PL
 |
EN
Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl
Preferencje help
Polish version English version Język
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 25

Liczba wyników na stronie
first rewind previous Strona / 2 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 2 next fast forward last
1
Content available Tuning of agent-based computing
100%
Byrski A.
Computer Science
|
2013
|
tom Vol. 14 (3)
491--512
EN
In this paper, an Evolutionary Multi-agent system-based computing process is subjected to a detailed analysis of its parameters in order to establish a base for a better understanding of the meta-heuristics from the practitioner’s point of view. After reviewing the concepts of EMAS and its immunological variant, a series of experiments is shown, and results of the influence of the search outcomes by certain parameters is discussed.
2
Content available Hybrid neuro-fuzzy classifier based on NEFCLASS model
63%
Gliwa B. , Byrski A.
Computer Science
|
2011
|
tom Vol. 12
115-135
EN
The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which was modified. The presented classifier was compared to popular classifiers - neural networks and k-nearest neighbours. Efficiency of modifications in classifier was compared with methods used in original model NEFCLASS (learning methods). Accuracy of classifier was tested using 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wis-consin. Moreover, influence of ensemble classification methods on classification accuracy was presented.
PL
Artykuł przedstawia zasadę działania oraz wyniki badań eksperymentalnych klasyfikatora opartego na hybrydzie sieci neuronowej z logiką rozmytą, bazujący na modelu NEFCLASS. Prezentacja struktury i działania klasyfikatora została zilustrowana wynikami eksperymentów porównawczych przeprowadzonych dla popularnych klasyfikatorów, takich jak perceptron wielowarstwowy k najbliższych sąsiadów. Skuteczność wprowadzonych modyfikacji do klasyfikatora została porównana z metodami używanymi w oryginalnym modelu NEFCLASS (metody uczenia). Jako dane benchmarkowe posłużyły wybrane bazy danych z UCI Machine Learning Repository (iris, wine, breast cancer wisconsin). Zaprezentowano również wpływ użycia metod klasyfikacji zbiorczej na efektywność klasyfikacji.
3
Stochastic Dynamics of Evolutionary Multi-Agent Systems
63%
Byrski A. , Schaefer R.
Prace Naukowe Politechniki Warszawskiej. Elektronika
|
2009
|
tom z. 169
27-34
EN
The refined model for the biologically inspired agent-based computation system EMAS conformed to BDI standard is presented. The considerations are based on the model of the system dynamics as the stationary Markov chain already presented. In the course of paper space of the system states is modified in order assure state coherency and set of actions is simplified. Such a model allows for better understanding the behavior of the proposed complex systems as well as their limitations.
4
Content available remote Ewolucja architektury sieci neuronowej w agentowym systemie predykcji ciągów czasowych
63%
Byrski A. , Kisiel-Dorohinicki M.
Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie
|
2003
|
tom T. 7, z. 1-2
65-72
PL
W artykule zaprezentowano agentowy system ewolucji sieci neuronowych. Idea ewolucyjnego systemu wieloagentowego (EMAS) może pomóc w likwidacji pewnych wad, którymi charakteryzują się klasyczne techniki ewolucyjnej optymalizacji. Rozważania teoretyczne zostały zilustrowane prezentacją systemu rozwiązującego problem predykcji ciągów czasowych, dla którego przedstawiono wybrane wyniki eksperymentów.
EN
In the paper an agent system of evolving neural networks is presented. A concept of decentralised evolutionary computation realised as an evolutionary multi-agent system (EMAS) may help to avoid some of the shortcommings of classical evolutionary optimisation techniques. General considerations are illustrated by the particular system dedicated to a problem of time-series prediction. Selected experimental results conclude the work.
5
Content available remote Stochastic Model of Evolutionary and Immunological Multi-Agent Systems: Mutually Exclusive Actions
63%
Byrski A. , Schaefer R.
Fundamenta Informaticae
|
2009
|
tom Vol. 95, nr 2/3
263-285
EN
The mathematical model of the biologically inspired, memetic, agent-based computation systems EMAS and iEMAS conformed to BDI standard is presented. The state of the systems and their dynamics are expressed as stationary Markov chains. Such an approach allows to better understand their complex behavior as well as their limitations.
