Krisztián Balázs

36195343300

Publications - 22

Construction site layout and building material distribution planning using hybrid algorithms

Krisztián Balázs Bence Kalmár András Kalmár L. T. Koczy

Publication Name: Studies in Computational Intelligence

Publication Date: 2014-02-03

Volume: 530

Issue: Unknown

Page Range: 75-88

Description:

Chapters have been written previously about how genetic algorithms and other evolution-based algorithms could aid construction site layout planning. These articles presented approaches that solved of the layout problem by applying costs on the moving of construction materials across the site. Our goal was to build an algorithm which is specialized in solving problems of distributing building materials- brick for example-on a site by placing their pallets at the optimal spots, for every unit built from a given material to be within optimal reach. This article describes a solution of this problem for the engineering practice and interprets the slow but accurate method of the Hungarian Algorithm, further it proposes a Memetic Algorithm as a faster but almost as accurate solution. Conclusions are drawn about the usability of this method. © Springer International Publishing Switzerland 2014.

Open Access: Yes

DOI: 10.1007/978-3-319-03206-1_6

A stochastic model for analyzing the interpretability-accuracy trade-off in interpretable fuzzy systems using nested Hyperball structures

Krisztián Balázs L. T. Koczy

Publication Name: 8th Conference of the European Society for Fuzzy Logic and Technology Eusflat 2013 Advances in Intelligent Systems Research

Publication Date: 2013-12-01

Volume: 32

Issue: Unknown

Page Range: 72-79

Description:

Our recent work proposed a new meaning preservation approach together with a parameterizable nested hyperball structured search space for interpretable fuzzy systems in order to solve a problem of inconsistency observed in conventional interpretable fuzzy knowledge bases and simultaneously to address the adjustment of the trade-off between interpretability and accuracy. Based on intuitive reasonings and simulation results a conjecture was formulated about favorable trade-off adjustment properties of the proposed method. The aim of the present paper is to construct a mathematical model, in which the conjectured properties can be analyzed and formally verified. Some computational considerations about the interpretation of the resulting knowledge bases are also made. © 2013. The authors -Published by Atlantis Press.

Open Access: Yes

DOI: DOI not available

Doctoral symposium on recent advances in information technology

Ferenc Lilik Piotr Kulczycki L. T. Koczy Piotr Andrzej Kowalski Dominika Golunska Szymon Lukasik Jaroslaw Arabas Alex Tormási Radko Mesiar Krisztián Balázs Krassimir T. Atanassov Modesto Castrillon-Santana Malgorzata Charytanowicz Thomas Corpetti Nicolas Courty Philippe Fournier-Viger David Gil Bao Gang Hu Carles Noguera I Clofent Milan Petrik Yujiu Yang Slawomir Zadrozny

Publication Name: 2013 Federated Conference on Computer Science and Information Systems Fedcsis 2013

Publication Date: 2013-12-01

Volume: Unknown

Issue: Unknown

Page Range: 637

Description:

No description provided

Open Access: Yes

DOI: DOI not available

Adaptive scheduling of optimization algorithms in the construction of interpolative fuzzy systems

Krisztián Balázs L. T. Koczy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2013-11-22

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

This paper presents an adaptive scheduling approach applied for constructing interpolative fuzzy rule based systems. This is a continuation of our preceding work, where the same approach was used for dense fuzzy rule bases. © 2013 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZ-IEEE.2013.6622555

Constructing dense fuzzy systems by adaptive scheduling of optimization algorithms

Krisztián Balázs L. T. Koczy

Publication Name: Proceedings of the 2013 Joint Ifsa World Congress and NAFIPS Annual Meeting Ifsa NAFIPS 2013

Publication Date: 2013-10-31

Volume: Unknown

Issue: Unknown

Page Range: 280-285

Description:

In this paper dense fuzzy rule based systems are constructed for solving machine learning problems. During the knowledge extraction process a scheduling approach is applied, which adaptively switches between the different optimization algorithms based on their convergence speed in the phases of the learning process, i.e. according to their respective local efficiency. © 2013 IEEE.

