|
|
Character recognition in the soundtrack with SOM
Malásek, Jan ; Honzík, Petr (referee) ; Honzík, Petr (referee) ; Pohl, Jan (advisor)
This bachelor´s thesis describes a history of neural networks evolution and their using in speech recognition systems and shows problems with working and learning neural networks. It presents three chosen systems for speech recognition including their evaluation in experiments, their advantages and disadvantages. It is also about human speech characteristics and systems of its recognition. The last part is focused on frequency spectrums of different types of vowels and gives instructions for programming neural networks using MATLAB.
|
|
|
Service unit for BUSE devices with remote management
Musil, Roman ; Sýkora, Tomáš (referee) ; Bradáč, Zdeněk (advisor)
The aim of this thesis is to create compact device which allows remote management of low-level devices of public transport information system. The thesis first deals introduction to the issues of the information system as a whole and its requisites. After that the thesis analysis the hardware of the existing board computer which the design was based. The next points od this thesis are focused to design and create software for upgrade firmware of information panels created by BUSE company and also for design and create system for remote managment. The conclusion summarizes obtained information and the results achieved.
|
|
|
Use of neural networks in classification of heart diseases
Skřížala, Martin ; Tannenberg, Milan (referee) ; Hrubeš, Jan (advisor)
This thesis discusses the design and the utilization of the artificial neural networks as ECG classifiers and the detectors of heart diseases in ECG signal especially myocardial ischaemia. The changes of ST-T complexes are the important indicator of ischaemia in ECG signal. Different types of ischaemia are expressed particularly by depression or elevation of ST segments and changes of T wave. The first part of this thesis is orientated towards the theoretical knowledges and describes changes in the ECG signal rising close to different types of ischaemia. The second part deals with to the ECG signal pre-processing for the classification by neural network, filtration, QRS detection, ST-T detection, principal component analysis. In the last part there is described design of detector of myocardial ischaemia based on artificial neural networks with utilisation of two types of neural networks back – propagation and self-organizing map and the results of used algorithms. The appendix contains detailed description of each neural networks, description of the programme for classification of ECG signals by ANN and description of functions of programme. The programme was developed in Matlab R2007b.
|
|
| |
|
|
Kohonen network
Kaňa, Michal ; Hynčica, Tomáš (referee) ; Jirsík, Václav (advisor)
The problems with artificial neuron systems, or, more precisely, with self-organising neuron systems and their usage, have been concisely described in this Bachelor's thesis. The thesis is more deeply concerned with the Kohonen self-organising system and describes the principle of its study and programmes for its simulation. The practical part of the thesis concerns the problem of regulating initial neuron weights in the Kohonen system and their effect upon the final position of the surviving neuron. This effect is demonstrated in the selected experiment set with the help of the programme MATLAB.
|
|
|
Kohonen network
Fic, Miloslav ; Hynčica, Tomáš (referee) ; Jirsík, Václav (advisor)
This Bachelor’s thesis deals with self-organizing networks and its learning mechanism. The activation, adaptation and application of Kohonen network are discussed in this thesis. The program Kohonen neural network is described. The practical part of this work analyzes effect of learning parameters choice on final state of Kohonen network and how do this learning parameters affect learning process. The effect of weight vector initialization on the final best-matching neuron “position” is analyzed.
|
|
|
Neural Network Based Image Segmentation
Jamborová, Soňa ; Řezníček, Ivo (referee) ; Žák, Pavel (advisor)
This work is about suggestion of the software for neural network based image segmentation. It defines basic terms for this topics. It is focusing mainly at preperation imaging information for image segmentation using neural network. It describes and compares different aproaches for image segmentation.
|
|
|
Combination of laser spectroscopy methods for chemical analysis
Holub, Daniel ; Novotný, Karel (referee) ; Pořízka, Pavel (advisor)
The topic of this Master’s thesis is combination of laser spectroscopic methods. LIBS and Raman spectroscopy were chosen for the combination. This combination is applied to plastic identification and separation as a mean to automate sorting of plastic waste. Data handling was done via different methods of computer learning algorithms scripted in R language. Plastic sorting accuracy over 90 % was reached thanks to the combination of chosen methods. This work also addresses some issues implied by combination of two different methods.
|
|
|
Service unit for BUSE devices with remote management
Musil, Roman ; Sýkora, Tomáš (referee) ; Bradáč, Zdeněk (advisor)
The aim of this thesis is to create compact device which allows remote management of low-level devices of public transport information system. The thesis first deals introduction to the issues of the information system as a whole and its requisites. After that the thesis analysis the hardware of the existing board computer which the design was based. The next points od this thesis are focused to design and create software for upgrade firmware of information panels created by BUSE company and also for design and create system for remote managment. The conclusion summarizes obtained information and the results achieved.
|
|
|
Combination of laser spectroscopy methods for chemical analysis
Holub, Daniel ; Novotný, Karel (referee) ; Pořízka, Pavel (advisor)
The topic of this Master’s thesis is combination of laser spectroscopic methods. LIBS and Raman spectroscopy were chosen for the combination. This combination is applied to plastic identification and separation as a mean to automate sorting of plastic waste. Data handling was done via different methods of computer learning algorithms scripted in R language. Plastic sorting accuracy over 90 % was reached thanks to the combination of chosen methods. This work also addresses some issues implied by combination of two different methods.
|
guest ::
