National Repository of Grey Literature 36 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Speech Disorders In Parkinson’S Disease Patients With Mild Form Of Freezing Of Gait
Galáž, Zoltán
This paper deals with the description of speech disorders present in the mild stage of freezing of gait (FOG) in patients with Parkinson’s disease (PD). Experimental dataset consisted of 48 PD patients and 52 healthy controls (HC). We used freezing of gait questionnaire (FOG-Q) to characterize FOG in PD. Using one-way analysis of variance, we found loosely adducted vocal folds during phonation (p = 0.0027), increased acoustic noise (p = 0.0294), reduced variability of pitch (p = 0.0440), and reduced mobility of articulatory organs (p = 0.0157) significantly statistically different in PD patients in comparison with HC.
Correlation Analysis Of Freezing Of Gait And Speech Disorders In Parkinson’S Disease
Galáž, Zoltán
This paper deals with the analysis of a relationship between freezing of gait (FOG) and hypokinetic dysarthria (HD) in Parkinson’s disease (PD). Experimental dataset consisted of 74 PD patients. We used freezing of gait questionnaire (FOG-Q) to characterize FOG in PD. The speech features that quantifies phonation, articulation and prosody was computed from the reading task composed of interrogative, imperative and indicative sentences. Using Spearman’s and Pearson’s correlation coefficients, we showed that reduced mobility of the articulatory organs in HD is significantly correlated with FOG in PD.
Automatic tagging of musical compositions using machine learning methods
Semela, René ; Galáž, Zoltán (referee) ; Kiska, Tomáš (advisor)
One of the many challenges of machine learning are systems for automatic tagging of music, the complexity of this issue in particular. These systems can be practically used in the content analysis of music or the sorting of music libraries. This thesis deals with the design, training, testing, and evaluation of artificial neural network architectures for automatic tagging of music. In the beginning, attention is paid to the setting of the theoretical foundation of this field. In the practical part of this thesis, 8 architectures of neural networks are designed (4 fully convolutional and 4 convolutional recurrent). These architectures are then trained using the MagnaTagATune Dataset and mel spectrogram. After training, these architectures are tested and evaluated. The best results are achieved by the four-layer convolutional recurrent neural network (CRNN4) with the ROC-AUC = 0.9046 ± 0.0016. As the next step of the practical part of this thesis, a completely new Last.fm Dataset 2020 is created. This dataset uses Last.fm and Spotify API for data acquisition and contains 100 tags and 122877 tracks. The most successful architectures are then trained, tested, and evaluated on this new dataset. The best results on this dataset are achieved by the six-layer fully convolutional neural network (FCNN6) with the ROC-AUC = 0.8590 ± 0.0011. Finally, a simple application is introduced as a concluding point of this thesis. This application is designed for testing individual neural network architectures on a user-inserted audio file. Overall results of this thesis are similar to other papers on the same topic, but this thesis brings several new findings and innovations. In terms of innovations, a significant reduction in the complexity of individual neural network architectures is achieved while maintaining similar results.
System of secured actigraph data transfer and processing
Mikulec, Marek ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
The new Health 4.0 concept brings the idea of combining modern technologies from field of science and technology with research in healthcare and medicine. This work realizes a system of secured actigraph data transfer and preprocessing based on the concept of Health 4.0. The system is successfully designed, implemented, tested and secured. With the help of a non-invasive method of monitoring the movement and temperature of the subject using the GENEActiv actigraph allows the system to securely transfer, process and evaluate the subject's sleep data using the machine learning algorithm XGBoost. The proposed system is in accordance with the valid law of the Czech Republic and meets legal requirements.
Development of modern acoustic features quantifying hypokinetic dysarthria
Kowolowski, Alexander ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (referee) ; Burget, Radim (advisor)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
Tool for parsing and analysing of web pages
Odstrčil, Štěpán ; Ilgner, Petr (referee) ; Galáž, Zoltán (advisor)
This bachelor’s thesis is dealing with parsing of text in HTML pages and its analysis. Practices from Natural Language Processing were used. There were written libraries (or packages) in programming language Python, with use of modern practices, techniques and libraries. The usages and examples of these libraries and classes were made. All these libraries were tested using Unit tests. Application contains GUI (Graphical User Interface) for wasier usefulness and demonstration of functionality.
Twitter data analysis tool
Rýdl, Pavel ; Komosný, Dan (referee) ; Galáž, Zoltán (advisor)
This work deals with the creation of an application for automatic downloading and Twitter data analysis based on natural language processing techniques. The application is created in the Python programming language. A development environment Jupyter Notebook was used for creating the application, where the entire application, including GUI, was implemented. In the section of theory are data downloading issues and data analysis by natural language processing described. In the part of implementation there is solution of the application described in several steps, such as creating the application on the Twitter's side, downloading, preprocessing, data analysis with techniques of natural language processing and following visualization. There was also a technique with no natural language processing implemented. Testing run on tweets that contained reference to US president Donald Trump.
Research of modern articulation features for the analysis of hypokinetic dysarthria
Vrba, Filip ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This thesis deals with hypokinetic dysarthria, as a disorder of motor speech, which occurs in approximately 70% of patients with Parkinson’s disease (PD). Two newly designed speech parameters for quantification of articulation within HD are analysed in this thesis. This parameters were validated on recording of both healthy and PD speakers. The theoretical part describes conventional and used methods of speech signal processing, parameterization and statistical analysis. In the part of the system implementation is described practical design of new parameters and also methods of their statistical evaluation by correlation analysis and machine learning. The aim of this work is to design new speech parameters for HD diagnostics. The proposed system was implemented in MATLAB software environment.
Android application for clinical assessment of patients
Rusnák, Daniel ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
This bachelor thesis deals with the design and implementation of a system for digitizing the process of clinical testing of patients with neurological diseases in the form of test questionnaires. The system consists of three applications that together form a functional system to help doctors work efficiently and speed up their work.

National Repository of Grey Literature : 36 records found   1 - 10nextend  jump to record:
See also: similar author names
1 Galáž, Z.
Interested in being notified about new results for this query?
Subscribe to the RSS feed.