Student EEICT 2024: Selected Papers
Permanent URI for this collection
Title: Proceedings II of the 30th Conference STUDENT EEICT 2024
Subtitle: Selected Papers
Publisher: Brno University of Technology, Faculty of Electrical Engineering and Communication
Editor: Assoc. Prof. Vítezslav Novák
Place and year: Brno, 2024
ISBN: 978-80-214-6230-4
ISSN: 2788-1334
https://www.eeict.cz/
Subtitle: Selected Papers
Publisher: Brno University of Technology, Faculty of Electrical Engineering and Communication
Editor: Assoc. Prof. Vítezslav Novák
Place and year: Brno, 2024
ISBN: 978-80-214-6230-4
ISSN: 2788-1334
https://www.eeict.cz/
Browse
Recent Submissions
Now showing 1 - 5 of 51
- ItemDetection of parking space availability based on video(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2024) Kužela, Miloslav; Frýza, TomášThis paper deals with the use of Machine vision and ML (Machine Learning) for a parking lot occupation detection. It presents and compares an already existing technology that solves such a problem with an AI (Artificial Intelligence) usecase. It introduces tools used to train and create such models and their subsequent results as well as a dataset that was used to verify the trained networks and discusses the future of how such a technology could be used to effectively and more affordably detect occupied parking spaces on parking lots.
- ItemFeastibility study and comparative study of air breathing electric propulsion systems operating in very low Earth orbit conditions(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2024) Šťastný, Marek; Dytrych, Tomáš; Dániel, Vladimír; Mrózek, Kryštof; Obrusník, AdamAir Breathing Electric Propulsion (ABEP) systems offer a promising solution to extending the lifetime of Very Low Earth Orbit (VLEO) missions by using residual atmospheric particles as a propellant. ABEP systems need to provide sufficient thrust to compensate for substantial aerodynamic drag present in VLEO environments. The feasibility of operating a hypothetical ABEP system of a given geometry at a given altitude is assessed via Direct Simulation Monte Carlo (DSMC) based on the following parameters: the mean pressure in the ionization chamber, compression factor and drag force acting upon the surface of the given geometry. Atmospheric models were used for reference to ensure realistic VLEO-like conditions. The comparative study is performed using a Global Plasma Model (GPM). A GPM can calculate the volume-averaged quantities of plasma systems with complex physics and reaction kinetics. The results of GPM are compared with a breadboard model of an Electron Cyclotron Resonance (ECR) ABEP system constructed by the Czech aerospace research institute (VZLU a.s.).
- ItemFour Channel Active Antenna Switch for UHF Band Satellite Reception(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2024) Kubeš, Václav; Urbanec, TomášThe aim of this work is to design and implement a complex electronic device, known as an antenna switch, that allows to receive a high-frequency satellite signals in the UHF band via one of five connected antennas at a given time. This device is capable of automatic antenna switching according to non-geostationary satellite position, from which signal is received, thus with suitable antenna selection, is alternative to motorized directional antennas. The device consists of outdoor and indoor unit and Human-Machine interface (HMI). The outdoor unit is driven by a microcontroller which collect diagnostic data about proper function and controls the RF switch. The outdoor unit amplifies the UHF signal too. indoor unit with power inserter, diplexer and USB to serial converter, allows diagnostic data and commands transfer between outdoor unit and users computer with Human-Machine interface.
- ItemMachine Learning-based Fingerprinting Localization in 5G Cellular Networks(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2024) Dinh Le, Thao; Mašek, PavelThis study explores the viability of employing machine learning (ML)-based fingerprinting localization in 5G heterogeneous cellular networks. We conducted an extensive measurement campaign to collect data and utilized them to train three ML models: Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM). The findings reveal that RF delivers the highest accuracy among the three ML algorithms. Furthermore, the results indicate that 5G New Radio (NR) can benefit the most from this localization method due to the dense deployment of base stations, achieving median localization errors of 17.5 m and 106 m during the validation and testing phases, respectively.
- ItemDeployment of deep learning-based anomaly detection systems: challenges and solutions(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2024) Ježek, Štěpán; Burget, RadimVisual anomaly detection systems play an important role in various domains, including surveillance, industrial quality control, and medical imaging. However, the deployment of such systems presents significant challenges due to a wide range of possible scene setups with varying number of devices and high computational requirements of deep learning algorithms. This research paper investigates the challenges encountered during the deployment of visual anomaly detection systems for industrial applications and proposes solutions to address them effectively. We present a model use case scenario from real-world manufacturing quality control and propose an efficient distributed system for deployment of the defect detection methods in manufacturing facilities. The proposed solution aims to provide a general framework for deploying visual defect detection algorithms base on deep neural networks and their high computational requirements. Additionally, the paper addresses challenges related the whole process of automated quality control, which can be performed with varying number of camera devices and it mostly requires interaction with other factory services or workers themselves. We believe the presented framework can contribute to more widespread use of deep learning-based defect detection systems, which may provide valuable feedback for further research and development.