|
|
ECG Signal Distortion Measures
Požár, Pavel ; Kozumplík, Jiří (referee) ; Vítek, Martin (advisor)
This master's thesis deals with electrocardiogram and its distortion, which causes errors, due to which a doctor can make a wrong diagnosis. In the theoretical part electrocardiogram is briefly described, further theory of wavelet transform, introduction to the signal compression and some information about ECG delineation. Methods used for the signal evaluation and therefore determination of the distortion size are described in the main theoretical part. This thesis contains known methods and also a method of own design based on the ECG delineation. Some of the described methods are checked in the practical part. These methods are tested for two different compression algorithms, which cause various distortion. In the final part distortion was tested on the influence on setting the wrong diagnosis.
|
|
|
An Arrhytmia Classifiication Based on RR Interval
Novotný, Jiří ; Škutková, Helena (referee) ; Kozumplík, Jiří (advisor)
This bachelor’s thesis deals with automatic classification of cardiac rhytm based on the sequence of RR intervals. The theoretical part deals both with characteristics of arrhytmias, which have been classified and the principles of the detectors and classificators used in this thesis. In the practical part, the QRS detector based on the calculation of the envelope of the ECG signal was realized in Matlab. Furthermore, the algoritm classifying arrhytmias based on the analysis of RR intervals was created. The reliability of the detector and the efficiency of the classificator was tested on the standard database CSE. The sensitivity of the detector was 98,28% and its positive predictive value was 98,38%. The diagnoses of the implemented classificator concurred in 73,17% with the cardiologists‘ diagnoses.
|
|
|
Delineation of experimental ECG data
Hejč, Jakub ; Janoušek, Oto (referee) ; Vítek, Martin (advisor)
This thesis deals with a proposition of an algorithm for QRS complex and typical ECG waves boundaries detection. It incorporates a literature research focused on heart electrophysiology and commonly used methods for ECG fiducial points detection and delineation. Out of the presented methods an algorithm based on a continuous wavelet transform is implemented. Detection and delineation algorithm is tested on CSE standard signal database towards references determined both manually and automatically. Obtained results are compared to other congenerous methods. The diploma thesis is further concerned with an algorithm modification for experimental electrocardiograms of isolated rabbit hearts. Recording specifics of these data are introduced. Additionally, based on time and frequency analysis, particular modifications of the algorithm are proposed and realized. Due to a large extent of records functionality is verified on randomly selected database samples. Efficiency of the modified algorithm is evaluated through manually annotated references.
|
|
|
Automatic delineation of ECG signals
Olšanská, Eva ; Kozumplík, Jiří (referee) ; Vítek, Martin (advisor)
This bachelor´s thesis deals with the delineation of ECG signals. The aim of this bachelor´s thesis is to become familiar with ECG delineation and realize one chosen delineation method in Matlab. The delineation algorithm was tested on a CSE database. The theoretical part of the work describes methods of QRS complex detection and ECG delineation.
|
|
|
Methods for detection of QRS complex
Lysák, Karel ; Chrobák, Martin (referee) ; Smital, Lukáš (advisor)
This bachelor’s thesis deals with methods for detection of QRS complex in the ECG signal. There are described selected detection approaches, basic information about ECG and electrical activity of cardiac muscle. There is also described detailed procedure for the implementation of the three methods of detection in MATLAB and an assessment is made of the detectors tested on the CSE database. There are described some methods of cluster analysis and their possibilities of usage. There is also a description of detectors created by using cluster analysis and their efficiency is tested on the CSE database. Finally, there is a comparison of detection rates of all created detectors.
|
|
|
Wavelet Wiener filter of ECG signals
Janů, Joshua ; Kozumplík, Jiří (referee) ; Smital, Lukáš (advisor)
The thesis focuses on the use of wavelet wiener filtration to remove muscular interference from ECG signals. As part of it, a filter has been implemented in the MATLAB programming environment. The main part of the thesis deals with the optimization of numerical parameters of the proposed filter. The results of the filtration are compared with the results reported by other authors.
|
|
|
Automatic delineation of ECG signals
Vítek, Martin ; Tyšler, Milan (referee) ; Halámek,, Josef (referee) ; Kozumplík, Jiří (advisor)
This dissertation deals with QRS complex detection and ECG delineation. The theoretical part of the work describes basics of electrocardiography, QRS detection approaches, ECG delineation approaches, the standard CSE database and the wavelet transform theory. The practical part of the work describes designed methods of QRS complex detection and ECG delineation. The designed methods are based on a continuous wavelet transform, appropriate scales, appropriate mother wavelet, cluster analysis and leads transformation. The introduced algorithms were evaluated on the standard CSE database. The obtained results are better, than directly comparable results of other methods and accomplished given database criteria. The robustness of designed algorithms was successfully tested on CSE database signals modified by compression and filtering. The proposed ECG delineation algorithm was successfully used as a tool for evaluation of diagnostic distortion of ECG signals modified by compression.
|
|
|
QT Interval Measurement
Váňa, Tomáš ; Chrobák, Martin (referee) ; Kozumplík, Jiří (advisor)
This semestral thesis deals with QT interval measurement. The theoretical part of the work describes ECG delineation, QT interval and methods for detection Q onset and T offset. The practical part of the work describes R wave detection, preprocessing of ECG signal and implementation of selected methods for QT interval measurement. Selected algorithms were evaluated on the standard CSE database. Detected positions were compared with reference values. Result of this work is evaluation of results.
|
|
|
Simple wavelet filter of ECG signals
Doležel, Jiří ; Ronzhina, Marina (referee) ; Smital, Lukáš (advisor)
The work deals with wavelet transfom and its possibilities of using it for elimination muscle noise from ECG signals. The first part of this thesis describes basic properties of ECG signal, the most common types of noise and describes basic types of wavelet transform, which are used for filtering the signals. Others parts describe a process of ECG signals wavelet filter design and afterwards the most appropriate setting are described. Finally results of filtration are evaluated, based on improved SNR, and compared with other author’s results.
|
|
|
Wavelet Based Filtering of Electrocardiograms
Smital, Lukáš ; Smékal, Zdeněk (referee) ; Halámek, Josef (referee) ; Kozumplík, Jiří (advisor)
This dissertation deals with possibilities of using wavelet transforms for elimination of broadband muscle noise in ECG signals. In this work, the characteristics of ECG signals and particularly the most frequently occurring type of interference are discussed firstly. The theory of wavelet transforms is also introduced and followed by design of the simple wavelet filter and the more sophisticated version with wiener filtering of wavelet coefficients. Next part is devoted to the design of our filter, which is based on wavelet wiener filtering and is complemented by algorithms that ensure full adaptability of its parameters when the properties of the input signal are changing. Suitable parameters of the proposed system are searched automatically and the algorithm is tested on the complete standard electrocardiograms database CSE, where it achieves significantly better results than other published methods.
|
guest ::
