|
|
Hybrid Model of Metaheuristic Algorithms
Šandera, Čeněk ; Zelinka, Ivan (referee) ; Matoušek, Radomil (referee) ; Šeda, Miloš (advisor)
The main topic of this PhD thesis is metaheuristic algorithm in wider scope. The first chapters are dedicated to a description of broader context of metaheuristics, i.e. various optimization classes, determination of their omplexity and different approaches to their solutions. The consequent discussion about metaheuristics and their typical characteristics is followed by several selected examples of metaheuristics concepts. The observed characteristics serve as a base for building general metaheuristics model which is suitable for developing brand new or hybrid algorithms. The thesis is concluded by illustration of author’s publications with discussion about their adaptation to the proposed model. On the attached CD, there is also available a program implementation of the created model.
|
|
|
Evolutionary Optimization of Control Algorithms
Weisser, Roman ; Šeda, Miloš (referee) ; Zelinka,, Ivan (referee) ; Ošmera, Pavel (advisor)
The dissertation thesis deals with Evolution optimization of control algorithms. The first part of the thesis describes the principles and partial methods of evolution optimization methods especially those used in two-level transplant evolution method. Later the grammatical evolution method is described, which modified algorithm became impulse for creation of transplant evolution method. The transplant evolution method and its two-level modification are new evolutionary algorithms proposed in this work, which were used for optimization of structure and parameters of general controllers control algorithms. The transplant evolution algorithm and its extended two-level modification are described in detail in next chapters. The proper settings of evolutionary algorithms are important for minimization the time of optimization and for finds results approaching the global optimum. For proper setting the parameters of differential evolution was created meta-evolution algorithm that is described in chapter named meta-evolution. The basic concepts of control, chosen methods of system identification and controller parameters settings are described in next part. This part describes algorithms of digital controllers and some specific methods uses in digital control. The demonstrations of control algorithm optimizations of various types of controllers are showed in experimental part. The optimized algorithms of general controllers are compared with various types of PSD controllers which were set by various algebraic methods or differential evolution for various models of systems. In the conclusion of this work is stated a recommendation for further development of evolutionary optimization of controllers are focusing on parallel and distributed computing.
|
|
|
Proposal of prediction model sales of selected food commodities
Řešetková, Dagmar ; Dostál, Petr (referee) ; Krčmarský, Miroslav (referee) ; Zelinka, Ivan (referee) ; Rais, Karel (advisor)
The dissertation is generally focused on the use of artificial intelligence tools in practice and with regard to the focus of study in the field of Management and Business Economics at using the tools of artificial intelligence in corporate practice, as a tool for decision support at the operational and tactical level management. In the narrower sense, the task deals with the proposal of the prediction sales model of selected food commodities. The proposed model is designed to serve as a substitute for a human expert in support decision-making process in the purchase of selected commodities, especially when training new staff and extend the currently used methods of managerial decision-making about artificial intelligence tools for company management and existing employees. The aim of this dissertation is the design prediction sales model of selected food commodities (apples and potatoes) for specific wholesale of fruit and vegetable operating in the Czech Republic. To become familiar with the behaviour of selected commodities were used primary and secondary research as well and knowledge gained from Czech and foreign literature sources and research. The resulting predictive model is developed using statistical analysis of time series and the sales prediction proceeds using the tools of artificial intelligence and is modeled by an artificial neural network. The dissertation in the practical part also contains proposals for the use of the prediction model and partial processing procedures for: • practice, • theory, • pedagogical activities.
|
|
|
Optimalization of Constructional Teams Creation by Genetic Algorithms
Špaček, Jiří ; Zelinka, Ivan (referee) ; Šeda, Miloš (referee) ; Ošmera, Pavel (advisor)
The thesis pertains to optimisation of workgroups in companies. It is based on the work of Dr. Meredith Belbin from the Henley Management College, who is the author of the so-called Belbin’s team role theory. The theory defines fundamental roles within a team including specifications of the behavioural patterns while stipulating that in order to ensure proper functionality of a team, it is essential for all the roles to be represented in it. However, in practice it is necessary for specific people to comply not only with certain personal and psychological requirements but also professional expertise and other requirements. Nevertheless, by the means of adding these parameters to specific people, an enormous number of possible alternatives of the resulting team, which may not be evaluated (easily and in the real time) using traditional methods, proves to come to existence. Therefore, the so-called genetic algorithms inspired by natural development processes originally described by J. G. Mendel and Ch. Darwin were selected for evaluation purposes. The genetic algorithms feature good solutions to the task to be resolved in a very short time while the task does not have to be based on exact specifications and therefore several solutions might exist. A Java application was created within the scope of the thesis; its core comprises a genetic algorithm and it was used for the purpose of modelling of specific teams. The results provided by the application were subsequently verified by the means of creation of teams used for completion of new tasks and monitoring their activities in practice. Furthermore, the model verification of teams previously created solely on the basis of experience of executives was performed and the respective results were compared.
