|
|
Image Compression Based on Artificial Neural Network
Vondráček, Jiří ; Pohl, Jan (referee) ; Jirsík, Václav (advisor)
The thesis is focused on the image compression based on artificial neural network with practical implementation. The objective of this thesis is to explore possibilities of an image compression by artificial neural network and analyze results. In the theoretical part of the work, the fundamentals of artificial neural network are described and basic image compression techniques are explained. In the practical part there is a brief description of the compression program, the comparison of different settings and result evaluation.
|
|
|
Analysis of Human Signature Based on Artificial Neural Network
Ševčík, Pavel ; Horák, Karel (referee) ; Pohl, Jan (advisor)
This bachelor thesis deals with methods of human signature and its analysis in practical service of artificial neural network. Actual processing and analysis of human signature consist in few steps. First of all, the signature pattern is digitized and processed with the assistance of preprocessing and segmentation methods. Afterwards, the object of human signature pattern is described with the assistance of centric geometric moments and moments invariant characteristics. Finally, the pattern is classified by multilayer perceptron, whose outputs determine the person, to that signature belongs to.
|
|
| |
|
|
Artificial neural network for modeling electromagnetic fields in a car
Kostka, Filip ; Škvor, Zbyněk (referee) ; Raida, Zbyněk (advisor)
The project deals with artificial neural networks. After designing and debugging the test data set and the training sample set, we created a multilayer perceptron network in the Neural NetworkToolbox (NNT) of Matlab. When creating networks, we used different training algorithms and algorithms improving the generalization of the network. When creating a radial basis network, we did not use the NNT, but a specific source code in Matlab was written. Functionality of neural networks was tested on simple training and testing patterns. Realistic training data were obtained by the simulation of twelve monoconic antennas operating in the frequency range from 2 to 6 GHz. Antennas were located inside a mathematical model of Octavia II. Using CST simulations, electromagnetic fields in a car were obtained. Trained networks are described by regressive characteristics andthe mean square error of training. Algorithms improving generalization are applied on the created and trained networks. The performance of individual networks is mutually compared.
|
|
|
Use of higher-order cumulants for heart beat classification
Dvořáček, Jiří ; Kolářová, Jana (referee) ; Ronzhina, Marina (advisor)
This master‘s thesis deals with the use of higher order cumulants for classification of cardiac cycles. Second-, third-, and fourth-order cumulants were calculated from ECG recorded in isolated rabbit hearts during experiments with repeated ischemia. Cumulants properties useful for the subsequent classification were verified on ECG segments from control and ischemic group. The results were statistically analyzed. Cumulants are then used as feature vectors for classification of ECG segments by means of artificial neural network.
|
|
|
Network Element with Advanced Control
Zedníček, Petr ; Kacálek, Jan (referee) ; Škorpil, Vladislav (advisor)
The diploma thesis deal with finding and testing neural networks, whose characteristics and parameters suitable for the active management of network element. Solves optimization task priority switching of data units from input to output. Work is focused largely on the use of Hopfield and Kohonen networks and their optimization. Result of this work are two models. The first theory is solved in Matlab, where each comparing the theoretical results of neural networks. The second model is a realistic model of the active element designed in Simulink
|
|
|
Design of algorithms for neural networks controlling a network element
Stískal, Břetislav ; Kacálek, Jan (referee) ; Škorpil, Vladislav (advisor)
This diploma thesis is devided into theoretic and practice parts. Theoretic part contains basic information about history and development of Artificial Neural Networks (ANN) from last century till present. Prove of the theoretic section is discussed in the practice part, for example learning, training each types of topology of artificial neural networks on some specifics works. Simulation of this networks and then describing results. Aim of thesis is simulation of the active networks element controlling by artificial neural networks. It means learning, training and simulation of designed neural network. This section contains algorithm of ports switching by address with Hopfield's networks, which used solution of typical Trade Salesman Problem (TSP). Next point is to sketch problems with optimalization and their solutions. Hopfield's topology is compared with Recurrent topology of neural networks (Elman's and Layer Recurrent's topology) their main differents, their advantages and disadvantages and supposed their solution of optimalization in controlling of network's switch. From thesis experience is introduced solution with controll function of ANN in active networks elements in the future.
|
|
|
Modelling and simulation in the field of waste management
Pařízková, Iva ; Popela, Pavel (referee) ; Touš, Michal (advisor)
This bachelor thesis is focused on the application of multilayer perceptron net for modelling the technolgical units of waste-to-energy facility ZEVO Malesice. It was specifically created to model the amount of steam generated in steam-boilers and to quantify the consumpion of steam by an external subject. Firstly, the basics of neuron theory are presented. In the following, a Statistica artificial neural network module is described. This module was used to develop the neural network models. The models appearing in practical section were created with the use of STATISTICA software. Last chapter deals with detailed description of the developed models and their comparison with simple linear and nonlinear regression models. Last but not least, the description of a software providing easy implementation of neural network models into Visual Basic for Application programming language is presented.
|
|
|
An efficiency comparison of simulation methods for artificial neural network training and inverse analysis
Nezval, Michal ; Novák, Drahomír (referee) ; Lehký, David (advisor)
The thesis deals with inverse analysis which is based on combination of artificial neural network and stochastic methods. The goal is to compare an efficiency of new simulation method Hierarchical Subset Latin Hypercube Sampling to classical Monte Carlo method and standard Latin Hypercube Sampling method used for neural network training. The efficiency is compared for a different neural network structures. The inverse analysis is then applied for engineering tasks – identification of limit state fiction parameters related to pitched-roof frame and material parameters of concrete specimen subjected to three-point bending. Finally an efficiency of Hierarchical Subset Latin Hypercube method comparing to Monte Carlo and Latin Hypercube Sampling methods is discussed.
|
|
|
Artificial neural networks for learning robots
Sovka, Michal ; Jirků, Petr (advisor) ; Berka, Petr (referee)
The main aim of this bachelor thesis is to understand, describe and explain the basic principles and elements used in learning robots with using artificial neural networks. Firstly, I focus on robots in general and their basic functional units. Then it is to introduce the theory of learning applied to real environments. Nervous system in this work becomes a central learning muse about theory with using artificial neural networks. It's very important in understanding of artificial neurons and artificial neural networks as a complex I consider the biological neuron and its synapses. That's why I take them very seriously. After introduction to artificial neural networks I attend to only the one of their group fully used in robotics. Finally, I demonstrate the function of Kohonen type of artificial neural network used in robotics and scilicet in the application developed in one of a foreign university workplace.I hope the benefits of my work is in a comprehensive text focused on the basic elements of robotics, as well as artificial neural networks and their neurobiological assumption. The work can then be used in studying for people interested in a broader approach to intelligent robotics.
|
guest ::
