Search Everything

Tip: Search using "First Name + Last Name", e.g.
János Kiss instead of Kiss János.

Publications - 6383

Improve the Accuracy of Neural Networks using Capsule Layers

Claudiu Radu Pozna Janos Hollosi

Publication Name: 18th IEEE International Symposium on Computational Intelligence and Informatics Cinti 2018 Proceedings

Publication Date: 2018-11-01

Volume: Unknown

Issue: Unknown

Page Range: 15-18

Description:

Neural networks are a powerful and widely used tools for various classification and segmentation tasks. Nowadays, in the field of computer vision the convolutional neural networks (CNNs) are the most popular solution for many problems. The CNNs performance is looks like exceptionally great when the test images are very close to the training dataset. However if the input images are transformed, such as rotating or tilting, the efficiency of the neural network may be greatly reduced. A new kind of neural network, is called capsule network, is trying to solve this problem. In this paper we examines the efficiency of the capsule network, by trying to increase the accuracy of different networks with capsule layers.

Open Access: Yes

DOI: 10.1109/CINTI.2018.8928194

Exploring the Influencing Factors of Big Data Analytics Adoption in Manufacturing Firms: A Survey Analysis

László Buics Mouhyar Saad Eddin

Publication Name: International Scientific Business Conference Limen Leadership Innovation Management and Economics Integrated Politics of Research

Publication Date: 2024-01-01

Volume: 2024

Issue: Unknown

Page Range: 689-697

Description:

Due to its attractive possibilities and potential benefits, the use of big data analytics is gaining popularity in both real operations and theoretical discourse. The goal of this research is to identify the factors that influence the adoption of big data analytics and their impact on the performance of supply chains in the manufacturing industry, examining how information sharing between firms affects this relationship with the help of a survey to collect and analyze data, with a sample size of 200 respondents. The study discovered that technological, organizational, environmental, and perceived risk factors all had a significant impact on big data analytics adoption. The study's findings also show a substantial and favorable relationship between big data analytics adoption and supply chain performance. Finally, it was observed that the act of sharing information had a moderating effect on the link between big data analytics adoption and firm performance.

Open Access: Yes

DOI: 10.31410/LIMEN.2024.689

Function approximation performance of Fuzzy Neural Networks based on frequently used fuzzy operations and a pair of new trigonometric norms

László Gál Rita Lovassy László T. Kóczy

Publication Name: 2010 IEEE World Congress on Computational Intelligence Wcci 2010

Publication Date: 2010-11-25

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

A new triangular t-norm and t-conorm are presented. The new fuzzy operations combined with the standard negation are applied in a practical problem, namely, they are proposed as suitable triangular norms for defining a fuzzy flip-flop based neuron. Other fuzzy J-K and D flip-flop based neurons are constructed by using algebraic, Lukasiewicz, Yager, Dombi and Hamacher connectives. The function approximation performance of a Fuzzy Neural Networks (FNN) built up from various fuzzy neurons are evaluated using six increasingly more complicated problems: various sine waves, battery cell charging characteristics, two dimensional trigonometric functions and a six dimensional benchmark problem. It is shown that the new norms lead to FNNs with better approximation properties in some cases than all the previous ones. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZY.2010.5584252

Performance Optimization of a Formula Student Racing Car Using IPG CarMaker—Part 2: Aiding Aerodynamics and Drag Reduction System Package Design †

Ambrus Zelei Dominik Takács

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

Part 1 of this paper summarizes the application of the IPG CarMaker 11.0 software for lap-time simulation and optimization. The goal is to use the IPG CarMaker on a given track for the optimization of the aerodynamics package parameters and the drag reduction system (DRS). The optimal aerodynamic downforce coefficient is determined for a given vehicle. The simulations clearly suggest that the application of the DRS pays off for a Formula Student car, if the DRS activation and deactivation times are chosen carefully. As IPG CarMaker seems to be a powerful tool, the Arrabona Racing Team decided to extend its application.

