|
|
Analysis of speech disorders in patients with a high risk of developing Lewy body diseases
Novotný, Kryštof ; Kováč, Daniel (referee) ; Mekyska, Jiří (advisor)
Lewy bodies diseases (one of the most common neurodegenerative disorders) have the same pathological basis, but the individual representatives differ in their clinical manifestations. Different diseases affect the mental or physical side of the patient to a greater or lesser extent. This work assumes that thanks to the acoustic analysis of speech, it is possible to distinguish individual diseases from one another, because the disorders of the cognitive and motor aspects of a patient reflect in speech in specific ways. The thesis aims to describe the clinical features of the main representatives of the Lewy bodies diseases, to investigate their impact on speech, to propose characterizing acoustic parameters and then to compare their discriminative power. Speech recordings from the CoBeN and preLBD databases are used as input data for the proposed algorithm. Descriptive statistics, Mann-Whitney U test, FDR correction and XGBoost machine learning model using stratified cross-validation and balanced accuracy are used for subsequent evaluation. The result are scripts for the automated calculation of speech parameters from the database and their evaluation. The results of the analysis prove that the selected diseases can really be distinguished from each other and from a healthy control based on the manifestations in speech, already in the prodromal stages.
|
|
|
Development of features quantifying respiratory dysfunctions in Parkinson’s disease patients
Cvetler, Dominik ; Mekyska, Jiří (referee) ; Kováč, Daniel (advisor)
In the beginning of the thesis, Parkinson's disease and hypokinetic dysarthria are briefly described, which have a negative effect on speech production and cause breathing problems during speech in sick patients. The aim of the thesis is to create an algorithm for automated detection of breaths and the design of parameters for the quantification of respiratory disorders in patients with Parkinson's disease. In the MATLAB environment, the recordings of the researched subjects were processed and an algorithm was created for the detection of breaths, which used the logistic regression method. Based on the predicted breaths, proposed parameters were extracted from the recordings, which were then statistically analyzed and compared in healthy controls and patients with Parkinson's disease. By using a machine learning model, it was possible to predict the clinical data of patients from the proposed parameters to a certain extent. The average accuracy of the model for predicting puffs was 0.85. Of the 14 proposed parameters, 6 were suitable for quantifying respiratory disorders associated with hypokinetic dysarthria. The result of the work is a functional algorithm for the automated detection of breaths in the speech signal and proposed parameters that could be useful for the quantification of respiratory disorders in patients with Parkinson's disease.
|
|
|
Sub-types of hypokinetic dysarthria in patients with moderete Parkinson's disease
Adamják, Adam ; Kováč, Daniel (referee) ; Mekyska, Jiří (advisor)
This final thesis deals with the research of Parkinson's disease, hypokinetic dysarthria, and acoustic and statistical analyses. Hypokinetic dysarthria is a speech disorder that is a typical manifestation of Parkinson's disease, a neurodegenerative disease that affects approximately 2% of the population over the age of 65. The aim of this work is to reveal the subtypes of hypokinetic dysarthria, based on clinical parameters, acoustic analysis, and statistical analysis. In the acoustic analysis, parameters that examine the area of phonation, prosody, articulation, and speech tempo have been implemented. Subsequently, a statistical analysis was processed, thanks to which it was possible to reveal the subtypes of hypokinetic dysarthria.
|
|
|
Design of a system for detecting devices connected to the electrical network
Homola, Michal ; Kováč, Daniel (referee) ; Musil, Petr (advisor)
This master thesis deals with the creation of a system for detecting devices connected to the power network using the measurement of high-frequency noise obtained via BPL modems. In the theoretical part, there was an introduction to the issue of PLC, electromagnetic compatibility of EMC, the issue of impedance in PLC and noise characteristics in PLC. In the practical part, measurement of noise characteristics for individual devices and the creation of a dataset took place. The dataset, which was then tested on five machine learning models selected for this task based on their properties. Finally, the suitability of each model for our application was evaluated.
|
|
|
The Drug problems and road safety in the České Budějovice region
KOVÁČ, Daniel
This bachelor thesis focuses on the issue of driving under the influence of drugs in the South of Bohemia. First chapter focuses on the history of drug use and basic concepts of drug issues which are related with bachelor thesis. Second chapter focuses on the individual drugs and their definition as addictive substances and the most common drugs in the Czech Republic. To understand the issue of driving under the influence it is very important to mention law and legislative measures which are connected with drug issues and also defined terms such as offence and crime. The last chaptor of the theoretical part of this bachelor thesis focuses on the Police of the Czech republic and their resources used to secure the intoxicated driver. The empirical chapters are oriented on issues of intoxicated drivers in the South of Bohemia and the issues of violating road safety. This part also contain research and evaluation. The aim of this work is a mapping road safety issues related to drugs and to find out if there are any patterns concerning the amount of incident involving drug using issues
|
|
|
Analysis of impact of noise in recordings on the automated detection of hypokinetic dysarthria
Havelková, Nikola ; Galáž, Zoltán (referee) ; Kováč, Daniel (advisor)
This thesis deals with the automated detection of hypokinetic dysarthria by analysing the influence of noise present in recordings. Appropriate single-channel methods, specifically the spectral subtraction and Kalman filter, are selected and implemented in the MATLAB R2022a to enhance speech. These methods are also used for noise-free recordings, to which additive white noise was added. Afterwards, the effectiveness of these methods is objectively evaluated by using signal-to-noise ratio values. After enhancing of speech, interferences are extracted from the recordings. The effect of the presence of noise, as well as its subsequent suppression by individual methods, is then evaluated by statistical analysis, specifically using the Kruskal-Wallis test and the post hoc Dunn’s test. The probability of distributing parameters of clean, noisy and enhanced recordings, for which the effect of noise is significant, according to statistical tests, are plotted using violin and box graphs. Finally, the classification was done by logistic regression with the help of machine learning, where the effect of the presence of noise and subsequent speech enhancement on automated detection of hypokinetic dysarthria was described according to the area values under the ROC curve.
