|
|
Semi-automatic computerized system for the segmentation of online handwriting
Gavenčiak, Michal ; Mekyska, Jiří (referee) ; Zvončák, Vojtěch (advisor)
The prevalence of developmental dysgraphia among school children is between 10-30%, yet in Czech Republic, there is no objective method to diagnose it or determine its severity. Past studies have shown the possibility of automatic diagnosis using digital data gathered using a digitizing tablet and a stylus. Data gathered within an ongoing study contain information on position, time stamp, tilt, pressure and azimuth of the stylus. These data are, however, unsuitable for further analysis due unspecified number of exercises contained in one SVC file. Within this thesis the data is analysed and a program, which is able to segment these data into units of exercises and display the processed data on the screen, is designed and implemented.
|
|
|
Synthesis of the musical audio signal using direct generation of harmonics
Ježek, Štěpán ; Mekyska, Jiří (referee) ; Přikryl, Lubor (advisor)
This thesis is focused on musical sound synthesis, in particular, the method of additive synthesis. The main goal is to implement a software musical instrument in the VST3 plug-in format, using the C++ programming language and the JUCE application framework. The final program offers spectral components editing capabilities and is able to morph between user-defined spectrum states in time. The introduction summarizes some common synthesis methods and their advantages or disadvantages. Next section deals with the technology used during the VST3 plug-in implementation and describes core parts that make up the final application. This analysis is focused mainly on the signal processing part, but there is also a brief description of the graphical user interface.
|
|
|
Potential calculation of mutual information from a time series
Hubr, Ivo ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
Mutual information is one of the factors used in traffic analysis and preparation phase space. Begin of this work deal with information theory, focusing on the calculation of mutual information. To calculate this parameter has been available for many algorithms which are analyzing in this final work. Two of the algorithms (Fraser-Swinney and calculation of mutual information using adaptive XY subdivision) are applied to the input data Rössler’ attractor, as shown in the output tables and graphs. The third consideration method is the computational Dinh-Tuan-Pham algorithm. The main goal of this work is a comparison of efficiency, speed and accuracy of the calculation of these algorithms.
|
|
|
Human behaviour monitoring system based on smartphone and bracelet data analysis
Mikulec, Marek ; Zvončák, Vojtěch (referee) ; Mekyska, Jiří (advisor)
There has been established new technological field using smart phones and wearable devices for medical research since the arrival of health 4.0. The main goal of this work is to design, implement and test new system for monitoring people´s behaviour using smart phone and wearable device. These smart compoments should oblige requirements of health~4.0. This work uses open source software AWARE Framework and data from Fitbit API. The final system enables gathering and sharing 36 measurable metrics from smart phone and wearable device. Furthermore it secures efective access to gathered data and puts particular emphasis on the security of the system. Finally the system was used to examine a patterns of REM (Rapid Eye Movement) sleep behaviour disorder.
|
|
|
Objectification of the Test 3F - dysarthric profile based on acoustic analysis
Bezůšek, Marek ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
Test 3F is used to diagnose the extent of motor speech disorder – dysarthria for czech speakers. The evaluation of dysarthric speech is distorted by subjective assessment. The motivation behind this thesis is that there are not many automatic and objective analysis tools that can be used to evaluate phonation, articulation, prosody and respiration of speech disorder. The aim of this diploma thesis is to identify, implement and test acoustic features of speech that could be used to objectify and automate the evaluation. These features should be easily interpretable by the clinician. It is assumed that the evaluation could be more precise because of the detailed analysis that acoustic features provide. The performance of these features was tested on database of 151 czech speakers that consists of 51 healthy speakers and 100 patients. Statistical analysis and methods of machine learning were used to identify the correlation between features and subjective assesment. 27 of total 30 speech tasks of Test 3F were identified as suitable for automatic evaluation. Within the scope of this thesis only 10 tasks of Test 3F were tested because only a limited part of the database could be preprocessed. The result of statistical analysis is 14 features that were most useful for the test evaluation. The most significant features are: MET (respiration), relF0SD (intonation), relSEOVR (voice intensity – prosody). The lowest prediction error of the machine learning regression models was 7.14 %. The conclusion is that the evaluation of most of the tasks of Test 3F can be automated. The results of analysis of 10 tasks shows that the most significant factor in dysarthria evaluation is limited expiration, monotone voice and low variabilty of speech intensity.
|
|
|
Music information retrieval techniques for determining the place of origin of the Czech chamber and orchestral music interpretations
Miklánek, Štěpán ; Mekyska, Jiří (referee) ; Kiska, Tomáš (advisor)
This diploma thesis is focused on the statistical analysis of chamber and orchestral classical music recordings composed by Czech authors. One of the chapters is dedicated to the description of a feature extraction process that precedes the statistical analysis. Techniques of Music Information Retrieval are used during several stages of this thesis. Databases used for analysis are described and pre-processing steps are proposed. A tool for synchronization of the recordings was implemented in MATLAB. Finally the system used for classification of recordings based on their geographical origin is proposed. The recordings are sorted by a binary classifier into two categories of Czech and world recordings. The first part of the statistical analysis is focused on individual analysis of features. The features are evaluated based on their discrimination strength. The second part of the statistical analysis is focused on feature selection, which can improve the overall accuracy of the binary classifier compared to the individual analysis of the features.
|
|
|
Patient assessment system based on mHealth techniques
Kulinich, Viacheslav ; Mucha, Ján (referee) ; Mekyska, Jiří (advisor)
This bachelor thesis is focused on the possibility of examining patients using an electronic questionnaire based on mHealth techniques. In the first two chapters of this work is included the issue of patient examination, the function that must fulfill the electronic questionnaire, the research of existing types of mobile applications and the description of the selected type. The following chapters contain the process of creating web applications, implementation of client and server part, their communication, used security elements and brief description of graphical interface. The result is a functional progressive web application that has been tested successfully and is published on the Internet.
|
|
|
Face parameterization using videosequence
Lieskovský, Pavol ; Mekyska, Jiří (referee) ; Rajnoha, Martin (advisor)
This work deals with the problem of face parameterization from the video of a speaking person and estimating Parkinson’s disease and the progress of its symptoms based on face parameters. It describes the syntax and function of the program that was created within this work and solves the problem of face parameterization. The program formats the processed data into a time series of parameters in JSON format. From these data, a dataset was created, based on which artificial intelligence models were trained to predict Parkinson’s disease and the progress of its symptoms. The process of model training and their results are documented within this work.
|
|
|
Real-time Facial Feature Tracking
Peloušek, Jan ; Mekyska, Jiří (referee) ; Přinosil, Jiří (advisor)
This thesis considers the problematic of the object recognition in a digital picture, particularly about the human face recognition and its components. There are described the basics of the computer vision, the object detector Viola-Jones, its computer realization with help of the OpenCV libraries and the test results. This thesis also describes the accurate system of the facial features detection per the algorithm of the Active Shape Models and also related mechanism of the classifier training, including the software implementation.
|
|
|
Speech Enhancement Methods
Kukučka, Peter ; Mekyska, Jiří (referee) ; Hudec, Antonín (advisor)
Aim of this work is summarize some single-channel methods of speech enhancement. These methods are explained in this work: Basic Spectral Subtraction Method, Modified Spectral Subtraction, Multi-band Spectral subtraction, spectral subtraction MMSE and Wiener filtering. All methods are implemented. Preprocessing, voice activity detector and speech scores are explained in this paper, too.
|
guest ::
RSS feed.