Open Access: Yes

DOI: 10.1109/IFSA-NAFIPS.2013.6608413

Improving system reliability in optical networks by failure localization using evolutionary optimization

Péter Soproni Krisztián Balázs L. T. Koczy

Publication Name: Syscon 2013 7th Annual IEEE International Systems Conference Proceedings

Publication Date: 2013-08-30

Volume: Unknown

Issue: Unknown

Page Range: 394-399

Description:

This paper proposes a novel approach for cost-effective link failure localization in optical networks in order to improve the reliability of telecommunication systems. In such failure localization problems the optical network is usually represented by a graph, where the task is to form connected edge sets, so-called monitoring trails (m-trails), in a way that the failure of a link causes the failure of such a combination of m-trails, which unambiguously identifies the failed link. Every m-trail consumes a given amount of resources (like bandwidth, detectors, amplifiers, etc.). Thus, operators of optical network may prefer a set of paths, whose paths can be established in an easy and cost-effective way, while minimizing the interference with the route of the existing demands, i.e. may maximize the revenue. In this paper, unlike most existing techniques dealing with failure localization in this context, the presently proposed method considers a predefined set of paths in the graph as m-trails. This way the task can also be formulated as a special Set Covering Problem (SCP), whose general form is a frequently used formulation in a certain type of operations research problems (e.g. resource assignment). Since for the SCP task evolutionary algorithms, like Ant Colony Optimization (ACO), has been successfully applied in the operations research field, in this work the failure localization task is solved by using ACO on the SCP formulation of the described covering problem, which is a rather unique combination of approaches of different fields (telecommunication, operations research and evolutionary computation) placing our investigation in the multi-field scope of complex systems. © 2013 IEEE.

Open Access: Yes

DOI: 10.1109/SysCon.2013.6549912

Multi-threaded Bacterial Iterated Greedy heuristics for the Permutation Flow Shop Problem

Krisztián Balázs L. T. Koczy Zoltán Horváth

Publication Name: Cinti 2012 13th IEEE International Symposium on Computational Intelligence and Informatics Proceedings

Publication Date: 2012-12-01

Volume: Unknown

Issue: Unknown

Page Range: 63-66

Description:

This paper proposes approaches for combining Iterated Greedy techniques, as state-of-the-art methods, with bacterial evolutionary algorithms based on a hybrid technique involving the Multi-Threaded Iterated Greedy heuristic and a memetic algorithm in order to efficiently solve the Permutation Flow Shop Problem on parallel computing architectures. In the present work three novel approaches are proposed by combining a variant of the Bacterial Memetic Algorithm and the recently proposed Bacterial Iterated Greedy technique with the mentioned hybrid multi-threaded approach. The techniques thus obtained are evaluated via simulation runs carried out on a series of data from the well-known Taillard's benchmark problem set. Based on the experimental results the multi-threaded hybrid methods are compared to each other and to the original techniques (i.e. to the techniques without bacterial algorithms). © 2012 IEEE.

Open Access: Yes

DOI: 10.1109/CINTI.2012.6496734

New parameterizable search space narrowing technique for adjusting between accuracy and interpretability in fuzzy systems

Krisztián Balázs L. T. Koczy

Publication Name: Cinti 2012 13th IEEE International Symposium on Computational Intelligence and Informatics Proceedings

Publication Date: 2012-12-01

Volume: Unknown

Issue: Unknown

Page Range: 323-328

Description:

It is well known that beyond the fact that fuzzy systems have favorable modeling capabilities from the viewpoint of accuracy, they also have outstanding inherent interpretability possibilities, which is a rather unique property among modeling architectures and which is a strong motivation for their research and application. This paper focuses on both mentioned property types and proposes a new technique for adjusting between accuracy and interpretability in modeling systems where fuzzy rule based architectures together with evolutionary algorithms are used for knowledge extraction. First, an inconsistency problem of conventional interpretable fuzzy systems is resolved. Then, a new search space narrowing technique for evolutionary algorithms is proposed, which can be applied for constructing interpretable fuzzy rule bases. Finally, the favorable properties of this new approach will be verified experimentally by carrying out simulation runs. © 2012 IEEE.

