Search in Publications

Found 6278 publications

Application of spatio-temporal data in site-specific maize yield prediction with machine learning methods

Endre Harsányi G. Milics Bálint Daróczy C. Kerepesi A. J. Kovács J. Nagy A. Nyéki M. Neményi András Benczúr

Publication Name: Precision Agriculture

Publication Date: 2021-10-01

Volume: 22

Issue: 5

Page Range: 1397-1415

Description:

In order to meet the requirements of sustainability and to determine yield drivers and limiting factors, it is now more likely that traditional yield modelling will be carried out using artificial intelligence (AI). The aim of this study was to predict maize yields using AI that uses spatio-temporal training data. The paper has advanced a new method of maize yield prediction, which is based on spatio-temporal data mining. To find the best solution, various models were used: counter-propagation artificial neural networks (CP-ANNs), XY-fused Querynetworks (XY-Fs), supervised Kohonen networks (SKNs), neural networks with Rectangular Linear Activations (ReLU), extreme gradient boosting (XGBoost), support-vector machine (SVM), and different subsets of the independent variables in five vegetation periods. Input variables for modelling included: soil parameters (pH, P2O5, K2O, Zn, clay content, ECa, draught force, Cone index), micro-relief averages, and meteorological parameters for the 63 treatment units in a 15.3 ha research field. The best performing method (XGBoost) reached 92.1% and 95.3% accuracy on the training and the test sets. Additionally, a novel method was introduced to treat individual units in a lattice system. The lattice-based smoothing performed an additional increase in Area under the curve (AUC) to 97.5% over the individual predictions of the XGBoost model. The models were developed using 48 different subsets of variables to determine which variables consistently contributed to prediction accuracy. By comparing the resulting models, it was shown that the best regression model was Extreme Gradient Boosting Trees, with 92.1% accuracy (on the training set). In addition, the method calculates the influence of the spatial distribution of site-specific soil fertility on maize grain yields. This paper provides a new method of spatio-temporal data analyses, taking the most important influencing factors on maize yields into account.

Open Access: Yes

DOI: 10.1007/s11119-021-09833-8

Valorization of Pea Pod (Pisum sativum L.) Waste: Application as a Functional Ingredient in Flatbreads

E. Lakatos Székelyhidi Rita Beatrix Sik G. Takács Zsolt Ajtony

Publication Name: Legume Science

Publication Date: 2024-12-01

Volume: 6

Issue: 4

Page Range: Unknown

Description:

Legumes provide valuable functional properties, serving as rich sources of protein, minerals, dietary fiber, and antioxidant compounds. This study evaluated the nutritional and antioxidant properties of pea pod powder (PPP) as a fortifying ingredient in flatbreads. The results indicate that PPP contains carbohydrates (55%), protein (16.7%), and dietary fiber (13.1%), with significant antioxidant properties (total polyphenol content: 463 mg GAE/100 g, total flavonoid content: 159 mg QE/100 g, DPPH radical scavenging activity: 166 mg AAE/100 g; IC50: 2.31 mg/mL, chlorophyll a: 17.4 mg/100 g, chlorophyll b: 17.4 mg/100 g, and total chlorophyll: 32.6 mg/100 g). Rutin, chlorogenic acid, and p-coumaric acid were identified and quantified by HPLC-DAD, with concentrations of 15.2, 2.94, and 6.60 mg/100 g, respectively. Flatbreads fortified with PPP at 5%w/w and 10%w/w showed increased thickness, reduced diameter and spread ratio, and enhanced antioxidant properties. However, consumer acceptance significantly declined at the 10%w/w level, likely due to off-flavors that affected sensory appeal.

Open Access: Yes

DOI: 10.1002/leg3.70017

The Effect of Heat Treatment on the Mechanical Properties of Continuously Fibre-Reinforced Standardised Specimens

Robert Magai Balazs Molnar

Publication Name: International Journal of Automotive Science and Technology

Publication Date: 2025-12-17

Volume: 9

Issue: 1st Future of Vehicles Conf.