Open Access: Yes

DOI: 10.3390/engproc2024079077

Detection of corrosion resistance of components in cyclic salt spray

Jan Mareček Tamás Ibriksz Vladimír Kročko Štefan Álló

Publication Name: Acta Universitatis Agriculturae Et Silviculturae Mendelianae Brunensis

Publication Date: 2015-01-01

Volume: 63

Issue: 1

Page Range: 9-13

Description:

The aim of this research is, to investigate the influence of two types of cyclic salt spray tests on parts surface treated with galvanizing. On the selected components was performed the method Zn-Ni surface treating on the bath line. Subsequently were the components embedded in the corrosion chamber, where was performed two types of cyclic salt test. In the first test was performed 4 hour salt spray, 8 hours drying, 60 hours condensation and 24 hours drying. Once cycle lasted 96 hours, and it was repeated 4 times. During the second test was performed 2 hours salt spray, 2 hours condensation. The cycle was repeated 4 times, that means 96 hours. After the cycle was performed 72 hours free relaxation in the corrosion chamber, on 20-25 °C temperature. As the research showed, after the cyclic salt spray was no red corrosion on the selected components. The white corrosion appeared only slightly.

Open Access: Yes

DOI: 10.11118/actaun201563010009

Numerical Study of the Effect of the Shape and Area of Shallow Foundations on the Bearing Capacity of Sandy Soils

Rashad Alsirawan Ammar N. Alnmr

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2024-01-01

Volume: 21

Issue: 1

Page Range: 103-120

Description:

The settlement and bearing capacity of shallow foundation models with different shapes and areas on cohesionless subsoil under the applied vertical load are presented in this study. Different shapes of foundations with rectangular, square, strip, plus horizontal cross-sectional shapes are numerically studied after the validation on the laboratory model has been conducted and the constitutive soil model that simulates the behaviour of sandy soil has been chosen. The result of the validation showed that the HS model is the most suitable for the simulation of stress-deformation behaviour of sand. The effect of the shape and area are clearly visible and greatly affects the bearing capacity of the soil. The study generally compared Vesic's, Hansen's and German’s bearing capacity equations and showed that Vesic's and Hansen's bearing capacity equations are best suited to the bearing capacity computed from numerical analysis by Plaxis3D. Finally, as a development of Hansen's bearing capacity equation, a new equation of plus shape foundation bearing capacity has been determined.

Open Access: Yes

DOI: 10.12700/APH.21.1.2024.1.7

HEAT AND MASS TRANSFER INVESTIGATION OF THIRD-GRADE WILLIAMSON-CASSON HYBRID NANOFLUID MODEL IN DARCY-FORCHHEIMER POROUS MEDIUM ACROSS EXPONENTIAL STRETCHING SURFACE INFLUENCED BY VISCOUS DISSIPATION

Siti Sabariah Binti Abas Mustafa Inc N. F.M. Noor Ali Rehman Ilyas Khan D. Baba Basha

Publication Name: Fractals

Publication Date: 2026-01-01

Volume: 34

Issue: 6

Page Range: Unknown

Description:

The novel concept of hybrid nanofluids (HNFs) captivated scientists and researchers due to its remarkable thermal conductivities, which led to improved thermal performance. There are several applications for these fluids in the fields of technology and industry. A third-grade Williamson-Casson HNF model for magnetohydrodynamics over an exponentially stretched surface in a DF permeable medium is presented in this work. It covers the impacts of viscous dissipation (VD) as well as the analysis of heat and mass transfer (HMT). The established governing PDEs for momentum, energy, and concentration transfer are transformed into a collection of nonlinear ODEs using similarity transformations (ST). These transformed equations are solved using semi-numerical methods called HAM. It investigates how velocity field (VF), temperature field (TF), and concentration field (CF) are affected by changes in critical parameters such as thermal conductivity, third-grade fluid parameter, DF number, magnetic field (MF) strength, Williamson and Casson fluid parameters, and nanoparticle volume fractions (VLFs). The results show that the presence of an HNF increases thermal conductivity, which improves heat transfer efficiency. Additionally, VD and third-grade fluid characteristics significantly impact fluid flow and energy transfer. The recent research offers important new information for practical applications in thermal engineering systems, biofluid mechanics, and polymer processing.

