally efficient models of investigated systems. In conjunction with proper optimization techniques, these neural models can be explored for an efficient full-wave design of microwave structures. Moreover, neural networks can serve as a direct design tool of microwave systems. In this paper, an overview of the so-far published applications of neural networks in microwaves is presented and their exploration in the full-wave design is discussed. Described neural modeling and design is illustrated by modeling and design of frequency-selective surfaces.
Automated Modeling of Microwave Structures by Enhanced Neural Networks
P. Smid,Z. Raida
Radioengineering , 2006,
Abstract: The paper describes the methodology of the automated creation of neural models of microwave structures. During the creation process, artificial neural networks are trained using the combination of the particle swarm optimization and the quasi-Newton method to avoid critical training problems of the conventional neural nets. In the paper, neural networks are used to approximate the behavior of a planar microwave filter (moment method, Zeland IE3D). In order to evaluate the efficiency of neural modeling, global optimizations are performed using numerical models and neural ones. Both approaches are compared from the viewpoint of CPU-time demands and the accuracy. Considering conclusions, methodological recommendations for including neural networks to the microwave design are formulated.
Modeling Broadband Microwave Structures by Artificial Neural Networks
Z. Raida,Z. Lukes,V. Otevrel
Radioengineering , 2004,
Abstract: The paper describes the exploitation of feed-forward neural networksand recurrent neural networks for replacing full-wave numerical modelsof microwave structures in complex microwave design tools. Building aneural model, attention is turned to the modeling accuracy and to theefficiency of building a model. Dealing with the accuracy, we describea method of increasing it by successive completing a training set.Neural models are mutually compared in order to highlight theiradvantages and disadvantages. As a reference model for comparisons,approximations based on standard cubic splines are used. Neural modelsare used to replace both the time-domain numeric models and thefrequency-domain ones.
Hardware Neural Networks Modeling for Computing Different Performance Parameters of Rectangular, Circular, and Triangular Microstrip Antennas  [PDF]
Taimoor Khan,Asok De
Chinese Journal of Engineering , 2014, DOI: 10.1155/2014/924927
Abstract: In the last one decade, neural networks-based modeling has been used for computing different performance parameters of microstrip antennas because of learning and generalization features. Most of the created neural models are based on software simulation. As the neural networks show massive parallelism inherently, a parallel hardware needs to be created for creating faster computing machine by taking the advantages of the parallelism of the neural networks. This paper demonstrates a generalized neural networks model created on field programmable gate array- (FPGA-) based reconfigurable hardware platform for computing different performance parameters of microstrip antennas. Thus, the proposed approach provides a platform for developing low-cost neural network-based FPGA simulators for microwave applications. Also, the results obtained by this approach are in very good agreement with the measured results available in the literature. 1. Introduction Low profile, conformable to planar and nonplanar surfaces, most economical, mechanically robust, light weight, and easily mount-ability are the key advantages of microstrip antennas (MSAs). Because of these add-on advantages, the microstrip antennas are widely used in many communication applications. Since the microstrip antenna operates only in the vicinity of the resonant frequency, it needs to be calculated accurately for analyzing the microstrip antennas. Similarly, for designing the microstrip antennas, the physical dimension(s) must also be calculated precisely [1]. There are two conventional ways for analyzing and/or designing the microstrip antennas, analytical methods and numerical methods. The analytical methods provide a good spontaneous explanation for the operation of microstrip antennas. As the analytical methods are based on the physical assumptions for simplifying the radiation mechanism of the microstrip antennas, these methods are not suitable for many structures, where the thickness of the substrate is not very thin. The numerical methods also provide the accurate results but the analysis using these methods leads to the expressions as an integral equation. The choice of test functions and path integrations appears to be more critical without any initial assumption in the final stage of the numerical results. Also, these methods require a new solution for any sort of alteration in the geometry. The problems associated with these conventional methods can be overcome by selecting the appropriate neural network methods [1]. In recent years, artificial neural networks (ANNs) have acquired
Neural Model for Circular-Shaped Microshield and Conductor-Backed Coplanar Waveguide
P. Thiruvalar Selvan;Singaravelu Raghavan
PIER M , 2009, DOI: 10.2528/PIERM09062903
Abstract: A Computer Aided Design (CAD) approach based on Artificial Neural Networks (ANN's) is successfully introduced to determine the characteristic parameters of Circular-shaped Microshield and Conductor-Backed Coplanar Waveguide (CMCB-CPW). ANN's have been promising tools for many applications and recently ANN has been introduced to microwave modeling, simulation and optimization. The Multi Layered Perceptron (MLP) neural network used in this work were trained with Levenberg-Marquart (LM), Bayesian regularization (BR), Quasi-Newton (QN), Scaled Conjugate gradient (SCG), Conjugate gradient of Fletcher-Powell (CGF) and Conjugate Gradient backpropagation with Polak-Ribiere (CGP) learning algorithms. This has facilitated the usage of ANN models. The notable benefits are simplicity & accurate determination of the characteristic parameters of CMCBCPW's. The greatest advantage is lengthy formulas can be dispensed with.
