arXiv subjects

Iztok Fister

Publications and source records attributed to Iztok Fister.

32 records · Page 2Linked to original sources

arXiv2013

Comparing various regression methods on ensemble strategies in differential evolution

Differential evolution possesses a multitude of various strategies for generating new trial solutions. Unfortunately, the best strategy is not known in advance. Moreover, this strategy usually depends on the problem to be solved. This paper suggests using various regression methods (like random forest, extremely randomized trees, gradient boosting, decision trees, and a generalized linear model) on ensemble strategies in differential evolution algorithm by predicting the best differential evolution strategy during the run. Comparing the preliminary results of this algorithm by optimizing a suite of five well-known functions from literature, it was shown that using the random forest regression method substantially outperformed the results of the other regression methods.

cs.NE↗

arXiv2013

Using the quaternion's representation of individuals in swarm intelligence and evolutionary computation

This paper introduces a novel idea for representation of individuals using quaternions in swarm intelligence and evolutionary algorithms. Quaternions are a number system, which extends complex numbers. They are successfully applied to problems of theoretical physics and to those areas needing fast rotation calculations. We propose the application of quaternions in optimization, more precisely, we have been using quaternions for representation of individuals in Bat algorithm. The preliminary results of our experiments when optimizing a test-suite consisting of ten standard functions showed that this new algorithm significantly improved the results of the original Bat algorithm. Moreover, the obtained results are comparable with other swarm intelligence and evolutionary algorithms, like the artificial bees colony, and differential evolution. We believe that this representation could also be successfully applied to other swarm intelligence and evolutionary algorithms.

cs.NE↗

arXiv2013

EasyTime++: A case study of incremental domain-specific language development

EasyTime is a domain-specific language (DSL) for measuring time during sports competitions. A distinguishing feature of DSLs is that they are much more amenable to change, and EasyTime is no exception in this regard. This paper introduces two new EasyTime features: classifications of competitors into categories, and the inclusion of competitions where the number of laps must be dynamically determined. It shows how such extensions can be incrementally added into the base-language reusing most of the language specifications. Two case studies are presented showing the suitability of this approach.

cs.PL↗

arXiv2013

Hybridization of Evolutionary Algorithms

Evolutionary algorithms are good general problem solver but suffer from a lack of domain specific knowledge. However, the problem specific knowledge can be added to evolutionary algorithms by hybridizing. Interestingly, all the elements of the evolutionary algorithms can be hybridized. In this chapter, the hybridization of the three elements of the evolutionary algorithms is discussed: the objective function, the survivor selection operator and the parameter settings. As an objective function, the existing heuristic function that construct the solution of the problem in traditional way is used. However, this function is embedded into the evolutionary algorithm that serves as a generator of new solutions. In addition, the objective function is improved by local search heuristics. The new neutral selection operator has been developed that is capable to deal with neutral solutions, i.e. solutions that have the different representation but expose the equal values of objective function. The aim of this operator is to directs the evolutionary search into a new undiscovered regions of the search space. To avoid of wrong setting of parameters that control the behavior of the evolutionary algorithm, the self-adaptation is used. Finally, such hybrid self-adaptive evolutionary algorithm is applied to the two real-world NP-hard problems: the graph 3-coloring and the optimization of markers in the clothing industry. Extensive experiments shown that these hybridization improves the results of the evolutionary algorithms a lot. Furthermore, the impact of the particular hybridizations is analyzed in details as well.

