In this semestral thesis, realizations of chosen linear filters for baseline wander are described. These filters are then used on artificial ECG signals from CSE database with added baseline wander. These methods are compared and results are evaluated. After that, literature search of Empirical mode decomposition method is utilized. Realization of designed filters in MATLAB programming language are described, then results are evaluated with respect to filtration success.

This master’s thesis deals with methods for detection of myocardial ischemia in the ECG signal. There is explained the principle of spreading of electrical activity through the heart muscle and its manifestations on the ECG. There are also mentioned the causes of myocardial ischemia and various methods of its detection in the ECG signal. In great detail there is explained the process of implementation of the two selected detection methods of myocardial ischemia in MATLAB. These methods are tested on the data from The PTB Diagnostic ECG Database. Finally, there is the presentation of detection results on used data and overall assessment of created algorithms.

This thesis focuses on the issue of atrial fibrillation and the success of their detection in the ECG signal. It provides a description of electrical activity of the heart with the theoretical analysis of atrial fibrillation and methods for their detection. Additionally the work describes procedures for the implementation of three selected methods for the detection of atrial fibrillation in the MATLAB environment, presents the results of their tests on two atrial fibrillation signal databases and assesses the accuracy of each method.

Atrial fibrillation is diagnosed in 1-2% of the population, in next decades, it expects a significant increase in the number of patients with this arrhythmia in connection with the aging of the population and the higher incidence of some diseases that are considered as risk factors of atrial fibrillation. The aim of this work is to describe the problem of atrial fibrillation and the methods that allow its detection in the ECG record. In the first part of work there is a theory dealing with cardiac physiology and atrial fibrillation. There is also basic descreption of the detection of atrial fibrillation. In the practical part of work, there is described software for detection of atrial fibrillation, which is provided by BTL company. Furthermore, an atrial fibrillation detector is designed. Several parameters were selected to detect the variation of RR intervals. These are the parameters of the standard deviation, coefficient of skewness and kurtosis, coefficient of variation, root mean square of the successive differences, normalized absolute deviation, normalized absolute difference, median absolute deviation and entropy. Three different classification models were used: support vector machine (SVM), k-nearest neighbor (KNN) and discriminant analysis classification. The SVM classification model achieves the best results. Results of success indicators (sensitivity: 67.1%; specificity: 97.0%; F-measure: 66.8%; accuracy: 92.9%).

This thesis deals with classification of different types of time courses of ECG signals. Main objective was to recognize the normal cycles and several forms of arrhythmia and to classify the exact types of them. Classification has been done with usage of algorithms of Neural Networks in Matlab program, with its add-on (Neural Network Toolbox). The result of this thesis is application, which makes possible to load an ECG signal, pre-process it and classify its each cycle into five classes. Percentage results of this classification are in the conclusion of this thesis.

The goal of this thesis is to detect pacing pulses in ultra high-frequency ECG so as to remove these pacing pulses. It makes evaluation of higher frequency components of QRS complex possible. This evaluation is impossible while pacing pulses are present. Chosen issue is solved using heuristic algorithm. Algorithm uses spacing of signal by line in the area which is not influenced by pacing pulses. Subsequently this line is made longer and using differences between line and signal (or another rules) edges of pacing pulses are detected. The top of the stimulation tip is detected by thresholding envelope of original signal´s first difference. More algorithms are tested in this thesis. Several methods of removing pacing pulses are suggested in thesis. Envelopes of high-frequency components are created. Envelopes are analyzed subsequently and suggested methods of removing pacing pulses are compared on the basis of these analysis. Finally the detection efficiency is evaluated.

Atrial fibrillation is one of the most common cardiac rhythm disorders characterized by ever-increasing prevalence and incidence in the Czech Republic and abroad. The incidence of atrial fibrillation is reported at 2-4 % of the population, but due to the often asymptomatic course, the real prevalence is even higher. The aim of this work is to design an algorithm for automatic detection of atrial fibrillation in the ECG record. In the practical part of this work, an algorithm for the detection of atrial fibrillation is proposed. For the detection itself, the k-nearest neighbor method, the support vector method and the multilayer neural network were used to classify ECG signals using features indicating the variability of RR intervals and the presence of the P wave in the ECG recordings. The best detection was achieved by a model using a multilayer neural network classification with two hidden layers. Results of success indicators: Sensitivity 91.23 %, Specificity 99.20 %, PPV 91.23 %, F-measure 91.23 % and Accuracy 98.53 %.

The thesis deals with detection of T-wave alternans. The presence of T-wave in surface ECG is recognized as a marker of electrical instability of heart in stage his repolarization, arise increased risk of emergence ventricular fibrillation and sudden cardiac death. The goal of our project is familiarize with methods of detection T-wave alternans. In particular spectral method and spectral method which was realized in variant for running reading values in time (“sliding window”). To suggest a QRS complex detector, localize the T-wave and to make TWA detection using spectral method and modified spectral method. This project is to be made in C language in appropriate user interface.

The thesis deals with one of the non-linear methods for signal processing - dynamic time warping (DTW). The method observes shape changes, which should be used in biomedical signals processing. The thesis involves the method description and consecution for finding DTW optimal way. The method is applied on the number series in the edutainment program, on the group of simulated signals and real electrocardiograms (ECG). ECG recordings were gained by performing experiments on the Masaryk University and their aim was clarifying the influence of voltage-sensitive dye on the heart tissue. One-lead ECG was described in time domain, frequency domain, time-frequency domain and subsequently remitted to DTW algorithm. The method outcomes evaluates the diversity rate of ECG signals obtained in each experiment stages. During the data evaluation were followed up the changes in process of the tension-sensible paint application and the stage of scouring toward control. The difference of elaborating signals group was verified in the time domain (37,5 %), in the frequency domain (75 %) and in the time-frequency domain (25 %). However, due to the small data group was not possible to explicitly approve the activity of voltage-sensitive dye on the heart tissue and to determinate limiting value of minimum algorithm way DTW for each heart round electrocardiogram classification. In the more data group analysis it is supposed to manifest the trend of growth heart round ECG differences in the stage of staining toward the stage of scouring.

This thesis deals with analysis of T-wave Alternans (TWA), periodical changes of T wave in ECG signal. Presence of these alternans may predict higher risk of sudden cardiac death. From the several possible ways of TWA classification, the training algorithms of self organizing maps are used in this thesis. Result of the thesis is a program, which in the first step detects QRS complexes in the signal. Then, in the next step, gained reference points are used for T-waves detection. Detected waves are represented by a vector of significant points, which is used as an input for artificial neural network. Final output of the program is a decision about presence of TWA in the signal and its rate.