Search in Publications

Found 6374 publications

Optimizing Video Resolution for Machine Learning-Based Traffic Monitoring Systems: A Performance Analysis

Ferenc Erdos Enas Elshebli

Publication Name: International Conference on Engineering and Emerging Technologies Iceet

Publication Date: 2024-01-01

Volume: Unknown

Issue: 2024

Page Range: Unknown

Description:

This study explores the impact of video resolution on the performance of machine learning-based traffic monitoring systems. Using a combination of empirical analysis and theoretical modeling, we assess how different resolutions affect detection accuracy, resource consumption, and computational efficiency. While other factors such as noise level, or compression artifacts also influence performance, resolution was chosen as a primary variable due to its critical role in balancing detail capture and computational cost. Higher resolutions can enhance object detection accuracy but also significantly increase data processing demands, making resolution a key trade-off in designing efficient surveillance systems. Findings of this study show significant insights into these trade-offs, guiding transportation authorities and system developers in making informed decisions to design scalable traffic monitoring solutions that meet the demands of modern urban environments.

Open Access: Yes

DOI: 10.1109/ICEET65156.2024.10913642

Accelerating unstructured finite volume computations on field-programmable gate arrays

Csaba Nemes Antal Hiba Zoltán Nagy András Kiss Árpád Csík Péter Szolgay Miklõs Ruszinkõ

Publication Name: Concurrency and Computation Practice and Experience

Publication Date: 2014-03-10

Volume: 26

Issue: 3

Page Range: 615-643

Description:

In the paper, an field-programmable gate array (FPGA)-based framework is described to efficiently accelerate unstructured finite volume computations where the same mathematical expression has to be evaluated at every point of the mesh. The irregular memory access patterns caused by the unstructured spatial discretization are eliminated by a novel mesh node reordering technique, and a special architecture is designed to fully utilize the benefits of the predictable memory access patterns. In the proposed architecture, a fixed-size moving window of the input stream of the reordered state variables is cached into the on-chip memory and a pipelined chain of processing elements, which gets input only from the fast on-chip memory, is used to carry out the computations. The arithmetic unit (AU) of the processing elements is generated from the data flow graph extracted from the given mathematical expression. The data flow graph is partitioned with a novel graph partitioning algorithm to break up the AU into smaller locally controlled parts, which can be more efficiently implemented in FPGA than the globally controlled AU. The proposed architecture and algorithms are presented via a case study solving the Euler equations on an unstructured mesh. On the currently available largest FPGA, the generated architecture contains three processing elements working in a pipelined fashion to provide one order of magnitude speedup compared with a high performance microprocessor and three times speedup compared with a high performance graphics processing unit. Copyright © 2013 John Wiley & Sons, Ltd. Copyright © 2013 John Wiley & Sons, Ltd.

Open Access: Yes

DOI: 10.1002/cpe.3022

Guidelines of proposal writing and project descriptions

J. Varsányi I. D. Mikus

Publication Name: Innovations in E Learning Instruction Technology Assessment and Engineering Education

Publication Date: 2007-12-01

Volume: Unknown

Issue: Unknown

Page Range: 157-162

Description:

This article deals with the relevant success factors of proposal writing and project description, based on long range experiences in the area of Leonardo and other large projects of skills development in Eastern-European regions. Authors emphasize the role of establishment and professionality in the proposal writing and project success. The article offers a framework and practical guidelines for trainers of proposal writing as well. © 2007 Springer.

Open Access: Yes

DOI: 10.1007/978-1-4020-6262-9_28

Mobile Robot Environment Representation Through Fuzzy Signatures-Integrated Quadtrees

Csaba Hajdu Ahmet Mehmet Karadeniz Laszlo T. Koczy

Publication Name: Romanian Journal of Information Science and Technology

Publication Date: 2025-01-01

Volume: 28

Issue: 1

Page Range: 103-116

Description:

This paper presents an innovative environment representation technique for mobile robots, incorporating obstacle detection within their operational space. Leveraging the fuzzy signature method, this approach uses quadtrees for efficient data organization. A set of fuzzy rules evaluates feature points to ascertain the relevance of identified obstacles. These points and their fuzzy associations are systematically arranged using a quadtree structure. The environmental model is reconstructed by traversing this tree and applying the established fuzzy rules. This paper has achieved a high-resolution grid representation of 0.1m within a 20m×20m area. Notably, the inference operation completes in just 0.5 ms, underscoring the method’s efficiency. Additionally, the technique is optimized for low memory consumption, demonstrating effective resource management even on older PCs, such as an Intel Core Duo 2 with 16 GB RAM. This representation is designed to support advanced robotic functions, such as obstacle navigation in a distributed computing environment.

Open Access: Yes

DOI: 10.59277/ROMJIST.2025.1.09

Description of rail track geometry deterioration process in hungarian rail lines no. 1 and no. 140

Richárd Nagy

Publication Name: Pollack Periodica

Publication Date: 2017-12-01

Volume: 12

Issue: 3

Page Range: 141-156

Description:

The aim was the perfection of an analytic examination, which describes the track deterioration process, characterized the correspondences more precisely and better to use in practice. This method was based on the destruction's theory of the railway track geometry and it exploited the possibilities of recent computer technology. More than one million measuring car (FMK-004) data were processed than analyzed and defined by configuring and programming a new method. The results of this method were descriptive functions, which afford interpretable information about the geometrically destruction's occurrences of the different railway lines.