6
Content available Optimization of simulation model parameters for solidification of metals with use of agent-based evolutionary algorithm
51%
Kluska-Nawarecka S. , Smolarek-Grzyb A. , Byrski A. , Wilk-Kołodziejczyk D.
Computer Science
|
2008
|
tom Vol. 9
55-66
EN
The finite elements method (FEM) is currently widely used for simulation of thermal processes. However, one of still unresolved problems remains proper selection of mathematical model parameters for these processes. As far as modelling of cooling casts in forms is concerned, particular difficulties appear while estimating values of numerous coefficients such as: heat transport coefficient between metal and form, specific heat, metal and form heat conduction coefficient, metal and form density. Coefficients mentioned above depend not only on materials properties but also on temperature. In the paper the idea of optimalization of simulation method parameters based on adaptive adjustment of curve representing sim­ulation result and result obtained in physical experiment is presented along with the idea of evolutionary and agent-based evolutionary optimization system designed to conduct such optimizations. Preliminary results obtained with use of ABAQUS system available in ACK CYFRONET and software developed at AGH-UST conclude the paper.
PL
Metoda elementów skończonych (MES) znajduje obecnie liczne zastosowania w symulacji procesów cieplnych. Wciąż jednak nierozwiązalny pozostaje problem doboru niektórych współczynników modeli matematycznych tych procesów. Przy modelowaniu stygnięcia odlewów w formie, szczególne trudności powstają przy wyznaczeniu wartości licznych parametrów, np.: współczynnika transportu ciepła pomiędzy metalem a formą, ciepła właściwego, współczynnika przewodnictwa cieplnego metalu i formy, gęstości metalu i formy. Współczynniki te zależą nie tylko od właściwości materiałów, lecz również od temperatury. W artykule zaproponowano metodę optymalizacji wartości parametrów modelu opartą na adaptacyjnym dostosowaniu krzywej stanowiącej wynik symulacji do przebiegu uzyskanego w eksperymencie fizycznym z zastosowaniem algorytmu ewolucyjnego w wersji agentowej. Wstępne wyniki obliczeń zostały zrealizowane przy wykorzystaniu systemu ABAQUS dostępnego w ACK CYFRONET oraz oprogramowania opracowanego przez AGH-UST.
7
Content available The island model as a Markov dynamic system
51%
Schaefer R. , Byrski A. , Smołka M.
International Journal of Applied Mathematics and Computer Science
|
2012
|
tom Vol. 22, no. 4
971-984
EN
Parallel multi-deme genetic algorithms are especially advantageous because they allow reducing the time of computations and can perform a much broader search than single-population ones. However, their formal analysis does not seem to have been studied exhaustively enough. In this paper we propose a mathematical framework describing a wide class of island-like strategies as a stationary Markov chain. Our approach uses extensively the modeling principles introduced by Vose, Rudolph and their collaborators. An original and crucial feature of the framework we propose is the mechanism of inter-deme agent operation synchronization. It is important from both a practical and a theoretical point of view. We show that under a mild assumption the resulting Markov chain is ergodic and the sequence of the related sampling measures converges to some invariant measure. The asymptotic guarantee of success is also obtained as a simple issue of ergodicity. Moreover, if the cardinality of each island population grows to infinity, then the sequence of the limit invariant measures contains a weakly convergent subsequence. The formal description of the island model obtained for the case of solving a single-objective problem can also be extended to the multi-objective case.
8
Koordynacja ruchu robotów mobilnych algorytmem inspirowanym zjawiskami społecznymi
51%
Szomiński S. , Cieśla Ł. , Turek W. , Byrski A.
Prace Naukowe Politechniki Warszawskiej. Elektronika
|
2016
|
tom z. 195, t. 1
25--36
PL
Zarówno zwierzęta jak i ludzie, są w stanie autonomicznie rozwiązać problem wyzmaczania trajektorii, podczas przemieszczania się we wspólnej, ograniczonej przestrzeni. Realizują to bez centralnego planowanie, oraz bez jawnej komunikacji. Obserwacje te skłoniły autorów do stworzenia zdecentralizowanego algorytmu koordynacji robotów mobilnych, rozwiązującego problem wąskich przejść, oraz wyznaczenia pierwszeństwa w drzwiach. W prezentowanej metodzie wykorzystano inspiracje naturalnymi zjawiskami, .jak respekt do osobników większych, czy stojących wyżej w hierarchii społecznej. Prezentowana metoda, została przetestowana w symulatorze, oraz na rzeczywistych robotach mobilnych, oraz została porównana z uznaną metodą Reciprocal Vetocity Obstacles.