|
|
|
Evolutionary Approach to Synthesis and Optimization of Ordinary and Polymorphic Circuits
Gajda, Zbyšek ; Schmidt, Jan (referee) ; Zelinka,, Ivan (referee) ; Sekanina, Lukáš (advisor)
Tato disertační práce se zabývá evolučním návrhem a optimalizací jak běžných, tak polymorfních digitálních obvodů. V práci jsou uvedena a vyhodnocena nová rozšíření kartézského genetického programování (Cartesian Genetic Programming, CGP), která umožňují zkrácení výpočetního času a získávání kompaktnějších obvodů. Další část práce se zaměřuje na nové metody syntézy polymorfních obvodů. Uvedené metody založené na polymorfních binárních rozhodovacích diagramech a polymorfním multiplexovaní rozšiřují běžné reprezentace digitálních obvodů, a to s ohledem na začlenění polymorfních hradel. Z důvodu snížení počtu hradel v obvodech syntetizovaných uvedenými metodami je provedena evoluční optimalizace založená na CGP. Implementované polymorfní obvody, které jsou optimalizovány s využitím CGP, reprezentují nejlepší známá řešení, jestliže je jako cílové kritérium brán počet hradel obvodu.
|
|
|
Security analysis of network traffic using behavioral signatures
Barabas, Maroš ; Hujňák,, Petr (referee) ; Zelinka,, Ivan (referee) ; Hanáček, Petr (advisor)
This thesis focuses on description of the current state of research in the detection of network attacks and subsequently on the improvement of detection capabilities of specific attacks by establishing a formal definition of network metrics. These metrics approximate the progress of network connection and create a signature, based on behavioral characteristics of the analyzed connection. The aim of this work is not the prevention of ongoing attacks, or the response to these attacks. The emphasis is on the analysis of connections to maximize information obtained and definition of the basis of detection system that can minimize the size of data collected from the network, leaving the most important information for subsequent analysis. The main goal of this work is to create the concept of the detection system by using defined metrics for reduction of the network traffic to signatures with an emphasis on the behavioral aspects of the communication. Another goal is to increase the autonomy of the detection system by developing an expert knowledge of honeypot system, with the condition of independence to the technological aspects of analyzed data (e.g. encryption, protocols used, technology and environment). Defining the concept of honeypot system's expert knowledge in the role of the teacher of classification algorithms creates autonomy of the~system for the detection of unknown attacks. This concept also provides the possibility of independent learning (with no human intervention) based on the knowledge collected from attacks on these systems. The thesis describes the process of creating laboratory environment and experiments with the defined network connection signature using collected data and downloaded test database. The results are compared with the state of the art of the network detection systems and the benefits of the proposed approximation methods are highlighted.
|
|
|
Acceleration Methods for Evolutionary Design of Digital Circuits
Vašíček, Zdeněk ; Miller, Julian (referee) ; Zelinka,, Ivan (referee) ; Sekanina, Lukáš (advisor)
Ačkoliv můžeme v literatuře nalézt řadu příkladů prezentujících evoluční návrh jakožto zajímavou a slibnou alternativu k tradičním návrhovým technikám používaným v oblasti číslicových obvodů, praktické nasazení je často problematické zejména v důsledku tzv. problému škálovatelnosti, který se projevuje např. tak, že evoluční algoritmus je schopen poskytovat uspokojivé výsledky pouze pro malé instance řešeného problému. Vážný problém představuje tzv. problém škálovatelnosti evaluace fitness funkce, který je markantní zejména v oblasti syntézy kombinačních obvodů, kde doba potřebná pro ohodnocení kandidátního řešení typicky roste exponenciálně se zvyšujícím se počtem primárních vstupů. Tato disertační práce se zabývá návrhem několika metod umožňujících redukovat problem škálovatelnosti evaluace v oblasti evolučního návrhu a optimalizace číslicových systémů. Cílem je pomocí několika případových studií ukázat, že s využitím vhodných akceleračních technik jsou evoluční techniky schopny automaticky navrhovat inovativní/kompetitivní řešení praktických problémů. Aby bylo možné redukovat problém škálovatelnosti v oblasti evolučního návrhu číslicových filtrů, byl navržen doménově specifický akcelerátor na bázi FPGA. Tato problematika reprezentuje případ, kdy je nutné ohodnotit velké množství trénovacích dat a současně provést mnoho generací. Pomocí navrženého akcelerátoru se podařilo objevit efektivní implementace různých nelineárních obrazových filtrů. S využitím evolučně navržených filtrů byl vytvořen robustní nelineární filtr implusního šumu, který je chráněn užitným vzorem. Navržený filtr vykazuje v porovnání s konvenčními řešeními vysokou kvalitu filtrace a nízkou implementační cenu. Spojením evolučního návrhu a technik známých z oblasti formální verifikace se podařilo vytvořit systém umožňující výrazně redukovat problém škálovatelnosti evoluční syntézy kombinačních obvodů na úrovni hradel. Navržená metoda dovoluje produkovat komplexní a přesto kvalitní řešení, která jsou schopna konkurovat komerčním nástrojům pro logickou syntézu. Navržený algoritmus byl experimentálně ověřen na sadě několika benchmarkových obvodů včetně tzv. obtížně syntetizovatelných obvodů, kde dosahoval v průměru o 25% lepších výsledků než dostupné akademické i komerční nástroje. Poslední doménou, kterou se práce zabývá, je akcelerace evolučního návrhu lineárních systémů. Na příkladu evolučního návrhu násobiček s vícenásobnými konstantními koeficienty bylo ukázáno, že čas potřebný k evaluaci kandidátního řešení lze výrazně redukovat (defacto na ohodocení jediného testovacího vektoru), je-li brán v potaz charakter řešeného problému (v tomto případě linearita).
