|
Nonlinear Control of Complex Systems by Utilization of Evolutionary Approaches
Minář, Petr ; Ošmera, Pavel (referee) ; Oplatková,, Zuzana Komínková (referee) ; Matoušek, Radomil (advisor)
Control theory of complex systems by utilization of artificial intelligent algorithms is relatively new science field and it can be used in many areas of technical practise. Best known algorithms to solved similar tasks are genetic algorithm, differential evolution, HC12 Nelder-Mead method, fuzzy logic and grammatical evolution. Complex solution is presented at selected examples from mathematical nonlinear systems to examples of anthems design and stabilization of deterministic chaos. The goal of this thesis is present examples of implementation and utilization of artificial algorithms by multi-objective optimization. To achieve optimal results is used designed software solution by multi-platform application, which used Matlab and Java interfaces. The software solution integrate every algorithms of this thesis to complex solution and it extends possible application of those approaches to real systems and practical world.
|
|
Nonlinear Control of Complex Systems by utilization of Evolutionary Approaches
Minář, Petr ; Matoušek, Radomil (advisor)
Control theory of complex systems by utilization of artificial intelligent algorithms is relatively new science field and it can be used in many areas of technical practise. Best known algorithms to solved similar tasks are genetic algorithm, differential evolution, HC12 Nelder-Mead method, fuzzy logic and grammatical evolution. Complex solution is presented at selected examples from mathematical nonlinear systems to examples of anthems design and stabilization of deterministic chaos. The goal of this thesis is present examples of implementation and utilization of artificial algorithms by multi-objective optimization. To achieve optimal results is used designed software solution by multi-platform application, which used Matlab and Java interfaces. The software solution integrate every algorithms of this thesis to complex solution and it extends possible application of those approaches to real systems and practical world.
|
|
Parallel Deep Learning
Šlampa, Ondřej ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
Aim of this thesis is to propose how to evaluate favourableness of parallel deep learning. In this thesis I analyze parallel deep learning and I focus on its length. I take into account gradient computation length and weight transportation length. Result of this thesis is proposal of equations, which can estimate the speedup on multiple workers. These equations can be used to determine ideal number of workers for training.
|
|
Constructive Neural Networks
Černík, Tomáš ; Dalecký, Štěpán (referee) ; Zbořil, František (advisor)
Master theses deals with Constructive Neural newtorks. First part describes neural networks and coresponding mathematical models. Furher, it shows basic algorithms for learning neural networks and desribes basic constructive algotithms and their modifications. The second part deals with implementation details of selected algorithms and provides their comparision. Further comparision with backpropagation algorithm is provided.
|
|
The Utilization of Soft Computing in Ordering Cycle Management
Šustrová, Tereza ; Fecenko, Josef (referee) ; Jurová, Marie (referee) ; Marček, Dušan (referee) ; Dostál, Petr (advisor)
This doctoral thesis deals with possibilities of using advanced methods of decision-making - Soft Computing, in company’s ordering cycle management. The main aim of the thesis is to propose an artificial neural network model with an optimal architecture for ordering cycle management within the supply chain management. The proposed model will be employed in an organization involved in retailing to ensure smooth material flow. A design and verification of artificial neural networks model for sales prediction is also part of this doctoral thesis as well as a comparison of results and usability with standard and commonly used statistical methods. Furthermore, the thesis deals with finding a suitable artificial neural network model with architecture capable of solving the lot-size problem according to specified inputs. Methods of statistical data processing, economical modelling and advanced decision-making (Soft Computing) were utilized during the model designing process.
|
| |
|
Using Softcomputing Techniques for User Behavior Prediction and Analysis
Šimon, Jakub ; Sopuch, Zbyněk (referee) ; Minařík, Miloš (advisor)
This Bachelor's thesis studies the possibilities of employee's behavior prediction and analysis. It uses softcomputing techniques, two types of neural networks - Multi-layer feedforward neural network with the Backpropagation algorithm, and Kohonen selforganizing map. The experiments performed on real activity records of employees are included. Part of the thesis is focused on activity records data and their characteristics. As a conclusion some basic information about the pros and cons of neural networks' use in the field of employee behavior prediction and analysis is given.
|
|
Artificial Intelligence in Power Oil Transformers Diagnostics
Janda, Ondřej ; Szabó,, Radek (referee) ; Kratochvíl, Petr (referee) ; Hammer, Miloš (advisor)
This dissertation thesis deals with the application of expert systems and soft computing methods in field of power oil transformers. The main work is divided into theoretical and practical part. First, the theoretical part presents the basic elements of the transformer, and approaches to its diagnosis. The work focused mainly on the diagnostics of the insulation system, and diagnostic methods and approaches in this specific area. Next part describes the basics of expert systems and other soft computing methods such as: fuzzy logic, neural networks, genetic algorithms and their combinations and extensions. At the end of the theoretical part, the possibility of optimization approaches by means of artificial intelligence and its application in fuzzy model optimization are described. The practical part begins with description of the used data file that runs through the entire work. The work is then divided into four parts, namely in parts which deal with the expert system for transformer diagnostics, DGA module, prediction module, and optimization using artificial intelligence. The section describing the expert system gives specific information about the particular expert system. The means and techniques used for constructing given system are described, and then the complete system design and description of all subsystems and modules are presented. The next section describes the developed DGA module and all selected approaches to its implementation and expansion. At the end of the chapter, the results of comparison between all implemented methods are evaluated. The third part deals with the prediction module and describes its design and construction, including description of the main parts which are based on the selected predictive approaches. Also, the predictions of selected quantities from the data file are included. There are two predictive approaches being used: the one step prediction, and the multiple step prediction. The comparison of prediction accuracy and computational cost of given methods is presented at the end of this chapter. The last part deals with the possibilities of optimization using artificial intelligence methods, namely differential evolution, PSO, and genetic algorithms. Both the single-objective and the multi-objective optimization are considered. The methods are compared in a series of synthetic tests and then applied to optimize the fuzzy models of DGA tests from an earlier part of this work. The dissertation also includes chapters: "The Aims", "The Contribution of the Work", and a list of publications, products, and projects of the author.
|
| |
| |