EN
Animals or humans are able to plan trajectories for individuals autonomously, without explicit communication. These observations led the authors to create a decentralized algorithm for coordination of mobile robots motion solving the problem of narrow passages and determine the priori ty in the door. The presented method models instincts such as respect for bigger individuals and groups. The presented method has been tested in simulation and with real mobile robots, and was compared with a well-recognized Reciprocal Velocity Obstacles method.
9
Content available Agent-based optimization of advisory strategy parameters
51%
Polnik M. , Kumięga M. , Byrski A.
Journal of Telecommunications and Information Technology
|
2013
|
tom nr 2
49--55
EN
In this paper, an application of Evolutionary Multiagent Systems (EMAS) and its memetic version to the optimization of advisory strategy (in this case, Sudoku advisory strategy) is considered. The problem is tackled using an EMAS, which has already proven as a versatile optimization technique. Results obtained using EMAS and Parallel Evolutionary Algorithm (PEA) are compared. After giving an insight to the possibilities of decision support in Sudoku solving, an exemplary strategy is defined. Then EMAS and its memetic versions are discussed, and experimental results concerning comparison of EMAS and PEA presented.
10
Content available Component-Based Architecture for Systems, Services and Data Integration in Support for Criminal Analysis
51%
Dajda J. , Dębski R. , Byrski A. , Kisiel-Dorohinicki M.
Journal of Telecommunications and Information Technology
|
2012
|
tom nr 1
67-73
EN
Criminal analysis processes is based on heterogeneous data processing. To support it, analysts utilize a large set of specialized tools, however they are usually designed to solve a particular problem are often incompatible with other existing tools and systems. Therefore, to fully leverage the existing supporting tools, their technological integration is required. In this paper we present original approach for integrating systems based on the component-driven paradigm. Firstly, a problem of supporting criminal analysis is described with a strong emphasis on the heterogeneity issues. Secondly, some theoretical information about integration is depicted followed by the details of the proposed architecture. Finally, the technological assumptions are discussed and prototype integration based on proposed concept is overviewed. om the experiments are discussed in the final part of the paper.
11
Content available Towards an Agent-Based Augmented Cloud
51%
Dębski R. , Byrski A. , Kisiel-Dorohinicki M.
Journal of Telecommunications and Information Technology
|
2012
|
tom nr 1
16-22
EN
In the paper an agent-based framework deployed in hybrid cluster and volunteer computing environment is presented. It utilizes two concepts proposed by the authors: Augmented Cloud and Agent Platform as a Service (AgPaaS). Both concepts are discussed in the context of Cloud Computing as defined by NIST. The key idea of the presented solution is to span the cloud (i.e., computing infrastructure) beyond the data center borders by utilizing web browsers as computational workers. The feasibility of the approach was demonstrated by two prototypes: the first one was based on Java Applets and Adobe Flash, whereas the second one on Microsoft Silverlight. The prototypes were next used to perform simple experiments, mainly related to scalability issues. Selected results from the experiments are discussed in the final part of the paper.
12
Content available A crisis management approach to mission survivability in computational multi-agent systems
51%
Byrski A. , Kisiel-Dorohinicki M. , Carvalho M.
Computer Science
|
2010
|
tom Vol. 11
99-113
EN
In this paper we present a biologically-inspired approach for mission survivability (considered as the capability of fulfilling a task such as computation) that allows the system to be aware of the possible threats or crises that may arise. This approach uses the notion of resources used by living organisms to control their populations. We present the concept of energetic selection in agent-based evolutionary systems as well as the means to manipulate the configuration of the computation according to the crises or user's specific demands.
