|
|
Biometric fingerprint liveness detection
Rišian, Lukáš ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
This bachelor thesis deals with the problem of biometric fingerprint liveness recognition. The aim of the thesis is to propose a solution that reliably and securely recognizes fake fingerprints from genuine ones. Specifically, the work focuses on investigating methods for detecting fingerprint liveness using software tools, creating a custom fingerprint test database, testing and identifying relevant characteristics for successful liveness detection, and using them to implement fingerprint liveness recognition algorithms. Another goal was to create a GUI to provide a tool for overall detection. The work includes an analysis of the basics of biometrics, fingerprint characteristics and structure, current sensors used for fingerprint extraction, databases used, image preprocessing methods, tested features, implemented algorithms, and two GUI variants. More than 180 different image features were tested and more than 20 variants of algorithms were implemented. From these algorithms, the best ones were selected, whose detection results were then compared with those of foreign authors. The best algorithm achieved an accuracy of almost 90%, which can be considered a reliable and satisfactory result compared to foreign authors.
|
|
|
Stress recognition using biological signals measured by wearable devices
Surkoš, Ondřej ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
With the growing importance of mental health in society and the increasing availability of wearable technology, biological signals offer a unique opportunity to monitor and manage stress in everyday life. The diploma thesis focuses on the automatic stress recognition of biological signals measured by wearable devices. Therefore, in the theoretical part, key terms related to stress and wearable devices are defined and selected biological signals relevant for stress detection are described. The work also presents several publicly available datasets and describes current stress recognition methods, together with the achieved results. The practical part of the work is devoted to the construction of the dataset, data preprocessing and the development of an algorithm for recognizing stress in the MATLAB program environment. In particular, machine learning techniques are used both for feature extraction and selection, as well as for the classics themselves. The performance of the proposed models, which reached an accuracy of up to 81.1 % in the case of the unified dataset, 97.1 % in the case of the WESAD dataset and 80 % in the case of the Non-EEG Biosignals dataset, are presented and discussed in the final part of the work, together with by finding a great influence of the methodology and the equipment used during data acquisition on the performance of individual models.
|
|
|
ECG signal quality annotation
Hluší, Veronika ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
This thesis deals with the topic of annotation of the quality of ECG recordings. Theo- retical part of the thesis contains a description of methods dealing with the ECG signal quality annotation. The practical part deals with designing and implementation of pur- posed method, which enables continuous estimation of the quality of ECG recordings.The implemented method is tested on publicly available records and the results are evaluated.
|
|
|
Classification of sleep events from polygraphic data
Bódi, Michal ; Smital, Lukáš (referee) ; Králík, Martin (advisor)
This bachelor’s thesis discusses the detection and classification of sleep apnea. First, it explains the differences between individual sleep disorders and data acquisition methods. Creating an overview such as gain signals and then suggests an algorithm procedure for detection and classification with the help of wavelet transform, thresholding and machine learning model. The thesis continues with the program solution itself in the Matlab environment and its evaluation through the visualization of the confusion matrix and the F1 score. The highest value of F1 in detection reached 91.33% and in classification 43,64%. The created algorithm was supposed to look for sleep-related breathing disorders in all-night recordings.
|
|
|
Upper limb gesture recognition from EMG recordings
Kostial, Martin ; Smital, Lukáš (referee) ; Harabiš, Vratislav (advisor)
This work covers gesture recognition from upper limb sEMG recordings, designing a custom classifier using machine learning. The thesis is divided into six chapters – the first describes the EMG signal properties, the second discusses current EMG evaluation methods using machine learning, the third presents the actual implementation of the recognition algorithm, the fourth one deals with capturing the actual EMG recordings, and the fifth one is a discussion of the obtained results.
|
|
|
Automatic diagnosis of the 12-lead ECG using deep learning
Blaude, Ondřej ; Smital, Lukáš (referee) ; Provazník, Valentine (advisor)
The aim of this diploma thesis is to investigate the problematics of automatic ECG diagnostics, namely on twelve-lead recordings. In the first chapter the heart and its electrical activity measurement is described shortly. In addition to that, the abnormalities which are going to be classified in this thesis are also briefly described. In the second chapter, it is described how the ECG was diagnosed earlier, by classical methods that preceded deep learning. Some of the shortcomings that the classical methods have compared to deep learning are also described here. The third part already pays attention to deep learning itself, and its contribution and advantages compared to classical methods. Convolutional neural networks and their individual blocks are also described here, later attention is paid to selected architectures that were used in some studies. The fourth chapter already focuses on the practical part, in which the data used from the PhysioNet database, the proposed algorithm and its implementation are described in more detail. In the fifth chapter the results are discussed and compared to the corresponding publications.
|
|
|
HRV analysis based on PPG signal
Kadlčík, Jindřich ; Hrbotický, Lukáš (referee) ; Smital, Lukáš (advisor)
Heart rate variability analysis has lately gained remarkable popularity as a tool in training optimalization and in prevention of cardiac disease. It is usually based on the ECG signal, the acquisition of which is uncomfortable during activity. Therefore, the option to base the analysis on the PPG signal instead was proposed, but not yet sufficiently studied. This study compiles the necessary information for correct heart rate variability analysis and introduces our own implemented detectors of fiducial points in the PPG signal, and compares their usability for calculation of HRV analysis metrics.
|
|
|
Calculation of the cyclist's power output based on data from shoe pressure insoles
Teturová, Iveta ; Smital, Lukáš (referee) ; Hrbotický, Lukáš (advisor)
Překlad abstraktu The Bachelor’s thesis deals with the question of utilizing pressure values measured by pressure inserts for calculating the performance of cyclists. Since this method has not been used in cycling before, the result of this work can be applied to expanding the methods of measuring performance in this sport in the future. The goal was to verify whether the use of this conversion is applicable in practice. This goal was verified by obtaining data during practical measurements, subsequent analysis of this data, and comparison of the results with other methods currently used for measuring performance in cycling.
|
|
|
QRS complex detector in ECG signals
Kosíř, Kamil ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
The aim of this thesis is to introduce issues and basic principles of QRS complex detection in ECG signals. This work is separated into several parts. The first part deals with anatomy and functions of the heart, for example the emergence and spread of potentials. The next part includes distribution ECG leads and explanation of ECG signal. Afterwards are described some detectors of QRS complex. The main part of this work is realization of two algorithms implemented in Matlab program. The first detector is based on squaring algorithm and the the second is based on a spreading of the signal into several frequency bands. The effectivness of both detectors is tested on signals from CSE library at the end of the work.
|
|
|
Averaging of biological signals
Němeček, Tomáš ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
The main objectives of this thesis are to study theory of signal averaging, filtered residue method and methods of stretching/shrinking signal. It will also test the functionality of those methods. Thesis contains theoretical analysis, explanation of principles and testing of behaving of used methods.
|
guest ::
