National Repository of Grey Literature 13 records found  1 - 10next  jump to record: Search took 0.00 seconds. 
Multilingual analysis of human emotional states
Rendek, Tomáš ; Koula, Ivan (referee) ; Atassi, Hicham (advisor)
This work deals with the properties of the speech signal. At the beginning it introduces a process of generation of the speech. Then, it covers the prosodic features of the speech, which represent a related characteristic of emotions. It defines an emotion itself, as well as the basic features and parameters of the human speech. For the analysis we use the program called Praat. As it is an unknown program, we devote a part of the work to it, which acquaints us with its advantages. The next part of this paper comprises also two enclosed databases containing records of particular emotional states of human. These databases were created and collected for Slovak and German language. However, none of them contain spontaneous material. Next, the work concerns a concept of the neural networks. It regards it as a possible realization of recognizing of emotional characteristics. The initial analysis presents large number of gained features, out of which only the best twelve were selected on the basis of geometric separability. These features are distinct for both sexes, as well as for both nationalities. Consequently, they are used for training with a neural network. The work concludes by summarizing of the results discussing the successfulness with recognition of emotional states. It also gives possible reasons which lead to degradation of their successful classifying. The thesis contains a CD with all the partial and ultimate results, and files with records for Slovak and German language.
Application of neural networks in telecommunications
Šulák, Michal ; Koula, Ivan (referee) ; Kacálek, Jan (advisor)
This Master’s Thesis consists of description of current routing protocols and routers, basic principles of neural networks and their interpretation in connection with the use for routing in data networks and telecommunications networks. In the thesis I focused on neural networks, which use energetic functions to find solution stabled states and their use for data routing. I produced the application software to test and find suitable variables for each function. This application counts the shortest path and is able to change variables to reach the best solution of stabled state of neural network. These solutions are compared with other functions that are usually used in nowadays systems for data network routing.
Design of programmable control system
Trpiš, Michal ; Říha, Kamil (referee) ; Koula, Ivan (advisor)
The goal of diploma thesis is design of programmable control system. This system can be used for regulation of basic parameters in an aquarium. Primary parameters for selection of this device are the price and the easy realization of final device. In first step there are selected parameters, which are needed to control. In second step there is described which kind of sensors can be used for measuring of selected parameters and suitable regulation of necessary parameters. The device is supposed to communicate with PC by USB and this communication is going to be compatible with an old RS-232. Device must be completed with hardware design. Device will be in principle system with real time, that is the reason why device will contain microcomputer. A microcomputer must communicate with other integrated circuit in the device and it supposes to communicate with PC. In specific chapter it will be described, how many different kinds of communication it is possible. For microcontroller it is necessary to create a program, which can figure the measured parameters and it also allows setting up the way how parameters can be regulated. Measured parameters are supposed to storage in the specific memory for the later interpretation. The completely device must be put into a case, which is calculating with a damp place. There must be created a host application for PC. This application suppose to detect if device is connected, figure measured parameters and also allows to set up the way, how to regulate the parameters and display the storages parameters. The application is suppose to run on the operation system created by Microsoft (Windows XP and Windows Vista or later). Diploma thesis contains a problem of the analysis which parameters may be controlled and the way how it can be controlled. There will be selected the sensors, which are suppose to measure and there will be described the basic data transfer and the specifications. It will also contain description of the hardware and software implementation of the device and possibilities of the user’s settings. There will be described the host application and its possibilities. Finally there will be described a functionality of the device and the host application. It will be also imagined some system upgrades for future.
Adaptive data compression by neural networks
Kučera, Michal ; Přinosil, Jiří (referee) ; Koula, Ivan (advisor)
Point of the work is using of neural networks for the datecompression. This brings new possibilities as by lossless as lossy compression. Draft of a few compress algorithm show the behaviour, advantages and weak points of these systems. As the solution we use knowledge of the layered perceptron Network and we try by the change of the structure and subparameters to teach such network to compress the data, according to our entry requirement. These networks have also advantages, which are meanwhile impediment to the using practically. The goal of this is to try some algorithms, look into their characteristics and posibility of the using. Then propose next posibility solutions and upgrading of these algorithms.