PL
W artykule prezentujemy biologicznie inspirowany mechanizm wspomagający utrzymanie krytycznych zadań (tzw. mission survivability) który umożliwia wykrywanie oraz przeciwdziałanie wybranym zagrożeniom. Przedstawione podejście wzorowane jest na wykorzystywaniu przez żywe organizmy zasobów do kontroli populacji. Prezentujemy koncepcje selekcji energetycznej mającej zastosowanie w ewolucyjnych systemach wieloagentowych (EMAS) oraz sposoby konfiguracji obliczenia w celu przeciwdziałania sytuacjom kryzysowym, według preferencji użytkownika.
13
Content available Evolutionary multi-agent computing in inverse problems
51%
Wróbel K. , Torba P. , Paszyński M. , Byrski A.
Computer Science
|
2013
|
tom Vol. 14 (3)
367--383
EN
This paper tackles the application of evolutionary multi-agent computing to solve inverse problems. High costs of fitness function call become a major difficulty when approaching these problems with population-based heuristics. However, evolutionary agent-based systems (EMAS) turn out to reduce the fitness function calls, which makes them a possible weapon of choice against them. This paper recalls the basics of EMAS and describes the considered problem (Step and Flash Imprint Lithography), and later, shows convincing results that EMAS is more effective than a classical evolutionary algorithm.
14
Content available Analiza dynamiki układu tłokowo-korbowego wybranego silnika spalinowego przy użyciu interfejsu programów MSC.ADAMS i ANSYS
51%
Harlecki A. , Urbaś A. , Nowakowski J. , Byrski A.
Combustion Engines
|
2013
|
tom R. 52, nr 3
1076--1083
PL
W pracy przedstawiono metodę analizy wytrzymałościowej członów układu tłokowo-korbowego wybranego silnika spalinowego o zapłonie samoczynnym, stanowiącego przykład układu mechanicznego o szybkozmiennej dynamice. W analizie dynamiki układu, zrealizowanej w środowisku programów MSC.ADAMS i ANSYS, uwzględniono podatność wszystkich jego podstawowych członów, tzn. tłoka wraz ze sworzniem tłokowym, korbowodu i wału korbowego. Finalną część analizy stanowiły obliczenia wytrzymałościowe wymienionych członów. Zdaniem autorów, prezentowana metoda może być użyteczna w nowocześnie pojmowanym procesie projektowania silników spalinowych.
EN
The paper presents a method of stress analysis of components of the piston-crank system of a selected internal combustion engine as an example of the mechanical system with quick-changing dynamics. In the analysis of the dynamics of the system, carried out in the MSC.ADAMS and ANSYS software environment, the flexibility of all the major members of the system, i.e. piston with piston pin, connecting rod, and crankshaft, was taken into account. The final part of the analysis includes calculations of strength of the aforementioned system members. In authors’ opinion, the method presented may be useful in the up-to-date process of designing internal combustion engines.
15
Content available Asymptotic guarantee of success for multi-agent memetic systems
51%
Byrski A. , Schaefer R. , Smołka M. , Cotta C.
Bulletin of the Polish Academy of Sciences. Technical Sciences
|
2013
|
tom Vol. 61, nr 1
257-278
EN
The paper introduces a stochastic model for a class of population-based global optimization meta-heuristics, that generalizes existing models in the following ways. First of all, an individual becomes an active software agent characterized by the constant genotype and the meme that may change during the optimization process. Second, the model embraces the asynchronous processing of agent’s actions. Third, we consider a vast variety of possible actions that include the conventional mixing operations (e.g. mutation, cloning, crossover) as well as migrations among demes and local optimization methods. Despite the fact that the model fits many popular algorithms and strategies (e.g. genetic algorithms with tournament selection) it is mainly devoted to study memetic algorithms. The model is composed of two parts: EMAS architecture (data structures and management strategies) allowing to define the space of states and the framework for stochastic agent actions and the stationary Markov chain described in terms of this architecture. The probability transition function has been obtained and the Markov kernels for sample actions have been computed. The obtained theoretical results are helpful for studying metaheuristics conforming to the EMAS architecture. The designed synchronization allows the safe, coarse-grained parallel implementation and its effective, sub-optimal scheduling in a distributed computer environment. The proved strong ergodicity of the finite state Markov chain results in the asymptotic stochastic guarantee of success, which in turn imposes the liveness of a studied metaheuristic. The Markov chain delivers the sampling measure at an arbitrary step of computations, which allows further asymptotic studies, e.g. on various kinds of the stochastic convergence.
