|
|
Speaker Segmentation using statistical methods of classification
Adamský, Aleš ; Přinosil, Jiří (referee) ; Smékal, Zdeněk (advisor)
The thesis discusses in detail some concepts of speech and prosody that can contribute to build a speech corpus for the speaker segmentation purpose. Moreover, the Elan multimedia annotator used for labeling is described. The theoretical part highlights some frequently used speech features such as MFCC, PLP and LPC and deals with currently most popular speech segmentation methods. Some classification algorithms are also mentioned. The practical part describes implementation of Bayesian information criterium algorithm in system for automatic speaker segmentation. For classification of speaker change point in speech, were used different speech features. The results of tests were evaluated by the graphic method of receiver operating characteristic (ROC) and his quantitative indices. As the best speech features for this system were provided MFCC and HFCC.
|
|
|
Human activity classification
Müller, Jakub ; Smital, Lukáš (referee) ; Smíšek, Radovan (advisor)
This bachelor's thesis describes daily activity classification using accelerometric data. The first theoretical part summarizes the basics about daily activity and benefits that we get from monitoring it. In the next part of theory the principles of accelerometer inner workings are described. The last part of theory is dedicated to explaining the basics of neural networks and SVM. The aim of the practical part was to find a suitable dataset from a publicaly shared database, containing daily activity accelerometric data and also to collect our own data. Then performing classification using our own algorithm, optimizing it and finally evaluating the results.
|
|
|
Comparison of analysis of speech in dependence on age and gender
Báňa, Josef ; Smékal, Zdeněk (referee) ; Atassi, Hicham (advisor)
This thesis deals with analysis of speech signal in dependence on the gender and the age of the speaker. We tried to investigate through the features to find the best set for the automatic classification of speakers. It also contains a brief discussion about the speech signal and its characteristics. We used a program called Praat for the speech analysis purpose. This program is also described in this work. We mainly focused on the suprasegmental features of speech. Our first step was to make our own speech corpus which should contain speech records from speakers with various age and gender. We made the analysis using Praat and reported it within this thesis. For the automatic classification purpose, twelve features were selected basing on there quality criteria and used with a neural network to classify the speakers to classes with different age and gender. As it was mentioned, a neural network was used as a classifier. We used “Neural Network Toolbox” in the Matlab program to create and train our networks.
|
|
| |
|
|
Anatomy based landmark detection in brain CT scans
Krajčiová, Alexandra ; Harabiš, Vratislav (referee) ; Jakubíček, Roman (advisor)
Manual detection of anatomical landmarks from head CT (Computed Tomography) scans is time-consuming task prone to observer errors. In addition, the accuracy of the detection correlates with image quality. The aim of this work is to create an algorithm that will perform automatic detection of anatomical landmarks. These landmarks can be later used to form radiological lines, which finds its application in CT scanning. SVM (Support Vector Machines) and HOG (Histograms of Oriented Gradients) features was chosen for anatomical landmark detection. The achieved results, possibilities of further progress and improvement of detection are summarized in the conclusion.
|
|
|
Application of Algorithms of Predictive Maintanence for RUL Estimation
Dvořák, Jan ; Brablc, Martin (referee) ; Dobossy, Barnabás (advisor)
The aim of this thesis is to acquaint the reader with the areas of predictive maintenance and its algorithms within its prognostic part. The remaining useful life of the system will be determined on the data sets and the performed experiment using prognostic models in accordance with the algorithms described in the research section. MATLAB and its other applications described in the work were used for data processing and modeling.
|
|
|
Document Classification
Marek, Tomáš ; Škoda, Petr (referee) ; Otrusina, Lubomír (advisor)
This thesis deals with a document classification, especially with a text classification method. Main goal of this thesis is to analyze two arbitrary document classification algorithms to describe them and to create an implementation of those algorithms. Chosen algorithms are Bayes classifier and classifier based on support vector machines (SVM) which were analyzed and implemented in the practical part of this thesis. One of the main goals of this thesis is to create and choose optimal text features, which are describing the input text best and thus lead to the best classification results. At the end of this thesis there is a bunch of tests showing comparison of efficiency of the chosen classifiers under various conditions.
|
|
|
Determining person's height from spoken utterance
Pelikán, Pavel ; Mekyska, Jiří (referee) ; Atassi, Hicham (advisor)
Diploma’s thesis is focused on determining person’s height from spoken utterance. First part of the work evaluates present situation and refers to the published studies. Knowledge gained in these studies was used in this thesis. Study with the best results according to estimated height of the speakers was chosen. The experiment realized in the chosen study was performed in this work. The system for the estimation of the height of the speakers based on the speech signal was created. This system was successfully tested by using several acoustic features on spoken utterances from TIMIT database.
|
|
|
Analysis of retinal nerve fiber layer in fundus images utilizing local binary patterns
Doležal, Petr ; Harabiš, Vratislav (referee) ; Odstrčilík, Jan (advisor)
This work describes LBP (Local Binary Pattern) method in its various forms as a tool for distinguishing images with and without texture. The first part of the essay looks into the retinal nerve fiber layer, loss of the nerve fiber and especially into possibilities of retinal images with help of the fundus camera and into properties of this way received data. Second part of the essay describes and explains the LBP method which uses local binary operators for description of texture by help of histograms. From this way brought force of histograms is possible to gain a complex of features. Due to different classification approaches can then determine if new samples were selected from an image loss of retinal nerve fiber layer (RNFL). This solves the next part of the essay. And then is evaluated the correlation of features of LBP histograms of these images with the thickness of the RNFL in the same place. The methods described in this essay have been tested on a set of images in Matlab program and received results show, that the method can be useful for the diagnosis of glaucoma diseases.
|
|
|
Analysis of hand-written text of patients with neurological disorders
Galáž, Zoltán ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
The master‘s thesis deals with the analysis of the hand-written text. There is a design and a realization of a system for the purpose of diagnosing a Parkinson’s desease based on the analysis of hand-written text. The system consists from several modules and it is programmed in the programming environment of MATLAB. The first module provides pre-processing of the records to adjust records to the form suitable for the segmentation. Afterwards, the records are divided into those with signals onto the surface of the tablet and those with the signals above the surface of the tablet. In the next module the records are segmented by the two-phase metod of automatic segmentation.High-level featuresare calculated from the extracted features. The results of the statistical analysis are exported in the form suitable for the classification process. The classification is performed by the proposed model made in the programming environment of RapidMiner. The output of designed system is the trained model capable of automatic classification of the Parkinson’s disease by the analysis of the hand-written text.
|
guest ::
