|
|
Behavioral Analysis of DDoS Network Attacks
Kvasnica, Ondrej ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
This bachelor thesis deals with anomaly detection in computer networks using artificial intelligence method. Main focus is on the detection of DDoS attacks based on the information from the lower layers of the OSI model. The target is to design and implement a system that is capable of detecting different types of DDoS attacks and characterize common features among them. Selected attacks are SYN flood, UDP flood and ICMP flood. Description and feature selection of the attacks is included. Furthermore, a system is designed that evaluates whether the network traffic (organized into flows) is a DDoS attack or not. Attacks are detected using the XGBoost method, which uses supervised learning. The final model is validated using cross-validation and tested on attacks generated by the author.
|
|
|
Finding guanine quadruplexes in DNA using decision trees
Kotrys, Kryštof ; Šťastný, Jiří (referee) ; Kaura, Patrik (advisor)
This bachelor’s thesis is focused on creating a functional decision tree model for detection of guanine quadruplexes in the DNA. The first part of the thesis summarizes theoretical knowledge in the fields of local DNA structures, computational prediction methods of guanine quadruplexes and decision trees. The second part describes the creation of a decision tree model, followed by a statistical comparison of the results with the G4Hunter algorithm.
|
|
|
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 %.
|
|
|
System of secured actigraph data transfer and processing
Mikulec, Marek ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
The new Health 4.0 concept brings the idea of combining modern technologies from field of science and technology with research in healthcare and medicine. This work realizes a system of secured actigraph data transfer and preprocessing based on the concept of Health 4.0. The system is successfully designed, implemented, tested and secured. With the help of a non-invasive method of monitoring the movement and temperature of the subject using the GENEActiv actigraph allows the system to securely transfer, process and evaluate the subject's sleep data using the machine learning algorithm XGBoost. The proposed system is in accordance with the valid law of the Czech Republic and meets legal requirements.
|
|
|
The use of artificial intelligence methods for time series prediction
Tripathi, Ankit
Financial market analysis and prediction have been topics of interest to traders and investors for decades. This thesis presents a comprehensive study on time series forecasting in the dynamic financial market of India, utilising a decade of historical data from Reliance Company's stock prices. The research encompasses three key components: bibliometric analysis for the domain globally, comparative evaluation of time series prediction methods in Indian markets, and implementation of a pre-processing approach incorporating economic factors on the selected models. Every section builds upon the collected information in the preceding section. The bibliometric analysis was used to establish an understanding of prevailing trends in time series forecasting techniques and answer relevant questions in the context of Indian markets to narrow down the scope of the study. This has been done by analysing 2202 documents ranging from the period of 1994-2023 consisting of articles, book chapter, review, book, note and letters in the English language only. The results help in the formation of a different perspective while understanding the overall intellectual landscape of the domain with subsections focusing on field leaders, author's productivity, uprise in domain based on publications and citations, the underlying pattern behind shifts in research areas based on authors keywords and publications that have impacted the domain significantly. The analysis extends beyond academic literature to include patents, providing a real-life state-of-the-art perspective. The results from bibliometrics have been used to select models for comparative analysis. The analysis assesses the performance of diverse time series prediction methods like deep learning algorithms (Long short-term memory model (LSTM)), traditional statistical models (Auto Regressive Integrated Moving Approach (ARIMA)), and advanced ensemble learning algorithms (XGBoost and FB-Prophet) using real-world data from the Indian financial market. The stock prices of Reliance Company serve as a case study, enabling a thorough evaluation of predictive accuracy and errors of the models. Simultaneously, a pre-processing approach has been proposed and implemented, integrating significant economic factors (Gold Price, USD to INR conversion, Consumer Price Index, Indian 10-year yield bond, and Wholesale Price Index) and evaluated with technical metrics (Mean squared error, Mean Absolute Error, R2 Score). The study investigates how the inclusion of these factors impacts prediction accuracy across the selected time series prediction methods. The comparative evaluation of models before and after the pre-processing method sheds light on the evolving predictive accuracy of LSTM, ARIMA, FB-Prophet, and XGBoost. This analysis provides valuable insights into the influence of economic factors on each method's performance. The study showed that the SARIMAX (extension of ARIMA with seasonality and exogenous factors) and XGBOOST performed relatively well with the proposed approach while LSTM with 80% training and FB prophet did not perform as expected in Indian financial markets. This research contributes to advancing the understanding of time series forecasting in the financial market of India, offering practical insights for decision-makers and researchers.