Open Access: Yes

DOI: 10.1109/CINTI.2012.6496783

Genetic and bacterial memetic programming approaches in hierarchical-interpolative fuzzy system construction

Krisztián Balázs L. T. Koczy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2012-10-23

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

As a straightforward continuation of our previous work in this paper new memetic (combined evolutionary and gradient based) methods are proposed for constructing hierarchical-interpolative fuzzy rule bases in the frame of a supervised machine learning system modeling black box systems defined by input-output pairs. In this work the resulting hierarchical rule bases are constructed by using structure building Genetic and Bacterial Memetic Programming Algorithms, thus stochastic evolutionary optimization methods containing deterministic local search steps. Applying hierarchical-interpolative fuzzy rule bases has proved an efficient way of reducing the complexity of knowledge bases, whereas memetic techniques often ensure a relatively fast convergence in the learning process. The literature has highlighted the advantages of memetic methods against pure evolutionary algorithms, thus the combination of hierarchical-interpolative fuzzy rule bases with memetic techniques may form promising hierarchical-interpolative machine learning systems. © 2012 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZ-IEEE.2012.6251218

Hybrid Bacterial Iterated Greedy heuristics for the Permutation Flow Shop Problem

Krisztián Balázs L. T. Koczy Zoltán Horváth

Publication Name: 2012 IEEE Congress on Evolutionary Computation CEC 2012

Publication Date: 2012-10-04

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

This paper proposes approaches for combining the Iterated Greedy (IG) technique, as a presently state-of-the-art method, with a recently proposed adapted version of the Bacterial Evolutionary Algorithm (BEA) in order to efficiently solve the Permutation Flow Shop Problem. The obtained techniques are evaluated via simulation runs carried out on the well-known Taillard's benchmark problem set. Based on the experimental results the hybrid methods are compared to each other and to the original techniques (i.e. to the original IG and BEA algorithms). © 2012 IEEE.

Open Access: Yes

DOI: 10.1109/CEC.2012.6256167

Different Chromosome-based Evolutionary Approaches for the Permutation Flow Shop Problem

Krisztián Balázs L. T. Koczy Zoltán Horváth

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2012-05-28

Volume: 9

Issue: 2

Page Range: 115-138

Description:

This paper proposes approaches for adapting chromosome-based evolutionary methods to the Permutation Flow Shop Problem. Two types of individual representation (i.e. encoding methods) are proposed, which are applied on three different chromosome based evolutionary techniques, namely the Genetic Algorithm, the Bacterial Evolutionary Algorithm and the Particle Swarm Optimization method. Both representations are applied on the two former methods, whereas one of them is used for the latter optimization technique. Each mentioned algorithm is involved without and with local search steps as one of its evolutionary operators. Since the evolutionary operators of each technique are established according to the applied representation, this paper deals with a total number of ten different chromosome-based evolutionary methods. The obtained techniques are evaluated via simulation runs carried out on the well-known Taillard's benchmark problem set. Based on the experimental results the approaches for adapting chromosome based evolutionary methods are compared to each other.

