|
|
Anomaly and threat detection in audit logs using machine learning
Ludes, Adam ; Ježek, Štěpán (referee) ; Tomašov, Adrián (advisor)
Tato práce představuje softwarové architektury založené na cloudu, techniky detekce anomálií, strojové učení a analýzu dat za účelem vytvoření modelu pro detekci anomálií v audit lozích z Red Hat OpenShift Container Platform. Jsou představeny statistické metody a analýza časových řad pro detekci anomálií, zatímco jsou implementovány a hodnoceny modely strojového učení a techniky předzpracování dat. Výsledky ukazují omezení tradičních modelů při zpracování anomálií v hluboce vnořených datech, zatímco model zpracovávající přirozený jazyk prokazuje robustní výkon. Tato práce poskytuje cenné poznatky a může být použita jako reference pro výzkum i praxi v oblasti softwarových architektur založených na cloudu, detekce anomálií, strojového učení a analýzy dat.
|
|
|
DEEP LEARNING FOR SINGLE-VOXEL AND MULTIDIMENSIONAL MR-SPECTROSCOPIC SIGNAL QUANTIFICATION, AND ITS COMPARISON WITH NONLINEAR LEAST-SQUARES FITTING
Shamaei, Amirmohammad ; Latta,, Peter (referee) ; Kozubek, Michal (referee) ; Jiřík, Radovan (advisor)
Pro získání koncentrace metabolitů ve vyšetřované tkáni ze signálů magnetické rezonanční spektroskopie (MRS) je nezbytné provézt předzpracování, analýzu a kvantifikaci MRS signálu. Rychlý, přesný a účinný proces zpracování (předzpracování, analýza a kvantifikace) MRS dat je však náročný. Tato práce představuje nové přístupy pro předzpracování, analýzu a kvantifikaci MRS dat založené na hlubokém učení (DL). Navržené metody potvrdily schopnost použití DL pro robustní předzpracování dat, rychlou a efektivní kvantifikaci MR spekter, odhad koncentrací metabolitů in vivo a odhad nejistoty kvantifikace. Navržené přístupy výrazně zlepšily rychlost předzpracování a kvantifikace MRS signálu a prokázaly možnost použití DL bez učitele. Z hlediska přesnosti byly získány výsledky srovnatelné s tradičními metodami. Dále byl zaveden standardní formát dat, který usnadňuje sdílení dat mezi výzkumnými skupinami pro aplikace umělé inteligence. Výsledky této studie naznačují, že navrhované přístupy založené na DL mají potenciál zlepšit přesnost a efektivitu zpracování MRS dat pro lékařskou diagnostiku. Disertační práce je rozdělena do čtyř částí: úvodu, přehledu současného stavu výzkumu, shrnutí cílů a úkolů a souboru publikací, které představují autorův přínos v oblasti aplikací DL v MRS.
|
|
|
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.
|
|
|
Correction of the concept of drift in prediction models
Michálková, Eva ; Provazník, Valentine (referee) ; Schwarzerová, Jana (advisor)
The main goal of this bachelor thesis is the analysis of concept drift in metabolomics. Concept drift is an undesirable phenomenon and can be caused by nonstationary data. It can have a negative impact on the performance and reliability of predictive modelling. This challenge can be solved by concept drift detection and subsequent correction. One of the fields where this issue has recently emerged is metabolomic diagnostics. Metabolomic data analysis can lead to early detection of several serious diseases, which can help with the recovery process. When diagnosing an illnes predictive models present a way to make the process more efficient, faster and give the option of personalization. The first part of this thesis specifies concept drift, it’s detection and correction methods and the importance of metabolomics and prediction models. The second part deals with the implementation of some available algorithms for concept drift detection and correction and the implementation of automatic concept drift correction. Finally, in the second part results and their discussion are described.
|
|
|
Classification of board defects in semiconductor manufacturing
Jašek, Filip ; Vágner, Martin (referee) ; Dřínovský, Jiří (advisor)
This diploma thesis focuses on detecting defects in semiconductor wafer manufacturing. It explores methods for identifying faulty chips and controlling yield during production. To classify defects machine learning techniques are used. Initially, ResNet18 architecture was used for inference, but low accuracy was attributed to limited input data. Transfer learning with ResNet50v2 was then attempted, resulting in improved metric with different dataset. Hyperparameter tuning and data augmentations were also explored. The study found that autoencoders for data compression during inference increased speed but led to degraded evaluation metrics.
|
|
|
Machine Learning from Intrusion Detection Systems
Dostál, Michal ; Očenášek, Pavel (referee) ; Hranický, Radek (advisor)
The current state of intrusion detection tools is insufficient because they often operate based on static rules and fail to leverage the potential of artificial intelligence. The aim of this work is to enhance the open-source tool Snort with the capability to detect malicious network traffic using machine learning. To achieve a robust classifier, useful features of network traffic were choosed, extracted from the output data of the Snort application. Subsequently, these traffic features were enriched and labeled with corresponding events. Experiments demonstrate excellent results not only in classification accuracy on test data but also in processing speed. The proposed approach and the conducted experiments indicate that this new method could exhibit promising performance even when dealing with real-world data.
|
|
|
Interpreting the learning process of an atrial fibrillation classifier
Lichtblauová, Anna ; Ředina, Richard (referee) ; Novotná, Petra (advisor)
In the theoretical part of the bachelor thesis the problems of atrial fibrillation (AF) detection and principles of convolutional neural networks (CNN) are discussed. Next, two classifiers were created in the practical part. The first was designed to classify sinus rhythm, atrial fibrillation and other pathologies, while the second further distinguished the category "atrial fibrillation" according to whether it was present in the whole recording or only in a part of it. The resulting accuracies are 82.12 \% and 85.14 \% for the first and second classifiers, respectively.
|
|
|
Identification of specified segments in the audio signal using machine learning
Pařízek, Radim ; Galáž, Zoltán (referee) ; Zvončák, Vojtěch (advisor)
The bachelor thesis deals with the design of a system for the identification of natural environmental sounds in audio recordings. The datasets and models used for this type of tasks are surveyed and their structure is described. A system for the identification of sounds in one layer and in two layers has been proposed for seven selected labels. The classifier used for this system was created by fine-tuning a transformer model from the Hugging Face platform. The results of two training approaches and one identification system were evaluated.
|
|
|
Approximation of functions determining colony activity using neural networks
Nevláčil, Jakub ; Ligocki, Adam (referee) ; Honec, Peter (advisor)
Bees as a primary pollinator are an indispensable contribution to global agriculture and food production. However, their numbers have been constantly declining in recent times, primarily due to climate change, parasites or the effect of pesticide use. Understanding their behavior and reliably determine their activity and health could significantly prevent or slow down their decline. That is why this work deals with the development of a device for the acquisition of useful data from beehives, which could be used to determine the activity and health of the bees. Furthermore, this work deals with analysis of the accumulated data using machine learning methods with an emphasis on determining the activity and health of the bees.
|
|
|
Application of Machine Learning for Prediction of Mechanical Properties of Mortars and Concretes
Prudil, Matěj
This paper deals with the application of machine learning (ML) in the field of concrete technology. Two databases of test mortars and concretes were created from selected academic theses, which include mechanical properties in relation to their composition. These databases were used to develop two ML models that predict the mechanical properties of mortars and concretes depending on their composition. The mortar test database contains a total of 242 mechanical property records and the concrete test database contains 111 records. The materials in the database are CEM I, CEM II and CEM III cements combined with additives such as ground granulated blast furnace slag, high temperature fly ash and micro-ground limestone.
|
guest ::