About Some Applications of Microwave Energy
Marius A.Silaghi,Ulrich L.Rohde
Journal of Electrical and Electronics Engineering , 2009,
Abstract: Microwave energy is an alternative energysource and the fundamentally different method oftransferring energy from the source to the sample isthe main benefit of utilizing microwave energy.Furthermore, the penetrating capacity of microwaveallows volumetric heating of samples. These attributesof microwave energy make utilizing it very attractivefor industrial applications as an alternative toconventional processing methods. The utilization ofmicrowave energy has produced improved resultscompared to conventional methods with reducedheating times or reaction temperature ,so this articleprovides a general overview of reported applications ofmicrowave energy.
Methodology of Neural Design: Applications in Microwave Engineering
P. Pomenka,Z. Raida
Radioengineering , 2006,
Abstract: In the paper, an original methodology for the automatic creation of neural models of microwave structures is proposed and verified. Following the methodology, neural models of the prescribed accuracy are built within the minimum CPU time. Validity of the proposed methodology is verified by developing neural models of selected microwave structures. Functionality of neural models is verified in a design - a neural model is joined with a genetic algorithm to find a global minimum of a formulated objective function. The objective function is minimized using different versions of genetic algorithms, and their mutual combinations. The verified methodology of the automated creation of accurate neural models of microwave structures, and their association with global optimization routines are the most important original features of the paper.
Some Exact Results of Hopfield Neural Networks and Applications  [PDF]
Hong-Liang Lu,Xi-Jun Qiu
Physics , 1999,
Abstract: A set of fixed points of the Hopfield type neural network was under investigation. Its connection matrix is constructed with regard to the Hebb rule from a highly symmetric set of the memorized patterns. Depending on the external parameter the analytic description of the fixed points set had been obtained. And as a conclusion, some exact results of Hopfield neural networks were gained.
Enhancing the Accuracy of Microwave Element Models by Artificial Neural Networks
J. Dobes,L. Pospisil
Radioengineering , 2004,
Abstract: In the recent PSpice programs, five types of the GaAs FET model havebeen implemented. However, some of them are too sophisticated andtherefore very difficult to measure and identify afterwards, especiallythe realistic model of Parker and Skellern. In the paper, simpleenhancements of one of the classical models are proposed first. Theresulting modification is usable for the accurate modeling of both GaAsFETs and pHEMTs. Moreover, its updated capacitance function can serveas an accurate representation of microwave varactors, which is alsoimportant. The precision of the updated models can be strongly enhancedusing the artificial neural networks. In the paper, both using anexclusive neural network without an analytic model and cooperating acorrective neural network with the updated analytic model will bediscussed. The accuracy of the analytic models, the models based on theexclusive neural network, and the models created as a combination ofthe updated analytic model and the corrective neural network will becompared.
Multiplicatively interacting point processes and applications to neural modeling  [PDF]
Stefano Cardanobile,Stefan Rotter
Mathematics , 2009,
Abstract: We introduce a nonlinear modification of the classical Hawkes process, which allows inhibitory couplings between units without restrictions. The resulting system of interacting point processes provides a useful mathematical model for recurrent networks of spiking neurons with exponential transfer functions. The expected rates of all neurons in the network are approximated by a first-order differential system. We study the stability of the solutions of this equation, and use the new formalism to implement a winner-takes-all network that operates robustly for a wide range of parameters. Finally, we discuss relations with the generalised linear model that is widely used for the analysis of spike trains.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.