Open Access: Yes

DOI: 10.1142/S0218348X26400566

Oil Degradation Patterns in Diesel and Petrol Engines Observed in the Field—An Approach Applying Mass Spectrometry

Charlotte Besser Péter Raffai Marcella Frauscher András Lajos Nagy Adam Agocs Andjelka Ristic Zsolt Tabakov

Publication Name: Lubricants

Publication Date: 2023-09-01

Volume: 11

Issue: 9

Page Range: Unknown

Description:

Engine oil degradation and tribological properties are strongly interrelated. Hence, understanding the chemical processes resulting in additive depletion and degradation products is necessary. In this study, in-service engine oils from petrol and diesel vehicles were analyzed with conventional and advanced methods (mass spectrometry). Additionally, the effect of the utilization profile (short- vs. long-range) was studied. Petrol engine oils generally showed accelerated antioxidant and antiwear degradation and higher oxidation, especially in the case of a short-range utilization profile, which can be attributed to the higher air-to-fuel ratio (more rich combustion) compared to diesel engines. A detailed overview of oxidation and nitration products, as well as degradation products resulting from zinc dialkyl dithiophosphate and boron ester antiwear additives, diphenylamine antioxidants and salicylate detergents is given. A side reaction between oxidation products (aromatic carboxylic acids) and the boron ester antiwear is highlighted. This reaction was only detected in the petrol engine oils, where the oxidation products were measured in a high abundance. However, no side reaction was found in the samples from the diesel vehicles, since there the aromatic carboxylic acids were largely absent due to lower oxidation.

Open Access: Yes

DOI: 10.3390/lubricants11090404

Environmental and socio-economic factors behind data provision in 17 citizen science projects

Zoltán Csabai Marianna Biró Judit Vörös László Mezőfi Barna Páll-Gergely Zsuzsanna Márton Zoltán Soltész Zsófia Horváth Bálint Halpern Zsóka Vásárhelyi Kornélia Kurucz Bálint Pernecker Gábor Földvári Barbara Barta Balázs Károlyi Ágnes Turóci Éva Szabó Erika Juhász Ádám Selmeczi-Kovács Péter Lovászi László Zsolt Garamszegi

Publication Name: People and Nature

Publication Date: 2026-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Citizen science approaches in ecology have recently become increasingly popular. Although many advantages, such as the cost-effective collection of vast amounts of data, outweigh the disadvantages, most projects face difficulties, such as non-random sampling, pseudo-absences or various biases, such as detection/reporting biases or participant-related biases. To unravel some of the environmental and socio-economic factors underlying data provision occurring non-randomly, we analysed the geographically tractable record-level databases of 17 separate citizen science projects in ecology and conservation in Hungary. We matched the records to an independent administrative dataset to identify those environmental and socio-economic predictors that are expected to shape participant activity, which varies widely according to the purpose, subject and other characteristics of the projects. Despite the projects' variation, we were able to identify general patterns linking population density of a given municipality and the proportion of protected areas with participant activity. Both variables were significantly associated with the number of observations. If the most urbanised and densely populated capital was left out of the analysis, both the level of education and the proportion of elderly people were positively associated with the number of observations a project received. However, the relationship between a population's socio-economic status and participant activity varied greatly across particular citizen science projects. Our results highlight that citizen science participation is shaped by both environmental context and socio-economic characteristics, revealing systematic spatial biases in data provision. Our results thus provide new insights into the methodology and design of future citizen science projects. Read the free Plain Language Summary for this article on the Journal blog.

Open Access: Yes

DOI: 10.1002/pan3.70335