cs.NE↗

arXiv2013

Graph 3-coloring with a hybrid self-adaptive evolutionary algorithm

This paper proposes a hybrid self-adaptive evolutionary algorithm for graph coloring that is hybridized with the following novel elements: heuristic genotype-phenotype mapping, a swap local search heuristic, and a neutral survivor selection operator. This algorithm was compared with the evolutionary algorithm with the SAW method of Eiben et al., the Tabucol algorithm of Hertz and de Werra, and the hybrid evolutionary algorithm of Galinier and Hao. The performance of these algorithms were tested on a test suite consisting of randomly generated 3-colorable graphs of various structural features, such as graph size, type, edge density, and variability in sizes of color classes. Furthermore, the test graphs were generated including the phase transition where the graphs are hard to color. The purpose of the extensive experimental work was threefold: to investigate the behavior of the tested algorithms in the phase transition, to identify what impact hybridization with the DSatur traditional heuristic has on the evolutionary algorithm, and to show how graph structural features influence the performance of the graph-coloring algorithms. The results indicate that the performance of the hybrid self-adaptive evolutionary algorithm is comparable with, or better than, the performance of the hybrid evolutionary algorithm which is one of the best graph-coloring algorithms today. Moreover, the fact that all the considered algorithms performed poorly on flat graphs confirms that this type of graphs is really the hardest to color.

cs.NE↗

arXiv2012

Using Differential Evolution for the Graph Coloring

Differential evolution was developed for reliable and versatile function optimization. It has also become interesting for other domains because of its ease to use. In this paper, we posed the question of whether differential evolution can also be used by solving of the combinatorial optimization problems, and in particular, for the graph coloring problem. Therefore, a hybrid self-adaptive differential evolution algorithm for graph coloring was proposed that is comparable with the best heuristics for graph coloring today, i.e. Tabucol of Hertz and de Werra and the hybrid evolutionary algorithm of Galinier and Hao. We have focused on the graph 3-coloring. Therefore, the evolutionary algorithm with method SAW of Eiben et al., which achieved excellent results for this kind of graphs, was also incorporated into this study. The extensive experiments show that the differential evolution could become a competitive tool for the solving of graph coloring problem in the future.

math.CO↗

arXiv2012

Measuring Time in Sporting Competitions with the Domain-Specific Language EasyTime

Measuring time in mass sporting competitions is unthinkable manually today because of their long duration and unreliability. Besides, automatic timing devices based on the RFID technology have become cheaper. However, these devices cannot operate stand-alone. To work efficiently, they need a computer timing system for monitoring results. Such system should be capable of processing the incoming events, encoding and assigning results to a individual competitor, sorting results according to the achieved time and printing them. In this paper, a domain-specific language named EasyTime will be defined. It enables controlling an agent by writing events to a database. Using the agent, the number of measuring devices can be reduced. Also, EasyTime is of a universal type that can be applied to many different sporting competitions

cs.PL↗

arXiv2012

Upgrading EasyTime: from a textual to a visual language

Measuring time in mass sports competitions is usually performed using expensive measuring devices. Unfortunately, these solutions are not acceptable by many organizers of sporting competitions. In order to make the measuring time as cheap as possible, the domain-specific language (DSL) EasyTime was proposed. In practice, it has been proven to be universal, flexible, and efficient. It can even reduce the number of required measuring devices. On the other hand, programming in EasyTime is not easy, because it requires a domain-expert to program in a textual manner. In this paper, the domain-specific modeling language (DSML) EasyTime II is proposed, which simplifies the programming of the measuring system. First, the DSL EasyTime domain analysis is presented. Then, the development of DSML is described in detail. Finally, the DSML was tested by regular organizers of a sporting competition. This test showed that DSML can be used by end-users without any previous programming knowledge.

cs.PL↗

arXiv2012

Implementation of the Domain-Specific Language EasyTime using a LISA Compiler Generator

A manually time-measuring tool in mass sporting competitions cannot be imagined nowadays because many modern disciplines, such as IronMan, take a long time and, therefore, demand additional reliability. Moreover, automatic timing devices, based on RFID technology, have become cheaper. However, these devices cannot operate stand-alone because they need a computer measuring system that is capable of processing the incoming events, encoding the results, assigning them to the correct competitor, sorting the results according to the achieved times, and then providing a printout of the results. In this article, the domain-specific language EasyTime is presented, which enables the controlling of an agent by writing the events in a database. In particular, we are focused on the implementation of EasyTime with a LISA tool that enables the automatic construction of compilers from language specifications using Attribute Grammars. By using of EasyTime, we can also decrease the number of measuring devices. Furthermore, EasyTime is universal and can be applied to many different sporting competitions in practice.

