Jiří Koziorek

Prof. Jiří Koziorek

orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
11 September 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ABAlexander Brecko
Alexander Brecko
Erik KajatiErik Kajati
Erik Kajati
JKJiří Koziorek
Jiří Koziorek
Iveta ZolotovaIveta Zolotova
Iveta Zolotova
New technologies bring opportunities to deploy AI and machine learning to the edge of the network, allowing edge devices to train simple models that can then be deployed in practice. Federated learning (FL) is a distributed machine learning technique to create a global model by learning from multiple decentralized edge clients. Although FL methods offer several advantages, including scalability and data privacy, they also introduce some risks and drawbacks in terms of computational complexity in the case of heterogeneous devices. Internet of Things (IoT) devices may have limited computing resources, poorer connection quality, or may use different operating systems. This paper provides an overview of the methods used in FL with a focus on edge devices with limited computational resources. This paper also presents FL frameworks that are currently popular and that provide communication between clients and servers. In this context, various topics are described, which include contributions and trends in the literature. This includes basic models and designs of system architecture, possibilities of application in practice, privacy and security, and resource management. Challenges related to the computational requirements of edge devices such as hardware heterogeneity, communication overload or limited resources of devices are discussed.

26 October 2022 in Archives of Computational Methods in Engineering
Verified
Journal Article
Open access
PDF file
RJRene Jaros
Rene Jaros
RBRadek Byrtus
Radek Byrtus
JDJakub Dohnal
Jakub Dohnal
LDLukas Danys
Lukas Danys
JBJan Baros
Jan Baros
Radek MartinekRadek Martinek
Radek Martinek
Condition monitoring of induction motors (IM) among with the predictive maintenance concept are currently among the most promising research topics of manufacturing industry. Production efficiency is an important parameter of every manufacturing plant since it directly influences the final price of products. This research article presents a comprehensive overview of conditional monitoring techniques, along with classification techniques and advanced signal processing techniques. Compared methods are either based on measurement of electrical quantities or nonelectrical quantities that are processed by advanced signal processing techniques. This article briefly compares individual techniques and summarize results achieved by different research teams. Our own testbed is briefly introduced in the discussion section along with plans for future dataset creation. According to the comparison, Wavelet Transform (WT) along with Empirical Mode Decomposition (EMD), Principal Component Analysis (PCA) and Park’s Vector Approach (PVA) provides the most interesting results for real deployment and could be used for future experiments.

5 September 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RHRadim Hercík
Radim Hercík
RBRadek Byrtus
Radek Byrtus
RJRene Jaros
Rene Jaros
JKJiří Koziorek
Jiří Koziorek
This study deals with the technology of autonomous mobile robots (AMR) and their implementation on the SmartFactory production line at the Technical University of Ostrava. The task of the mobile robot is to cooperate with the production line, take over the manufactured products, and then deliver them. The content also includes a description of the individual steps that were necessary to make the mobile robot operational, such as loading a virtual map of the space, creating a network for communication with the mobile robot, and programming it. The main part of the experiment deals with testing the accuracy of moving the mobile robot to each position and establishing communication between the production line and the mobile robot. A high accuracy is a necessity in this process. The result of the study is the configuration of the autonomous mobile robot. The repetitive precision of the approach of the autonomous mobile robot to a position is ±3 mm.

1 November 2016 in Applied Energy
Verified
Journal Article
Closed access
NRNada Rapantova
Nada Rapantova
PPPavel Pospíšil
Pavel Pospíšil
JKJiří Koziorek
Jiří Koziorek
PVPetr Vojcinak
Petr Vojcinak
DGDavid Grycz
David Grycz
ZRZdenek Rozehnal
Zdenek Rozehnal

1 February 2021 in Robotics and Computer-Integrated Manufacturing
Verified
Journal Article
Closed access
JMJozef Mocnej
Jozef Mocnej
APAdrian Pekar
Adrian Pekar
WSWinston K.G. Seah
Winston K.G. Seah
PPPeter Papcun
Peter Papcun
EKErik Kajati
Erik Kajati
Iveta ZolotovaIveta Zolotova
Iveta Zolotova

1 August 2018
Verified
Conference Paper
Closed access
PPPeter Papcun
Peter Papcun
Erik KajatiErik Kajati
Erik Kajati
JKJiří Koziorek
Jiří Koziorek
Smart industry and the concept of Industry 4.0 bring new solutions, architectures, and technologies to industry and manufacturing. Some of these concepts have evolved. For example, Web 4.0, Operator 4.0, Society 5.0 and many other Technologies X.0. Among others, the Human Machine Interface has also changed from buttons and diodes in control rooms, through web visualization to cognitive and intelligent space. This paper describes this evolution and provides examples of solutions or case studies for every generation in this evolution.