|
|
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.
|
|
|
Knowledge Discovery from Data of an Insurance Company
Kříž, Ondřej ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
This bachelor thesis deals with the issue of knowledge discovery from databases. Its aim is to compile algorithmically processable datasets from operational data of an unnamed insurance company, which will subsequently be analyzed by functions of the scikit-learn library in the Python language using various classification algorithms and the FP-growth algorithm in the area of creating strong association rules and subsequent evaluation of results.
|
|
|
Application of deep learning in sleep apnea detection
Láznička, Jakub ; Šaclová, Lucie (referee) ; Králík, Martin (advisor)
The master thesis focuses on the use of deep learning methods for the detection of sleep apnea, a sleep disorder characterized by repeated episodes of cessation or significant reduction in airway flow during sleep. The study investigates the effectiveness of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) models in the automatic detection of different types of sleep apnea using polysomnographic recordings. The datasets used in this work are from the MESA database, which have been specially prepared and modified for deep learning. The best performing models achieved F1-scores of 0.87 and 0.83, showing that deep learning can provide accurate tools for sleep apnea diagnosis, representing a potential improvement in clinical practice. The paper also discusses the possibilities of integrating these models into clinical diagnostic processes and outlines directions for future research in this area.
|
|
|
Acoustic analysis of emotionally affected sentences in patients with Parkinson's disease
Gavlasová, Radka ; Kováč, Daniel (referee) ; Mekyska, Jiří (advisor)
This thesis focuses on Parkinson's disease and its effect on emotional expression in speech. The aim was to conduct a literature search on acoustic emotional analysis of PD patients and to implement acoustic parameters to distinguish between healthy and diseased individuals. The database used contained recordings of 100 patients with PD and 52 healthy controls for various speech tasks. For this analysis, 7 emotionally coloured sentences and 11 acoustic parameters were selected and implemented in Python. From the statistical analysis, it was found that the most significant parameters include pauses in speech and intensity variability. The XGBoost algorithm with 10-fold stratified cross-validation was used for classification. A total of 10 models were implemented to analyze all tasks together and each task separately. Optimization was performed using randomized search. For the combination of all tasks, the significant parameter was the variability in intensity or speech rate. For the individual speech tasks, variability in intonation and formant areas was highly significant. The best model achieved a 63% success rate (BACC) and 85% sensitivity. The results suggest that emotional prosody affects classification, confirming previous findings and pointing to the need for further investigation in this area.
|
|
|
Regeneration of brownfields in the South Bohemian Region
ŠÁDKOVÁ, Pavla
The thesis on the topic of Brownfield Regeneration in the South Bohemian Region deals with a comprehensive approach to the analysis and regeneration of brownfields in the South Bohemian Region. The main objective of the thesis is to analyse and synthesize the ecological, social, and economic impacts of brownfield and greenfield regeneration on selected sites in the South Bohemian Region. A combination of quantitative and qualitative research methods was used to achieve the goals of the thesis. The work is divided into two parts, theoretical and practical. The theoretical part focuses on defining the issues of brownfields, evaluating the development and current state. It includes possible ways of classifying brownfields and methods of financing. In the second, practical part, a comparison of selected brownfields and greenfields in the South Bohemian Region is conducted. The sites are evaluated according to the model of the South Bohemian Region, which is based on a study by the German Ministry of the Environment and is based on the scoring of given criteria and their parameters. The model consists of 3 criteria - potential from the perspective of the municipality, potential from the perspective of the investor, and the change in the value of the site. Based on these, the significance of the sites is evaluated. Through the comparison of the Preference Index, the thesis subsequently presents a selection of sites suitable for implementation, including a proposal for future use. The outputs of the thesis contribute to a deeper understanding of the issues of brownfield regeneration and offer suggestions for the effective use of the potential of these sites to support the local economy and improve the quality of life for residents.
|
|
|
Encrypted video-stream identification
MACÁK, Tomáš
The aim of this thesis is to create a data set of measured encrypted video streams and subsequently try to discover if it is possible to identify the content of those streams. In the theoretical part the on - demand video streaming is introduced and then suitable machine learning models applicable to solve this problem are presented. The works focused on a similar topic are presented next. In followed practical part the already mentioned data set is created. This set is then analysed and it is determined if there is a way how to represent those measured video streams for later content identification with use of statistical and machine learning models. In the last part of this chapter the machine learning models for classification and similarity detection are implemented and trained. The models are then tested and the results are summarised and compared.
|
|
|
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.
|
|
|
Health assessment using smart devices
Vargová, Enikö ; Filipenská, Marina (referee) ; Němcová, Andrea (advisor)
This thesis deals with the possibilities of non-invasive determination of blood glucose from photoplethysmographic signals. Elevated blood sugar is often associated with disease called diabetes mellitus. Diabetes is one of the world’s major chronic diseases. Untreated diabetes is often a cause of death. The aim of the work is to propose methods for glycemic classification and prediction. Two datasets have been created by recording the PPG signals using two smart devices (a smart wristband and a smartphone), along with their blood glucose levels measured in an invasive way. The PPG signals were preprocessed, and suitable features were extracted from them. Various machine-learning models for glycemic classification and prediction were created.
|
|
|
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.
|
|
|
Metasearch for Reviews on the Czech Web
Šmahel, Michal ; Doležal, Jan (referee) ; Smrž, Pavel (advisor)
The main purpose of this work is to create a metasearch engine for review articles with built-in sentiment analysis. In addition, a complex survey of main text extraction tools and web browser automation tools for web crawling has been carried out to achieve of the best possible results. The resulting metasearch engine provides a web interface for searching relevant review articles, thus saving time spent on manual searching. Thanks to multi-level transformer-based filtering, it can return 10—15 relevant review articles on frequently reviewed topics in about 4 minutes with no effort, just by clicking on a button.
|
guest ::