|
|
|
Remodeling of the intima-media complex of the common carotid artery and left ventricle myocardium in patients with primary and secondary hypertension
Majtan, Bohumil ; Holaj, Robert (advisor) ; Piťha, Jan (referee) ; Danzig, Vilém (referee)
Arterial hypertension ranks among the most prevalent cardiovascular disorders and represents one of the most significant risk factors for cardiovascular morbidity and mortality. Beyond hypertension itself, additional hemodynamic and neuroendocrine influences contribute to the pathological mechanisms that induce structural alterations in the cardiovascular system. Of notable importance in this process is the excessive production of aldosterone and catecholamines. The objective of the research has been to study the impact of aldosterone and catechola- mine excess on intima-media complex remodeling in the common carotid artery and left ventricular wall in primary aldosteronism (PA) and pheochromocytoma (PHEO) patients. Texture analysis of the intima-media complex of the common carotid artery was conducted in 33 PA patients, 52 EH patients, and 33 normotensive individuals. 140 Haralick features and 10 wavelets were analyzed and utilized to train an XGBoost classifier. Additionally, the intima-media thickness (IMT) of the common carotid artery and left ventricular mass index (LVMi) were examined in 50 PHEO patients before and 5 years post- adrenalectomy and compared to 50 EH patients. In differentiating between PA and EH, we achieved a classification accuracy of 73 %, compared to the clinical gold...
|
|
|
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.
|
|
|
Design of a Predictive User Loyalty Model Based on Machine Learning
Kuchtová, Dominika ; Bartík,, Vladimír (referee) ; Doubravský, Karel (advisor)
The bachelor thesis focuses on creating an optimal model for evaluating specific phenomena related to modeling customer behavior with the aim of support decision-making. It describes the process of data handling and the significance of the importance of converting data into knowledge. The first part of the bachelor thesis includes a description of the tools, processes, ideas, and methods used in the practical part at a theoretical level for an easier understanding of how to solve the assignment in the practical part of the thesis. The second part of the bachelor thesis includes the practical application of specific procedures and the creation of the actual predictive model based on the XGBoost ensemble method and its optimization.
|
|
|
Behavioral Analysis of DDoS Network Attacks
Kvasnica, Ondrej ; Homoliak, Ivan (referee) ; Očenášek, Pavel (advisor)
This bachelor thesis deals with anomaly detection in computer networks using artificial intelligence method. Main focus is on the detection of DDoS attacks based on the information from the lower layers of the OSI model. The target is to design and implement a system that is capable of detecting different types of DDoS attacks and characterize common features among them. Selected attacks are SYN flood, UDP flood and ICMP flood. Description and feature selection of the attacks is included. Furthermore, a system is designed that evaluates whether the network traffic (organized into flows) is a DDoS attack or not. Attacks are detected using the XGBoost method, which uses supervised learning. The final model is validated using cross-validation and tested on attacks generated by the author.
|
|
|
Finding guanine quadruplexes in DNA using decision trees
Kotrys, Kryštof ; Šťastný, Jiří (referee) ; Kaura, Patrik (advisor)
This bachelor’s thesis is focused on creating a functional decision tree model for detection of guanine quadruplexes in the DNA. The first part of the thesis summarizes theoretical knowledge in the fields of local DNA structures, computational prediction methods of guanine quadruplexes and decision trees. The second part describes the creation of a decision tree model, followed by a statistical comparison of the results with the G4Hunter algorithm.
|
guest ::