|
|
|
Multilingual Analysis Of Hypokinetic Dysarthria In Patients With Parkinson’s Disease
Kováč, Daniel
This article deals with the multilingual analysis of hypokinetic dysarthria (HD) in patientswith Parkinson’s disease (PD). The goal is to identify acoustic features that have high discriminationpower and that are independent of the language of a speaker. The speech corpus contains 59 PD patientsand 44 healthy controls (HC) speaking in Czech (cs) and American English (en-US). Based onnon-parametric statistical tests and logistic regression, we observed the best discrimination power hasthe speech index of rhythmicity (extracted from a reading text) and harmonic-to-noise ratio (extractedfrom a sustained vowel). We were able to identify PD with 67% sensitivity and 79% specificity inthe Czech corpus and with 78% sensitivity and 67% specificity in the English one. The performanceof the model was significantly lower when combining both datasets, thus suggesting language playsa significant role during the automatic assessment of HD.
|
|
|
Automatic speech recordings segmentation tool
Santa, Roman ; Zvončák, Vojtěch (referee) ; Kováč, Daniel (advisor)
Nástroj pre automatickú segmentáciu spracováva nahrávky reči a extrahuje hovorené slovo z nahrávok. Je dôležité, aby pokročilá analýza pracovala iba s rečovými časťami z nahrávky. Nástroj na segmentáciu má ulahčiť spracovanie nahrávok pre analýzu rozdielov medzi hláskami pacientov s parkinsonovou chorobou a tými zdravými. Cieľ tejto práce je navrhnúť a otestovať detektory reči s Google WebRTC detektorom a vybrať ten najvhodnejší detektor reči s minimálnym počtom chýb. Ďalej, vytvoriť nástroj na segmentáciu nahrávok a otestovať rozpoznávanie reči pomocou dynamic time warping. Bola použitá databáza poskytnutá laboratóriom pre analýzu mozgových ochorení. Obsahuje české a maďarské nahrávky s rovnakým počtom mužských a ženských pacientov a aj rovnakým počtom zdravých pacientov a pacientov s parkinsonovou chorobou. Najlepšie výsledky v testoch dosiahol detektor na základe energie reči. Nebol zistený žiaden rozdiel v presnosti detektoru pri spracovaní mužských a ženských nahrávok alebo nahrávok zdravých či chorých pacientov. Nahrávky s nízkym odstupom signálu od šumu boli náročnejšie na spracovanie s frekvenciou chýb od 12%. Na základe výsledkov, bol navrhnutý nový detektor pre spracovanie úplnej nahrávky. Na záver bol testovaný algoritmus pre rozpoznávanie podobnosti reči na základe melovských kepstrálnych koeficientov.
|
|
|
Differential analysis of multilingual corpus in patients with neurodegenerative diseases
Kováč, Daniel ; Zvončák, Vojtěch (referee) ; Mekyska, Jiří (advisor)
This diploma thesis focuses on the automated diagnosis of hypokinetic dysarthria in the multilingual speech corpus, which is a motor speech disorder that occurs in patients with neurodegenerative diseases such as Parkinson’s disease. The automatic speech recognition approach to diagnosis is based on the acoustic analysis of speech and subsequent use of mathematical models. The popularity of this method is on the rise due to its objectivity and the possibility of working simultaneously on different languages. The aim of this work is to find out which acoustic parameters have high discriminative power and are universal for multiple languages. To achieve this, a statistical analysis of parameterized speech tasks and subsequent modelling by machine learning methods was used. The analyses were performed for Czech, American English, Hungarian and all languages together. It was found that only some parameters enable the diagnosis of the hypokinetic disorder and are, at the same time, universal for multiple languages. The relF2SD parameter shows the best results, followed by the NST parameter. When classifying speakers of all the languages together, the model achieves accuracy of 59 % and sensitivity of 72 %.
|
|
|
Predicting light use efficiency using optical vegetation indices at various time scales and environmental conditions
Kováč, Daniel ; Ač, Alexander ; Veselovská, Petra ; Dreveňáková, Petra ; Rapantová, Barbora ; Klem, Karel
This study presents data points acquired during 2 years of measuring optical properties and gas-exchange\ncharacteristics of European beech (Fagus sylvatica) and Norway spruce (Picea abies) tree species in controlled\nenvironments. The observed statistical relationships between 105 pairs of selected optical parameters\n(i.e. photochemical reflectance index [PRI], ΔPRI, and normalized difference between wavebands R690\nand R630 [where R is a reflectance at a subscripted wavelength]) and light use efficiency (LUE) were considered\nat assumed different canopy leaf area index, changing pigments stoichiometrics, and daily changing\ndynamics of environmental conditions. Our measurements suggested that consistency of the LUE estimation\nusing PRI may be disrupted by acclimation responses of plants that reduce energetic carriers for\nuse in photosynthetic CO2 uptake and the xanthophyll cycle. Also, a changing chlorophylls-to-carotenoids\nratio tends to interrupt the PRI–LUE relationship. ΔPRI showed sensitivity to leaf area index of the measured\ntrees that complicated leaf-level estimation of LUE. The most consistent assessment of LUE was\nachieved using the chlorophyll fluorescence detecting ratio (R690 – R630)/(R690 + R630).
|
guest ::
RSS feed.