Search in Publications

Found 6289 publications

Novel calculation of fuzzy exponent in the sigmoid functions for fuzzy neural networks

János Botzheim Peter Foldesi

Publication Name: Neurocomputing

Publication Date: 2014-04-10

Volume: 129

Issue: Unknown

Page Range: 458-466

Description:

This paper presents a novel calculation of fuzzy exponent in the sigmoid functions for fuzzy neural networks. The investigated fuzzy neural network applies fuzzy input signals and crisp connection weights in the network's hidden and output layers. The applied calculation of fuzzy exponent is based on a parametric representation of the fuzzy exponent that is able to provide a crisp output instead of the extension principle's fuzzy output and requires significantly less computational effort than the learning based on α-cuts. For the training of the network the bacterial memetic algorithm is applied which effectively combines the bacterial evolutionary algorithm with gradient based learning. The method is tested on a benchmark problem and on two real datasets. Comparison to the classical technique concerning the learning time is also provided in the paper. © 2013 Elsevier B.V.

Open Access: Yes

DOI: 10.1016/j.neucom.2013.09.013

Measurement and simulation of magnetic flux density, a comparative study

Miklós Kuczmann Gergely Friedl

Publication Name: Pollack Periodica

Publication Date: 2014-04-01

Volume: 9

Issue: 1

Page Range: 133-144

Description:

The paper presents a modified version of the T.E.A.M. Problem No. 32 of the Compumag Society. The original problem is a measurement arrangement to study the magnetic flux density distribution inside an EI ferrite core. A finite element simulation of the device in the frame of COMSOL Multiphysics using the A-formulation has been worked out. First, the device has been realized, and a LabVIEW program has been implemented to measure the waveform of the voltage of B-coils. The geometry and the solution of the problem have been implemented in the frame of COMSOL Multiphysics, to calculate magnetic flux density at the points, where B-coils are on the core.

Open Access: Yes

DOI: 10.1556/Pollack.9.2014.1.14

Accelerating unstructured finite volume computations on field-programmable gate arrays

Csaba Nemes Antal Hiba Zoltán Nagy András Kiss Árpád Csík Péter Szolgay Miklõs Ruszinkõ

Publication Name: Concurrency and Computation Practice and Experience

Publication Date: 2014-03-10

Volume: 26

Issue: 3

Page Range: 615-643

Description:

In the paper, an field-programmable gate array (FPGA)-based framework is described to efficiently accelerate unstructured finite volume computations where the same mathematical expression has to be evaluated at every point of the mesh. The irregular memory access patterns caused by the unstructured spatial discretization are eliminated by a novel mesh node reordering technique, and a special architecture is designed to fully utilize the benefits of the predictable memory access patterns. In the proposed architecture, a fixed-size moving window of the input stream of the reordered state variables is cached into the on-chip memory and a pipelined chain of processing elements, which gets input only from the fast on-chip memory, is used to carry out the computations. The arithmetic unit (AU) of the processing elements is generated from the data flow graph extracted from the given mathematical expression. The data flow graph is partitioned with a novel graph partitioning algorithm to break up the AU into smaller locally controlled parts, which can be more efficiently implemented in FPGA than the globally controlled AU. The proposed architecture and algorithms are presented via a case study solving the Euler equations on an unstructured mesh. On the currently available largest FPGA, the generated architecture contains three processing elements working in a pipelined fashion to provide one order of magnitude speedup compared with a high performance microprocessor and three times speedup compared with a high performance graphics processing unit. Copyright © 2013 John Wiley & Sons, Ltd. Copyright © 2013 John Wiley & Sons, Ltd.

Open Access: Yes

DOI: 10.1002/cpe.3022

Environmental prerequisites of "sustainable well-being" program

Gergely Horváth

Publication Name: Tarsadalomkutatas

Publication Date: 2014-03-01

Volume: 32

Issue: 1

Page Range: 51-62

Description:

Sustainability will not be achieved as long as the human race does not realize its perpetual dependence on the environment. Economic prosperity is based on natural capital, "the natural bases of life" that man can not change with impunity. Man has to be aware of the effects of forcing economic growth and the misconception of the endless biophysical environment. The Seventh Environmental Action Programme, the title of which is "Living well within the limits of our planet" is inconsistent in the state of "overshoot"52. The "growth"-with any indicative before-can not be sustainable in a biophysically inherently finite world. "Well-being" is a relative level, and has a different content as a concept according to patterns of values, and is also fundamentally re-evaluated in a crisis situation.

