|
|
Using Neural Networks in the Hierachical Routing
Straka, Martin ; Lokoč, Jakub (referee) ; Štanclová, Jana (advisor)
The objective of the diploma thesis is to show possible utilization of the neural networks for the partitioning needs of the hierarchical routing algorithm. The work proposes a hierarchical approach, which can be useful for the optimal path searching process. We focus on the application of several neural network models to extract hierarchical information from the transportation network data. Introduced models are based on the energy minimization principle and we demonstrate an employment of the deterministic annealing methods (MFA) as quite ambitious in the partitioning process. The experimental part of this work makes use of our findings and propose several suggestions on the proper parametrization of employed neural network models. In the experimental tests, we demonstrate capabilities of the MFA to provide a partitioning task also in case of lack of the global information.
|
|
|
Hand Recognition
Malovec, Róbert ; Hoksza, David (referee) ; Štanclová, Jana (advisor)
The research object of this diploma thesis is hand recognition problematics. The first part of this work is dedicated to palm photograph processing and extraction of characteristic features. Extracted features are used as inputs of investigated classification methods. The second part of this work provides detailed description of explored methods and their modifications, which are the research objects. Diploma thesis includes description and experimental results of minimum distance classifier, Bayes naive classifier and method based on neural networks. The aim of this work is the comparison of the particular methods with respect to classification success and time needed for classifier construction and classification of all available patterns. The main approach is to choose the best method, which solves the problem of hand recognition according to our experimental results.
|
|
|
Associative recall of damaged data
Lukešová, Jana ; Mrázová, Iveta (referee) ; Štanclová, Jana (advisor)
The focus of this work are asociative memories as one type of neural networks. We compare models of asociative memories with respect to recall of damaged spatial patterns. We deal with three types of asociative memories: Hopeld network know also as standard associative memory, hierarchical associative memory and cascade associative memory. Based on dened comparison criteria, we test the models on test data. Comparison and evaluation of the models based on test results concludes our work.
|
|
|
Multilayer hierarchical models
Béger, Michal ; Petříčková, Zuzana (referee) ; Štanclová, Jana (advisor)
This diploma thesis deals with hierarchical associative memories (HAM), which have been experimentally analysed only in the case of two layer hierarchy so far. The aim of this thesis is to study existing hierarchical models and evaluate experimentally their performance for more than two layer hierarchy. We show, that existing hierarchical model HAM is not suitable for three or more layer hierarchy. For that reason, we propose a new version of hierarchical model (called HAM-N), which enables utilization of any number of layers. The new model HAM-N uses the structure of the HAM model. However, due to modied learning and recall process, the HAM-N model eliminates the above-mentioned drawbacks of the HAM model. Finally, the HAM-N model is experimentally studied with respect to processing of large amounts of correlated patterns. Thesis also includes analysis of experiment results.
|
|
|
Multilayer Perceptron Learning
Brambora, Tomáš ; Štanclová, Jana (referee) ; Rydvan, Pavel (advisor)
Multilayer perceptron networks are interesting alternative to the classical von neuman computational models. This thesis summarizes theoretical basis of their learning and describes the implemenatation of a multilayer pereptron network, designed as an agent for multiagent system BANG3. At the end of the thesis, we summarize the results of testing the implemented multilayer perceptron network on two data sets using different learning algorithms with various parameter configurations.
|
|
|
Scrabble
Cipra, Jan ; Obdržálek, David (referee) ; Štanclová, Jana (advisor)
The aim of this work is to examine and implement algotithms and data structures suitable for Scrabble game. The most important data structure is the lexikon of legal words. The program allows human players to play against each oder or computer controlled players. Moreover, the players can play over network.
|
|
|
Voice chat
Novák, Hynek ; Bednárek, David (referee) ; Štanclová, Jana (advisor)
VoiceChat is program intended for voice and chat communication between several computers with the Windows operating system. Command and chat messages are sent over the network using TCP protocol. Voice is captured and played by DirectSound and transferred with UDP protocol. GSM 6.10 codec is used to lower data transfer rate.
|
|
|
Single-Image License Plate Recognition
Vala, Tomáš ; Winkler, Zbyněk (referee) ; Štanclová, Jana (advisor)
The diploma thesis deals with analysis and design of an automatic system for a single-image license plate (LP) recognition. Input data came from a system for car speed measurement on the roads in the emirate of Abu Dhabi (the United Arab Emirates). A goal is to recognize a numeric identi cation code on a LP and a type of the LP. In details there are discussed individual parts of the system for LP recognition. A particular stress is put on segmentation and grouping of individual characters to be able to utilize specific information on the LP from Abu Dhabi during the character recognition. The diploma thesis compares several methods for character recognition - a minimum distance classi er, feed-forward neural networks and hidden Markov models. The methods (and some modifications of them) are tested on real data and compared according to the percentage of correctly recognized digits (at fi rst the digits were manually classi ffied). Wrongly recognized LPs are undesirable. Instead in some cases it is better to mark the LP as "unrecognized". That's why there were introduced sophisticated tests for recognized digits reliability veri cation. A summary of our own results is included.
|
|
|
Feed-forward neural networks and their application in data mining
Civín, Lukáš ; Štanclová, Jana (referee) ; Mrázová, Iveta (advisor)
The goal of data mining is to solve various problems dealing with knowledge extraction from huge amounts of real-world data, the quality of which might be disputable. Neural networks can help with the solution due to their generalization capabilities. While working on data mining projects, we have essentially the following two objectives in real-world applications of feed-forward neural networks. To obtain applicable results, it is crucial to provide the networks with well-prepared data. However, it is equally important to choose the right training strategy for the networks themselves - including network architecture, parameter settings or the training algorithm. One of the most important ideas behind these steps is namely to prevent "over-training". The final network should recall unknown examples as well as possible. There are plenty of techniques with different approaches to the solution. It is possible to modify the data, these comprises modifying the range of the data or its dimension, adding noise to the data, etc. Yet another way is the modification of the neural network by structural learning with forgetting, weight decay or early stopping. These techniques are analyzes both theoretically and experimentally in this thesis. With regard to the results achieved in a number of experimental tests we have...
|
|
|
FTP server
Tekeľ, Michal ; Holub, Viliam (referee) ; Štanclová, Jana (advisor)
This work deals with implementation of an effective FTP server and programs needed for its administration, which are also part of the work. Important factor is performance of the server alone and ability to fully utilize system resources when needed. Server should support all common FTP commands, ocassionaly used commands can be implemented using plugins. Communication protocol between server and administrative programs is also part of this work. This protocol permits use of third party programs for server management too.
|
guest ::
