Jiří Švub

Dr. Jiří Švub

VSB - Technical University of Ostrava
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 August 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
VHVěroslav Holuša
Věroslav Holuša
MVMichal Vaněk
Michal Vaněk
FBFilip Beneš
Filip Beneš
JŠJiří Švub
Jiří Švub
PSPavel Stasa
Pavel Stasa
The paper deals with the possibilities of using Virtual Reality in the training and safety of enterprises active in the raw materials industry. It examines the influence and impact on their employees. The main impetus for starting research in this area has been a need for more use of the full potential of Virtual Reality in the industrial sector. Virtual Reality (VR) has become a promising education and employee training tool. It provides an immersive and interactive learning environment, allowing users to engage with simulations, scenarios, and simulations in real time. VR can facilitate the acquisition of practical skills, help learners retain information better, and foster the development of soft skills, such as communication, teamwork, and leadership. The paper is divided into the following sections. The first two are devoted to the introduction to the issue and a review of the literature. The materials and methods section describes the possibilities of using photogrammetry to create virtual scenes and 3D models usable in Virtual Reality. This section also describes the research methods used to evaluate the approach for teaching and training employees. The last two sections evaluate and discuss the results achieved. Having regarded the research realized, it was found that our approach to researching the education of employees and the development of their skills brings excellent benefits and, compared to the traditional educational approach, is much more time-efficient so that employees can improve their work habits and behavior in a relatively short period. In employee training, VR can simulate real-life scenarios, providing workers with hands-on experience in a safe, controlled environment. This technology can also help companies save time and resources, eliminating the need for travel and reducing expenditure on expensive equipment. However, despite its many benefits, VR in education and training can be cost-demanding and requires specialized hardware and software, which may limit its widespread adoption.

19 September 2020 in Mathematics
Verified
Journal Article
Open access
PDF file
Ganjar AlfianGanjar Alfian
Ganjar Alfian
MSMuhammad Syafrudin
Muhammad Syafrudin
NFNorma Latif Fitriyani
Norma Latif Fitriyani
Muhammad AnshariMuhammad Anshari
Muhammad Anshari
PSPavel Stasa
Pavel Stasa
JRJongtae Rhee
Jongtae Rhee
Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

25 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
FBFilip Beneš
Filip Beneš
PSPavel Stasa
Pavel Stasa
JŠJiří Švub
Jiří Švub
Ganjar AlfianGanjar Alfian
Ganjar Alfian
YKYong-Shin Kang
Yong-Shin Kang
JRJongtae Rhee
Jongtae Rhee
As a part of the supply chain, inventory management includes, among other things, maintaining the storage of stock, controlling the amount of product for sale and order fulfilment. In business terms, inventory management means the right stock, at the right levels, in the right place, at the right time. In the case of large outdoor warehouses, common identification methods are lengthy and inappropriate. One way to determine inventory easily and quickly is to deploy UAV’s (unmanned aerial vehicle) for product identification purposes. In this case, however, there is a problem in determining where the goods are located. A drone moves at higher altitudes, which can lead to a situation where we will not be able to determine the exact location of the goods. This article deals with a method of determining the correct flight level suitable to distinguish the identified items located at least 2 m apart. The evaluation is performed based on an RSSI (received signal strength indicator) value. The experiment proved that even at maximum reading distance of selected passive UHF RFID tags the two objects can be distinguished.

1 May 2015
Verified
Conference Paper
Closed access
ZNZdenek Neustupa
Zdenek Neustupa
Roman DanelRoman Danel
Roman Danel
PSPavel Stasa
Pavel Stasa
FBFilip Beneš
Filip Beneš
JŠJiří Švub
Jiří Švub
Every company and institution faces the necessity to manage its inventory. For high accuracy, security and easy operation of inventory management system it is necessary to have an easily recognizable identifier on all managed objects. The aim of our present project is to modernize the methods of automatic inventory management and asset protection with the help of the application of radio frequency identification technology (RFID hereinafter) to automatically identify the occurrence of marked objects. During the solutions we have to deal with many obstacles such as the bindings of data flowing from RFID system with internal information systems of asset owner companies. Appropriate choice of tags for individual subjects, their testing and readability experiments also have to be done. Another important part of the solution, that has to be developed in the project, is the system of reading gates. The gates are integrated in the door frames to allow automated identification of the objects brought in and out of the selected room. By modifying of mentioned solution we also introduce the design of a gatehouse that is able to prevent theft or unauthorized take away of material and equipment. In contrast, when the permitted items are taken away the system can easily generate the necessary forms to manage status of selected objects, decreasing the administrative burden. The result of the project is a solution consisting of information system and described hardware components for inventory management. The information system is possible to integrate with corporate ERP information systems. The pilot project was implemented and tested at VřB laboratories and we suppose deployment of the system in close future in cooperation with TINT Ltd. Company.

1 May 2015
Verified
Conference Paper
Closed access
OKOldrich Kodym
Oldrich Kodym
FBFilip Beneš
Filip Beneš
JŠJiří Švub
Jiří Švub
Internet of Things philosophy implementation in conditions of the existing communication networks requires new types of services and interoperability. Once of the desired innovations is communication between existing IP world and the new generation network. Not just networks of smart devices that may not always have IP connectivity, but also other RFID-labeled objects and sensors. Fulfilling the need for high-quality applications for further more specific parameters of these objects internet of things, as may be location, serial number, distinctive and unique characters/connections, can add a proper extension of the existing network and system infrastructure with new information and naming service. Their purpose is not only to assign a unique identifier to the object, but also allow users to new services use other information associated with the selected object. The technology that enables the data processing, filtering and storage is defined in the Electronic Product Code Application Framework (EPCAF) as RFID middleware and EPCIS. One of the implementations of these standards is the Open Source solution Fosstrak. We experimented with Fosstrak system that was developed on Massachusetts Institute of Technology (MIT) by an academic initiative but nowadays we are going to prove its benefits in the context of business environment. The project is aimed also on connection and linking between systems of the EPCIS class made by the ONS systems.

20 November 2017 in International Journal of Mining, Reclamation and Environment
Verified
Journal Article
Closed access
PSPavel Stasa
Pavel Stasa
FBFilip Beneš
Filip Beneš
JŠJiří Švub
Jiří Švub
In this paper, the possibilities of alternative approach to the visual presentation of computer fluid dynamics modelling results are discussed. Related work and physical background are mentioned first, followed by the experimental results. The paper is focused mainly on the interpretation of the data obtained from the models’ simulation process with the help of Augmented Reality. The experimental deployment offers promising results and presents the way for further development in this field.