|
|
|
Aerofoil Aerodynamic Features Optimization
Müller, Jan ; Rozehnal,, Dalibor (referee) ; Popela, Robert (referee) ; Zelinka, Ivan (referee) ; Ošmera, Pavel (advisor)
The content of the presented thesis is advanced optimization of the aerofoil wing of a general aircraft. Advanced metaheuristic optimization techniques based on evolutionary calculations and swarm algorithms are used for optimization. These algorithms are characterized by robustness of optimization and engineered degree of convergence and optimality of the solution. Within the solution, fundamental modifications of the original aerofoil optimizations were designed and implemented. A new variant of aerofoil evolutionary algorithms (aEA) was created from the original evolutionary algorithm (EA), followed by a new variant of aerofoil particle swarm optimization (aPSO) developed from the original particle swarm optimization (PSO). Then the hybridization of the mentioned methods was created in a parallel variant. The Bezier-PARSEC 3434 parameterization model that generates the aerofoil shape was used for the optimization process. A parametric model based on B-Spline was used to optimize the original aerofoil. Fluid dynamics simulation for the calculation of basic aerodynamic features (lift, drag, moment) was realized by Xfoil software. The results are then verified using fluid dynamics simulation (CFD ANSYS Fluent). From the point of view of optimization tasks developed by optimization and implementation, it is clear that this is a complex interdisciplinary task, the results of which are presented in this thesis.
|
|
|
Aerofoil Aerodynamic Features Optimization
Müller, Jan ; Popela, Robert (referee) ; Zelinka, Ivan (referee) ; Rozehnal,, Dalibor (referee) ; Ošmera, Pavel (advisor)
The content of the presented thesis is advanced optimization of the aerofoil wing of a general aircraft. Advanced metaheuristic optimization techniques based on evolutionary calculations and swarm algorithms are used for optimization. These algorithms are characterized by robustness of optimization and engineered degree of convergence and optimality of the solution. Within the solution, fundamental modifications of the original aerofoil optimizations were designed and implemented. A new variant of aerofoil evolutionary algorithms (aEA) was created from the original evolutionary algorithm (EA), followed by a new variant of aerofoil particle swarm optimization (aPSO) developed from the original particle swarm optimization (PSO). Then the hybridization of the mentioned methods was created in a parallel variant. The Bezier-PARSEC 3434 parameterization model that generates the aerofoil shape was used for the optimization process. A parametric model based on B-Spline was used to optimize the original aerofoil. Fluid dynamics simulation for the calculation of basic aerodynamic features (lift, drag, moment) was realized by Xfoil software. The results are then verified using fluid dynamics simulation (CFD ANSYS Fluent). From the point of view of optimization tasks developed by optimization and implementation, it is clear that this is a complex interdisciplinary task, the results of which are presented in this thesis.
|
|
|
Security analysis of network traffic using behavioral signatures
Barabas, Maroš ; Hujňák,, Petr (referee) ; Zelinka,, Ivan (referee) ; Hanáček, Petr (advisor)
This thesis focuses on description of the current state of research in the detection of network attacks and subsequently on the improvement of detection capabilities of specific attacks by establishing a formal definition of network metrics. These metrics approximate the progress of network connection and create a signature, based on behavioral characteristics of the analyzed connection. The aim of this work is not the prevention of ongoing attacks, or the response to these attacks. The emphasis is on the analysis of connections to maximize information obtained and definition of the basis of detection system that can minimize the size of data collected from the network, leaving the most important information for subsequent analysis. The main goal of this work is to create the concept of the detection system by using defined metrics for reduction of the network traffic to signatures with an emphasis on the behavioral aspects of the communication. Another goal is to increase the autonomy of the detection system by developing an expert knowledge of honeypot system, with the condition of independence to the technological aspects of analyzed data (e.g. encryption, protocols used, technology and environment). Defining the concept of honeypot system's expert knowledge in the role of the teacher of classification algorithms creates autonomy of the~system for the detection of unknown attacks. This concept also provides the possibility of independent learning (with no human intervention) based on the knowledge collected from attacks on these systems. The thesis describes the process of creating laboratory environment and experiments with the defined network connection signature using collected data and downloaded test database. The results are compared with the state of the art of the network detection systems and the benefits of the proposed approximation methods are highlighted.
|
guest ::
RSS feed.