cs.PL↗

arXiv2012

Implementation of EasyTime Formal Semantics using a LISA Compiler Generator

A manual measuring time tool in mass sporting competitions would not be imaginable nowadays, because many modern disciplines, such as IRONMAN, last a long-time and, therefore, demand additional reliability. Moreover, automatic timing-devices based on RFID technology, have become cheaper. However, these devices cannot operate as stand-alone because they need a computer measuring system that is capable of processing incoming events, encoding the results, assigning them to the correct competitor, sorting the results according to the achieved times, and then providing a printout of the results. This article presents the domain-specific language EasyTime, which enables the controlling of an agent by writing the events within a database. It focuses, in particular, on the implementation of EasyTime with a LISA tool that enables the automatic construction of compilers from language specifications, using Attribute Grammars.

cs.PL↗

arXiv2012

Concept of drafting detection system in Ironmans

One of the biggest challenges for the Computer Science of today can be summed up by the paradigm "access to information from $everywhere$ at $anytime$". This is especially true for pervasive computing. With the growth of mobile devices (e.g., smart-phones), on the one hand, and the quick development of the Internet (this has become the really pervasive network of today), on the other hand, the development of real-time pervasive applications has broadened. This paper focuses on the problem of drafting detection in the Ironman triathlons which causes serious problems for the majority of organizers regarding such competitions. A concept of drafting detection system in Ironman is based on the paradigm of pervasive computing. Results of performing a test system show that this concept can along with further development of computer technologies become a reality in the near future.

eess.SY↗

arXiv2012

Memetic Artificial Bee Colony Algorithm for Large-Scale Global Optimization

Memetic computation (MC) has emerged recently as a new paradigm of efficient algorithms for solving the hardest optimization problems. On the other hand, artificial bees colony (ABC) algorithms demonstrate good performances when solving continuous and combinatorial optimization problems. This study tries to use these technologies under the same roof. As a result, a memetic ABC (MABC) algorithm has been developed that is hybridized with two local search heuristics: the Nelder-Mead algorithm (NMA) and the random walk with direction exploitation (RWDE). The former is attended more towards exploration, while the latter more towards exploitation of the search space. The stochastic adaptation rule was employed in order to control the balancing between exploration and exploitation. This MABC algorithm was applied to a Special suite on Large Scale Continuous Global Optimization at the 2012 IEEE Congress on Evolutionary Computation. The obtained results the MABC are comparable with the results of DECC-G, DECC-G*, and MLCC.

cs.NE↗

arXiv2012

Memetic firefly algorithm for combinatorial optimization

Firefly algorithms belong to modern meta-heuristic algorithms inspired by nature that can be successfully applied to continuous optimization problems. In this paper, we have been applied the firefly algorithm, hybridized with local search heuristic, to combinatorial optimization problems, where we use graph 3-coloring problems as test benchmarks. The results of the proposed memetic firefly algorithm (MFFA) were compared with the results of the Hybrid Evolutionary Algorithm (HEA), Tabucol, and the evolutionary algorithm with SAW method (EA-SAW) by coloring the suite of medium-scaled random graphs (graphs with 500 vertices) generated using the Culberson random graph generator. The results of firefly algorithm were very promising and showed a potential that this algorithm could successfully be applied in near future to the other combinatorial optimization problems as well.

math.OC↗

arXiv2012

A Hybrid Artificial Bee Colony Algorithm for Graph 3-Coloring

The Artificial Bee Colony (ABC) is the name of an optimization algorithm that was inspired by the intelligent behavior of a honey bee swarm. It is widely recognized as a quick, reliable, and efficient methods for solving optimization problems. This paper proposes a hybrid ABC (HABC) algorithm for graph 3-coloring, which is a well-known discrete optimization problem. The results of HABC are compared with results of the well-known graph coloring algorithms of today, i.e. the Tabucol and Hybrid Evolutionary algorithm (HEA) and results of the traditional evolutionary algorithm with SAW method (EA-SAW). Extensive experimentations has shown that the HABC matched the competitive results of the best graph coloring algorithms, and did better than the traditional heuristics EA-SAW when solving equi-partite, flat, and random generated medium-sized graphs.

cs.NE↗