16
Content available remote Stochastic Model of Evolutionary and Immunological Multi-Agent Systems: Parallel Execution of Local Actions
51%
Schaefer R. , Byrski A. , Smołka M.
Fundamenta Informaticae
|
2009
|
tom Vol. 95, nr 2/3
325-348
EN
The refined model for the biologically inspired agent-based computation systems EMAS and iEMAS conforming to the BDI standard is presented. Moreover, their evolution is expressed in the form of the stationary Markov chains. This paper generalizes the results obtained by Byrski and Schaefer [7] to a strongly desired case in which some agents’ actions can be executed in parallel. In order to find the Markov transition rule, the precise synchronization scheme was introduced, which allows to establish the stepwise stochastic evolution of the system. The crucial feature which allows to compute the probability transition function in case of parallel execution of local actions is the commutativity of their transition operators. Some abstract conditions expressing such a commutativity which allow to classify the agents’ actions as local or global are formulated and verified in a very simple way. The above-mentioned Markov model constitutes the basis of the asymptotic analysis of EMAS and iEMAS necessary to evaluate their search possibilities and efficiency.
17
Agent-based optimization of neural classifiers
51%
Byrski A. , Dobrowolski J. , Toboła K.
Prace Naukowe Politechniki Warszawskiej. Elektronika
|
2008
|
tom z. 165
59-65
EN
In the paper an agent-based system of evolving neural networks dedicated to solving classification problem is presented. Next, aspects of the system concerning management of collective intelligence and evolution of parameters of neural network are discussed. Evolutionary multi-agent system (EMAS) is described with enhanced immune-inspired selection mechanism. Finally selected results of the experiments are presented.
18
Content available remote Volunteer computing in a scalable lightweight web-based environment
45%
Chorazyk P. , Byrski A. , Pietak K. , Kisiel-Dorohinicki M. , Turek W.
Computer Assisted Methods in Engineering and Science
|
2017
|
tom Vol. 24, no. 1
17--40
EN
Volunteer computing is a very appealing way of utilizing vast available resources in efficient way. However, the current platforms that support such computing style are either difficult to use or not available at all, as a results of finished scientific projects, for example. In this paper, a novel lightweight volunteer computing platform is presented and thoroughly tested in an artificial environment of a commercially available computing cloud using two computing-related tasks and one web-crawling-related task.
19
Content available Collectively intelligent prediction in evolutionary multi-agent system
38%
Kijak J. , Martyna P. , Byrski A. , Faber Ł. , Piętak K. , Kisiel-Dorohinicki M.
International Journal of Microelectronics and Computer Science
|
2017
|
tom Vol. 8, nr 3
85--96
EN
In the paper a summary of our previously realized and published work connected with constructing collective intelligent evolutionary multi-agent systems for time series prediction, based on multi-layered perceptrons is shown. Besides recalling our past papers, we describe the whole concept, present an implementation in a contemporary, componentoriented software framework AgE 3.0 and we conduct a number of experiments, finding different optimal parametrization for the considered instances of the problems (popular Mackey-Glass chaotic time series). The paper may be useful for a practitioner willing to use our meatheuristic algorithm (EMAS) along with the idea of collective agent-based system in order to realize prediction tasks.
20
Content available Parallel patterns for agent-based evolutionary computing
38%
Stypka J. , Anielski P. , Mentel S. , Krzywicki D. , Turek W. , Byrski A. , Kisiel-Dorohinicki M.
Computer Science
|
2016
|
tom Vol. 17 (1)
83--98
EN
Computing applications such as metaheuristics-based optimization can greatly benefit from multi-core architectures available on modern supercomputers. In this paper, we describe an easy and efficient way to implement certain population-based algorithms (in the discussed case, multi-agent computing system) on such runtime environments. Our solution is based on an Erlang software library which implements dedicated parallel patterns. We provide technological details on our approach and discuss experimental results.
first rewind previous Strona / 2 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.