Open Access: Yes

DOI: DOI not available

Hierarchical-interpolative fuzzy system construction by genetic and bacterial memetic programming approaches

Krisztián Balázs L. T. Koczy

Publication Name: International Journal of Uncertainty Fuzziness and Knowldege Based Systems

Publication Date: 2012-01-01

Volume: 20

Issue: SUPPL. 2

Page Range: 105-131

Description:

In this paper a family of new methods are proposed for constructing hierarchical-interpolative fuzzy rule bases in the frame of a fuzzy rule based supervised machine learning system modeling black box systems defined by input-output pairs. The resulting hierarchical rule base is constructed by using structure building pure evolutionary and memetic techniques, namely, Genetic and Bacterial Programming Algorithms and their memetic variants containing local search steps. Applying hierarchical-interpolative fuzzy rule bases is a rather efficient way of reducing the complexity of knowledge bases, whereas evolutionary methods (including memetic techniques) ensure a relatively fast convergence in the learning process. As it is presented in the paper, by applying a newly proposed representation schema these approaches can be combined to form hierarchical-interpolative machine learning systems. © 2012 World Scientific Publishing Company.

Open Access: Yes

DOI: 10.1142/S021848851240017X

Hierarchical-interpolative fuzzy system construction by Genetic and Bacterial Programming Algorithms

Krisztián Balázs L. T. Koczy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2011-09-27

Volume: Unknown

Issue: Unknown

Page Range: 2116-2122

Description:

In this paper a method is proposed for constructing hierarchical- interpolative fuzzy rule bases in order to model black box systems defined by input-output pairs, i.e. to solve supervised machine learning problems. The resulting hierarchical rule base is the knowledge base, which is constructed by using evolutionary techniques, namely, Genetic and Bacterial Programming Algorithms. Applying hierarchical-interpolative fuzzy rule bases is an advanced way of reducing the complexity of the knowledge base, whereas evolutionary methods ensure a relatively efficient learning process. This is the reason of the investigation of this combination. © 2011 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZY.2011.6007594

Hierarchical fuzzy system construction applying genetic and bacterial programming algorithms with expression tree building restrictions

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: 2010 World Automation Congress Wac 2010

Publication Date: 2010-12-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper various restrictions are proposed in the construction of hierarchical fuzzy rule bases by using Genetic and Bacterial Programming algorithms in order to model black box systems defined by input-output pairs, i.e. to solve supervised machine learning problems. The properties (learning speed, accuracy) of the established systems are observed based on simulation results and they are compared to each other. © 2010 TSI Press.

Open Access: Yes

DOI: DOI not available

Using multiple populations of memetic algorithms for fuzzy rule-base optimization

Krisztián Balázs Zsolt Dányádi L. T. Koczy

Publication Name: 11th IEEE International Symposium on Computational Intelligence and Informatics Cinti 2010 Proceedings

Publication Date: 2010-12-01

Volume: Unknown

Issue: Unknown

Page Range: 113-118

Description:

Evolutionary algorithms are an important branch of soft computing, being able to provide approximate solutions to problems in a reasonable amount of time. The underlying principle can be realized in an almost unlimited number of ways. This paper presents four main variants of evolutionary algorithms, and a method of running them in a topology consisting of multiple populations. The resources given to each population and migration are altered dynamically throughout the test, based on the effectiveness they show. Along with evolutionary methods, the solutions are also adjusted by gradient-based numerical optimization, in our case the Levenberg-Marquardt algorithm. These steps are added to the evolutionary processes as an extension, resulting in what are called memetic algorithms. The specific application for these methods here is optimizing fuzzy rule-bases, thereby making inference systems better at emulating a desired behavior, such as modeling a certain objective function. ©2010 IEEE.

Open Access: Yes

DOI: 10.1109/CINTI.2010.5672264

A remark on adaptive scheduling of optimization algorithms

Krisztián Balázs L. T. Koczy

Publication Name: Communications in Computer and Information Science

Publication Date: 2010-12-01

Volume: 81 PART 2

Issue: Unknown

Page Range: 719-728

Description:

In this paper the scheduling problem of optimization algorithms is defined. This problem is about scheduling numerical optimization methods from a set of iterative 'oracle-based' techniques in order to obtain an as efficient as possible optimization process based on the given set of algorithms. Statements are formulated and proven about the scheduling problem and methods are proposed to solve this problem. The applicability of one of the proposed methods is demonstrated through a simple fuzzy rule based machine learning example. © Springer-Verlag Berlin Heidelberg 2010.