Open Access: Yes

DOI: 10.1556/606.2017.12.3.13

Enhanced emulated digital CNN-UM (CASTLE) arithmetic cores

P. Keresztes Timót Hidvégi Péter Szolgay

Publication Name: Journal of Circuits Systems and Computers

Publication Date: 2003-12-01

Volume: 12

Issue: 6

Page Range: 711-738

Description:

An emulated digital CNN-UM (CASTLE) architecture was published few years ago.1 Different emulated digital CNN-UM architectures are analyzed in the paper. These new modified architectures are optimized according to the silicon area, operating speed or dissipated power. A reconfigurable arithmetic core will also be shown in the paper, by which solution of the neighborhood size can be changed. An advanced CASTLE with pipe-lining is presented. The operation frequency is increased by using this solution in approximately 10 times.

Open Access: Yes

DOI: 10.1142/S0218126603001136

Induction Motor Energy Efficiency Investigation †

Istvan Szenasy Dániel Csikor

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

The energy efficiency of the induction motor (IM) is extremely important in the drives of electric vehicles. The first part of the article examines the possibilities of modifying the torque and efficiency curves in order to realize high-torque work points more efficiently by modifying the motor’s impedances. Later, it analyzes the flux-dependent changes in the highly load-dependent efficiency based on the literature. The FEM-type investigations of the experimental IM development carried out at the Vehicle Industry Research Center Institute of the Széchenyi István University offer new control options for increasing the efficiency of work points with lower torque and speed as well as for modifying the examined torque curve sections.

Open Access: Yes

DOI: 10.3390/engproc2024079075

Relationships between cycle theories, sustainable tourism, and the effects of the COVID-19 in Hungary

Laszlo Vasa Bulcsú Remenyik Dániel Horváth

Publication Name: Economic Annals Xxi

Publication Date: 2020-01-01

Volume: 185

Issue: 9-10

Page Range: 79-90

Description:

Examining cycle theories calls our attention to the fact that tourism will be described by descending and ascending curves within certain periods in the future. According to cycle theories, the downturn in the tourism industry will continue from four to five years. According to the study conducted by the authors, domestic tourism will become more intensive, trips will have spatial limitations, the length of stay will increase, and cars will be the most popular means of transport. As part of the research, the authors surveyed 230 respondents concerning tourism activities. An in-depth interview was carried out with Zoltán Somogyi, a former Deputy Secretary General of the UNWTO, about the possibilities of solving the effects of COVID-19. To address COVID-19 challenges, the Hungarian government is required to make quick decisions. Demand needs to be diversified, and new sustainable tourism products need to be introduced. Visits to Hungary should be extended in space and time, and an interest in domestic tourists in the state should be increased by implementing strong marketing. More serious regulations should be adopted with the participation of local entrepreneurs; more consideration should be given to contactless technologies. In the post-COVID-19 period, the overtourism in Hungary should be replaced by sustainable and creative tourism.

Open Access: Yes

DOI: 10.21003/EA.V185-08

Discovering smart cities’ potential in Kazakhstan: A cluster analysis

Laszlo Vasa Anel A. Kireyeva Kuralay Nurgaliyeva Akan Nurbatsin Marat Urdabayev Ivan Digel

Publication Name: Plos One

Publication Date: 2024-03-01

Volume: 19

Issue: 3 March

Page Range: Unknown

Description:

The potential for developing smart cities in Kazakhstan is evaluated using cluster analysis. Built on previous research focused on clustering the regions of Kazakhstan, this study applies the same method to the cities of the country. The analysis uses indicators related to human capital, infrastructure, education, information technology, production, and other factors to assess the potential of each city. The clustering is performed using Single Linkage, Complete Linkage, and Ward’s methods. The results show that Almaty and Astana are the cities with the highest potential for becoming smart cities. Aktobe is identified as a city with distinctive features that may help or hinder its development as a smart city. The remaining cities are clustered into two groups, with one group having the potential to catch up and maintain the trend of developing smart cities, while the other group is less suitable for starting smart city projects and may require more investment per capita. The study highlights the deep regional inequality affecting the potential to successfully develop and manage smart cities in Kazakhstan. The analysis also reveals some limitations and challenges in the data and variables used, including the lack of data for some variables and the difficulties in "translating" some factors and indicators into quantitative variables for clustering. The study concludes that future research should address these challenges and consider clustering inside certain regions to focus on their unique features. The study recommends launching pilot projects in small cities, with the most successful practices then scaled and implemented in the core smart cities and possibly Aktobe, if it manages to use its advantages to compensate for risks. Overall, this study provides insights into the potential of smart city development in Kazakhstan and can inform policymakers in their efforts to support smart city projects in the country.

Open Access: Yes

DOI: 10.1371/journal.pone.0296765