|
|
Acoustic call analysis application for Android system
Hejda, Jakub ; Mucha, Ján (referee) ; Mekyska, Jiří (advisor)
The telemedicine’s capabilities are rapidly expanding due to technological advances in a smarphone development. The goal of this thesis was to suggest the architecture and prepare the design providing acquisition, processing and synchronization of voice para- meters recorded by patients with Parkinson’s disease and to implement such system. The architecture was completed successfully, it consists of the mobile application able to record patient’s calls, the server application introducing an interface to store and synchronize the data and to provide them to the web application, where doctors can see the data and analyze it. Implementation of the server application was finished according to the design and to the requirements for robustness and security as well as the web application. By an extension of the existing mobile application for recording voice calls there was developed a huge system for the analysis of this disease.
|
|
|
Mobile application for dysarthria assessment utilising the Test 3F
Grenčík, Dominik ; Mucha, Ján (referee) ; Mekyska, Jiří (advisor)
Speech dysarthria is a impaired communication ability, a motor disorder affecting basic modal aspects of speech. In the Czech Republic, Test 3F, developed in the current clinical speech therapy, is used in diagnostics in both text and electronic form, consisting of 45 execution tasks. Currently, the trend of using mobile applications is expanding in various areas of life, which speed up and streamline human communication and work. The aim of this work is to create a simple but high-quality and reliable mobile application of Test 3F as a diagnostic tool for the examination of speech dysarthria in an effort to help clinical speech therapy in simplifying the diagnosis of this disorder. Mobile application is programmed using several programming languages: Backend is programmed in PHP using the Laravel framework. Frontend is programmed in JavaScript using the React library and the Material UI component library.
|
|
| |
|
|
Library for Python used for dysarthric speech parameterization
Koutný, Tomáš ; Galáž, Zoltán (referee) ; Mucha, Ján (advisor)
Bachelor thesis is focused on parameterization of dysartoric speech. Attention is paid to methods of Speech Signal Analysis for Parkinson's disease, modern parametrization techniques, which are designed to quantify the damage of motoric aspects of speech and implementation of selected parameters in Python. The main goal of this work was to create a parameter library that is realized in the PyCharm development environment.
|
|
|
Advanced Parameterisation of Online Handwriting in Writers with Graphomotor Disabilities
Mucha, Ján ; Šimák, Boris (referee) ; Drotár,, Peter (referee) ; Mekyska, Jiří (advisor)
Grafomotorické obtíže (GD) výrazně ovlivňují kvalitu života školním věkem počínajíc, kde se vyvíjejí grafomotorické schopnosti, až do důchodového věku. Včasná diagnóza těchto obtíží a terapeutický zásah mají velký význam k jejich zlepšení. Vzhledem k tomu, že GD souvisí z vícerými symptomy v oblasti kinematiky, základní kinematické parametry jako rychlost, zrychlení a švih prokázaly efektivní kvantizaci těchto symptomů. Objektivní výpočetní systém podpory rozhodování pro identifikaci a vyšetření GD však není dostupný. A proto je hlavním cílem mé disertační práce výzkum pokročilé metody parametrizace online písma pro analýzu GD se speciálním zaměřením na využití metod zlomkového kalkulu. Tato práce je první, která experimentuje s využitím derivací neceločíselného řádu (FD) pro analýzu GD pomocí online písma získaného od pacientů s Parkinsonovou nemocí a u dětí školního věku. Byla navržena a evaluována nová metoda parametrizace online písma založena na FD využitím Grünwald-Letnikova přístupu. Bylo dokázáno, že navržená metoda významně zlepšuje diskriminační sílu a deskriptivní schopnosti v oblasti Parkinsonické dysgrafie. Stejně tak metoda pozitivně ovlivnila i nejmodernější techniky v oblasti analýzy GD u dětí školního věku. Vyvinutá parametrizace byla optimalizována s ohledem na výpočetní náročnost (až o 80 %) a také na vyladění řádu FD. Ke konci práce byly porovnány víceré přístupy výpočtu FD, jmenovitě Riemann-Liouvillův, Caputův společně z Grünwald-Letnikovým přístupem za účelem identifikace těch nejvhodnějších pro jednotlivé oblasti analýzy GD.
|
|
|
Music mood and emotion recognition using Music information retrieval techniques
Smělý, Pavel ; Mucha, Ján (referee) ; Kiska, Tomáš (advisor)
This work focuses on scientific area called Music Information Retrieval, more precisely it’s subdivision focusing on the recognition of emotions in music called Music Emotion Recognition. The beginning of the work deals with general overview and definition of MER, categorization of individual methods and offers a comprehensive view of this discipline. The thesis also concentrates on the selection and description of suitable parameters for the recognition of emotions, using tools openSMILE and MIRtoolbox. A freely available DEAM database was used to obtain the set of music recordings and their subjective emotional annotations. The practical part deals with the design of a static dimensional regression evaluation system for numerical prediction of musical emotions in music recordings, more precisely their position in the AV emotional space. The thesis publishes and comments on the results obtained by individual analysis of the significance of individual parameters and for the overall analysis of the prediction of the proposed model.
|
|
|
E-communication in a Small Company Using ICT Processes
Hübel, Květoslav ; Mucha, Jan (referee) ; Kříž, Jiří (advisor)
This thesis is focused on information and communication technologies (ICT) in conditions and with limits typical for small companies. The goal of this work is to improve competitive advantage in the market and to create an effective cooperation in the team of this company. The Solution of the thesis suggests how to design such an information strategy in service and marketing company and how to implement ERP system in future.
|
|
|
Recognizing the historical period of interpretation based on the music signal parameterization
Král, Vítězslav ; Mucha, Ján (referee) ; Kiska, Tomáš (advisor)
The aim of this semestral work is to summarize the existing knowledge from the area of comparison of musical recordings and to implement an evaluation system for determining the period of creation using the music signal parameterization. In the first part of this work are describe representations which can music take. Next, there is a cross-section of parameters that can be extracted from music recordings provides information on the dynamics, tempo, color, or time development of the music’s recording. In the second part is described evaluation system and its individual sub-blocks. The input data for this evaluation system is a database of 56 sound recordings of the first movement of Beethoven’s 5th Symphony. The last chapter is dedicated to a summary of the achieved results.
|
|
|
Musical instruments recognition from audio records using Music information retrieval techniques
Kárník, Radoslav ; Mucha, Ján (referee) ; Kiska, Tomáš (advisor)
This paper discusses design and implementation of classifying system for recognition of musical instruments from audio records with use of Musical Information Retrieval techniques. In the first part, paper describes parameters used for instrument classification, calculation of said parameters from records and reduction of feature vector. Next part is devoted to tuning and implementation of various classifiers with focus on neural networks. These classifiers ar further tested on records from IRMAS dataset wchich contain 11 musical instruments playing solo or with other instruments. Results of classifiers tested on different parameters and different numbers of instruments are discussed in the last part.
|
|
|
Web application for training and validation of machine learning models
Svoboda, Jan ; Mucha, Ján (referee) ; Galáž, Zoltán (advisor)
The delegation of resource-intensive operations to the server-side computers is an ongoing trend. Containerized applications serve as an abstraction over the servers and provide needed scalability. The architecture of the implemented application utilized as a platform for an asynchronous execution of training and validation of machine learning models is heavily influenced by the containerization. Individual users of a web application are given a separate container with prepared environment for running a model with selected parameters. Status of the training process is monitored by the application. After the result is obtained the analysis takes place and components providing visualization are rendered in the user interface.
|
guest ::