Open Access: Yes

DOI: 10.1007/978-3-642-14058-7_74

Hierarchical fuzzy system modeling by genetic and bacterial programming approaches

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: 2010 IEEE World Congress on Computational Intelligence Wcci 2010

Publication Date: 2010-11-25

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper a method is proposed for constructing hierarchical fuzzy rule bases in order to model black box systems defined by input-output pairs, i.e. to solve supervised machine learning problems. The resultant hierarchical rule base is the knowledge base, which is constructed by using structure constructing evolutionary techniques, namely, Genetic and Bacterial Programming Algorithms. Applying hierarchical fuzzy rule bases is a way of reducing the complexity of the knowledge base, whereas evolutionary methods ensure a relatively efficient learning process. This is the reason of the investigation of this combination. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZY.2010.5584220

Comparative analysis of interpolative and non-interpolative fuzzy rule based machine learning systems applying various numerical optimization methods

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: 2010 IEEE World Congress on Computational Intelligence Wcci 2010

Publication Date: 2010-11-25

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper interpolative and non-interpolative fuzzy rule based machine learning systems are investigated by using simulation results. The investigation focuses mainly on two objectives: to compare the efficiency of the inference techniques combined with different numerical optimization methods for solving machine learning problems and to discover the difference between the properties of systems applying interpolative and non-interpolative inference techniques. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZY.2010.5584156

Comparative investigation of various evolutionary and memetic algorithms

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: Studies in Computational Intelligence

Publication Date: 2010-11-03

Volume: 313

Issue: Unknown

Page Range: 129-140

Description:

Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems. © 2010 Springer-Verlag Berlin Heidelberg.

Open Access: Yes

DOI: 10.1007/978-3-642-15220-7_11

A comparative study of various evolutionary algorithms used for fuzzy rule-based inference and learning systems

Krisztián Balázs Zsolt Dányádi L. T. Koczy

Publication Name: Iccc Conti 2010 IEEE International Joint Conferences on Computational Cybernetics and Technical Informatics Proceedings

Publication Date: 2010-08-06

Volume: Unknown

Issue: Unknown

Page Range: 49-54

Description:

The goal of this paper is to provide an overview of a variety of evolutionary algorithms, comparing their efficiency on fuzzy rule-based inference and learning. Fuzzy rule-based inference can be used to model a desirable outward behavior of a system when given a specific input, which, in the case of this comparative study, is determined by a set of samples, generated by sufficiently complex objective functions. Optimizing a fuzzy rule-based inference system is a matter of finding a rule base that is as close to imitating the desired behavior as possible. While the specific applications of evolutionary methods are endless, the objective functions used here remain general in nature. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/ICCCYB.2010.5491228

Comparative analysis of various evolutionary and memetic algorithms

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: 10th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics Cinti 2009

Publication Date: 2009-12-01

Volume: Unknown

Issue: Unknown

Page Range: 193-205

Description:

Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared by applying them on several numerical optimization benchmark functions and on fuzzy rule base identification.

Open Access: Yes

DOI: DOI not available

Comparison of fuzzy rule-based learning and inference systems

J. Botzheim Krisztián Balázs L. T. Koczy

Publication Name: 9th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics Cinti 2008

Publication Date: 2008-12-01

Volume: Unknown

Issue: Unknown

Page Range: 61-75

Description:

In our work we have compared various fuzzy rule based learning and inference systems. The base of the investigations was a modular system that we have implemented in C language. It contains several alternative versions of the two key elements of rule based learning - namely, the optimization algorithm and the inference method - which can be found in the literature. We obtained very different properties when combining these alternatives (changing the modules and connecting them) in all possible ways. The investigations determined the values of the quality measures (complexity and accuracy) of the obtained alternatives both analitically and experimentally where it was possible. Based on these quality measures the combinations have been ordered according to different aspects.

Open Access: Yes

DOI: DOI not available