Multilingual analysis of human emotional states
Rendek, Tomáš ; Koula, Ivan (referee) ; Atassi, Hicham (advisor)
This work deals with the properties of the speech signal. At the beginning it introduces a process of generation of the speech. Then, it covers the prosodic features of the speech, which represent a related characteristic of emotions. It defines an emotion itself, as well as the basic features and parameters of the human speech. For the analysis we use the program called Praat. As it is an unknown program, we devote a part of the work to it, which acquaints us with its advantages. The next part of this paper comprises also two enclosed databases containing records of particular emotional states of human. These databases were created and collected for Slovak and German language. However, none of them contain spontaneous material. Next, the work concerns a concept of the neural networks. It regards it as a possible realization of recognizing of emotional characteristics. The initial analysis presents large number of gained features, out of which only the best twelve were selected on the basis of geometric separability. These features are distinct for both sexes, as well as for both nationalities. Consequently, they are used for training with a neural network. The work concludes by summarizing of the results discussing the successfulness with recognition of emotional states. It also gives possible reasons which lead to degradation of their successful classifying. The thesis contains a CD with all the partial and ultimate results, and files with records for Slovak and German language.
Adaptive data compression by neural networks
Kučera, Michal ; Přinosil, Jiří (referee) ; Koula, Ivan (advisor)
Point of the work is using of neural networks for the datecompression. This brings new possibilities as by lossless as lossy compression. Draft of a few compress algorithm show the behaviour, advantages and weak points of these systems. As the solution we use knowledge of the layered perceptron Network and we try by the change of the structure and subparameters to teach such network to compress the data, according to our entry requirement. These networks have also advantages, which are meanwhile impediment to the using practically. The goal of this is to try some algorithms, look into their characteristics and posibility of the using. Then propose next posibility solutions and upgrading of these algorithms.
Application of neural networks in telecommunications
Šulák, Michal ; Koula, Ivan (referee) ; Kacálek, Jan (advisor)
This Master’s Thesis consists of description of current routing protocols and routers, basic principles of neural networks and their interpretation in connection with the use for routing in data networks and telecommunications networks. In the thesis I focused on neural networks, which use energetic functions to find solution stabled states and their use for data routing. I produced the application software to test and find suitable variables for each function. This application counts the shortest path and is able to change variables to reach the best solution of stabled state of neural network. These solutions are compared with other functions that are usually used in nowadays systems for data network routing.
Design of programmable control system
Trpiš, Michal ; Říha, Kamil (referee) ; Koula, Ivan (advisor)
The goal of diploma thesis is design of programmable control system. This system can be used for regulation of basic parameters in an aquarium. Primary parameters for selection of this device are the price and the easy realization of final device. In first step there are selected parameters, which are needed to control. In second step there is described which kind of sensors can be used for measuring of selected parameters and suitable regulation of necessary parameters. The device is supposed to communicate with PC by USB and this communication is going to be compatible with an old RS-232. Device must be completed with hardware design. Device will be in principle system with real time, that is the reason why device will contain microcomputer. A microcomputer must communicate with other integrated circuit in the device and it supposes to communicate with PC. In specific chapter it will be described, how many different kinds of communication it is possible. For microcontroller it is necessary to create a program, which can figure the measured parameters and it also allows setting up the way how parameters can be regulated. Measured parameters are supposed to storage in the specific memory for the later interpretation. The completely device must be put into a case, which is calculating with a damp place. There must be created a host application for PC. This application suppose to detect if device is connected, figure measured parameters and also allows to set up the way, how to regulate the parameters and display the storages parameters. The application is suppose to run on the operation system created by Microsoft (Windows XP and Windows Vista or later). Diploma thesis contains a problem of the analysis which parameters may be controlled and the way how it can be controlled. There will be selected the sensors, which are suppose to measure and there will be described the basic data transfer and the specifications. It will also contain description of the hardware and software implementation of the device and possibilities of the user’s settings. There will be described the host application and its possibilities. Finally there will be described a functionality of the device and the host application. It will be also imagined some system upgrades for future.
Objektivní porovnání účinnosti jednokanálových metod potlačení šumu
Koula, Ivan ; Heralt, J.
The contribution tries to evaluate objectively the efficiency of most widely used one-channel noise cancellation methods for a speech record. In this contribution three basic one-channel methods are compared (spectral thresholding, spectral subtraction and RASTA algorithm). The efficiency of designated methods is evaluated by percentage hit rate of isolated words recognition. This test enables an objective evaluation of methods with regard to the intelligibility.
Wavelet transform properties
Koula, Ivan
Multidimensional time-scale representations of signals are images of changes in time of short time sub band energy and thus play an important role when they are analyzed and processed. The properties depend on the transformation algorithm used, and they differ not only in the resolution of changes in the time and the scale domain but also in the computation complexity during the realization.

National Repository of Grey Literature : 13 records found   1 - 10next  jump to record:
See also: similar author names
3 Koula, Ivo
Interested in being notified about new results for this query?
Subscribe to the RSS feed.