Open Access: Yes

DOI: 10.1556/Tarskut.32.2014.1.4

Modeling the condition of buildings by real fuzzy sets

Ádám Bukovics L. T. Kóczy

Publication Name: International Journal for Housing Science and Its Applications

Publication Date: 2014-02-13

Volume: 38

Issue: 1

Page Range: 1-12

Description:

It is an important task to qualify and rank residential buildings based on various priority aspects and to make optimum allocation of the material resources available for the renewal of the buildings. To this end a model based on fuzzy logic was prepared. To construct and to test this model many detailed technical-static expert reports were available all related to a stock of residential buildings in Budapest. Based on this report a database was created. With the help of this database a model was prepared, calculating a so-called status characteristic value between 0 and 1 on the basis of the structures and status of the buildings. For this calculation a fuzzy singleton signature model was prepared. Based on this a hierarchy can be set up related to the stock of buildings, which is suitable for supporting the decision-making on intervention. The model was examined by using the created database. Membership values characterising the status of the load-bearing structures - were defined on the basis of the deterioration of the structures. In this paper a new method for the determination of the membership values is described, which in addition to the deteriorations of the structures takes into account other parameters of the structures, and the impact exerted on the quality of the structure, too. The method is suitable for the determination of the membership values of all primary and secondary structures. As an example the membership values of the foundation structures of the buildings in the database were defined and the results were analysed. The method was elaborated by the use of 'real fuzzy values' (R-fuzzy sets), an extension of the concept of classic fuzzy sets, the former being suitable for simultaneously taking into account various aspects text. Copyright©2014 IAHS.

Open Access: Yes

DOI: DOI not available

Fuzzy single-stroke character recognizer with various rectangle fuzzy grids

A. Tormási L. T. Kóczy

Publication Name: Studies in Computational Intelligence

Publication Date: 2014-02-03

Volume: 530

Issue: Unknown

Page Range: 145-159

Description:

In this chapter we introduce the results of a formerly published FUBAR character recognition method with various fuzzy grid parameters. The accuracy and efficiency of the handwritten single-stroke character recognition algorithm with different sized rectangle (N×M) fuzzy grids are investigated. The results are compared to other modified FUBAR algorithms and known commercial and academic recognition methods. Possible applications and further extensions are also discussed. This work is the extended and fully detailed version of a previously published abstract. © Springer International Publishing Switzerland 2014.

Open Access: Yes

DOI: 10.1007/978-3-319-03206-1_11

Test generation for short-circuit faults in digital circuits

Jozsef Sziray

Publication Name: Studies in Computational Intelligence

Publication Date: 2014-02-03

Volume: 530

Issue: Unknown

Page Range: 313-319

Description:

In the first part, the paper presents a test calculation principlewhich serves for producing tests of logic faults in digital circuits. The name of the principle is composite justification. The considered faultmodel includes stuck-at-0/1 logic faults. Both single and multiple faults are included. In this paper only combinational logic is taken into consideration. The computations are performed at the gate level. The calculation principle is comparatively simple. It is based only on successive linevalue justification, and it yields an opportunity to be realized by an efficient computer program. The first part serves for presenting the basic principle which is used in the second part of the paper. The second part deals with another fault class, namely, short-circuit or bridging faults. A short circuit is an erroneous galvanic connection between two circuit lines. Here, a new algorithm is presented for generating tests, where the composite justification is extended to handle this type of faults, as well. © Springer International Publishing Switzerland 2014.

Open Access: Yes

DOI: 10.1007/978-3-319-03206-1_21

Vehicle classification using neural networks with a single magnetic detector

Peter Šarčević

Publication Name: Studies in Computational Intelligence

Publication Date: 2014-02-03

Volume: 530

Issue: Unknown

Page Range: 103-115

Description:

In this work, principles of operation, advantages and disadvantages are presented for different detector technologies. An idea of a new detection and classification method for a single magnetic sensor based system is also discussed. It is important that the detection algorithm and the neural network classifier needs to be easily implementable in a microcontroller based system. © Springer International Publishing Switzerland 2014.

Open Access: Yes

DOI: 10.1007/978-3-319-03206-1_8

Intelligent robot cooperation with fuzzy communication

Claudiu Radu Pozna Áron Ballagi L. T. Kóczy

Publication Name: Studies in Computational Intelligence

Publication Date: 2014-02-03

Volume: 530

Issue: Unknown

Page Range: 185-197

Description:

Designing the decision-making engine of a robot which works in a collaborative team is a challenging task. This is not only due to the complexity of the environment uncertainty, dynamism and imprecision, but also because of the coordination of the team has to be included in this design. The robots must be aware of other robots' actions in order to cooperate and to successfully achieve their common goal. In addition, decisions must be made in real-time and using limited computational resources. In this chapter we propose some novel algorithms for action selection in ambiguous tasks where the communication opportunities among the robots are very limited. © Springer International Publishing Switzerland 2014.

Open Access: Yes

DOI: 10.1007/978-3-319-03206-1_14