Page Range: 22-27

Description:

This study investigates the influence of post-printing heat treatments on the mechanical characteristics of 3D-printed specimens strengthened with continuous Kevlar filaments. After their fabrication, the specimens underwent thermal annealing at temperatures of 100 °C and 150 °C for either 1 or 3 hours. To assess the effects of these treatments on mechanical performance, tensile tests and microscopic analyses were performed. The findings indicated that the most significant enhancement was observed in specimens annealed at 150 °C for 1 hour, which resulted in an approximately 20% increase in tensile strength compared to untreated samples. Heat treatments at 100 °C for 1 hour and 3 hours led to moderate improvements of 5–8%, whereas extended treatment at 150 °C for 3 hours resulted in a reduction of about 10% in tensile strength. Microscopy revealed that brief, high-temperature treatment enhanced interlayer bonding and decreased internal stress without harming the structure, while prolonged thermal exposure led to local delamination and compromised fibre–matrix adhesion. These results suggest that controlled post-printing heat treatment can enhance the mechanical properties of continuous fibre-reinforced composites, though excessive heat exposure can lead to degradation. Therefore, careful optimisation of temperature and duration is crucial. The outcomes offer valuable insights for improving the structural performance of additively manufactured continuous fibre-reinforced components.

Open Access: Yes

DOI: 10.30939/IJASTECH..1752437

Design constraints of a forerunner UAV in safety improvement of first responders

Antal Hiba Péter Bauer

Publication Name: Transportation Research Interdisciplinary Perspectives

Publication Date: 2025-11-01

Volume: 34

Issue: Unknown

Page Range: Unknown

Description:

Unmanned Aerial Vehicles (UAVs) are already in use by emergency services. Drones are becoming faster and more reliable, making them suitable for safety-critical tasks. A forerunner UAV can fly ahead of an emergency ground vehicle (EGV). It can make a decision on the traffic situation at the next intersection to notify the EGV driver if other vehicles have given the right of way or not. This notification service can increase the speed of the EGV and prevent crashes that may occur due to the driver's obstructed view. A forerunner drone for slow-speed EGV (10 m/s) has already been developed and successfully tested; however, the applicability of current drone technology to the forerunner task at higher speeds was not analyzed. This paper identifies the key parameters of the task itself and the forerunner system in a general case, and gives the main tradeoff inequalities of these design parameters. The requirements and limitations of a forerunner drone are investigated within a reasonable parameter space, and the most relevant configurations are tested in dynamic simulation using optimized velocity profiles for the drone. Software-in-the-loop tests were also performed in a complete city simulation. The results indicate that the forerunner task is solvable with current fastest or near-future drone technology if the route of the EGV is known to the UAV control.

Open Access: Yes

DOI: 10.1016/j.trip.2025.101662

Integration of structural designers’ workflows into BIM

Kitti Karolyfi Dóra Szalai

Publication Name: Journal of Building Engineering

Publication Date: 2024-12-01

Volume: 98

Issue: Unknown

Page Range: Unknown

Description:

BIM has revolutionized architectural design workflows. In this process, the work of structural engineers relies on the work of many other disciplines, and their decisions are input data for them. However, these data are not always provided in a structured form. Live load and composite load values are typically such data, that may frequently change during the design process. This research explores BIM-based tools for interdisciplinary collaboration between architectural and structural disciplines, with a focus on managing design changes and ensuring that load data is available as early as possible in the design process. In this article, automatic load definition possibilities were explored and adapted to the BIM methodology by using Archicad, Revit, and Allplan. The software options and their logic differ greatly, therefore the proposed methodology can be applied most seamlessly in Archicad. It was demonstrated that by linking the composite structure database to the model, the loads from the built-in materials and the room functions can be generated and updated semi-automatically in response to design changes.

Open Access: Yes

DOI: 10.1016/j.jobe.2024.111141

Numerical solver for analyzing the thermal behaviour of permanent magnet synchronous machines

Lotfi Abdelhakim

Publication Name: Aip Conference Proceedings

Publication Date: 2019-07-24

Volume: 2116

Issue: Unknown

Page Range: Unknown

Description:

This study investigates a 3D numerical analysis of the thermal behavior of a permanent magnet (PM) motor, performed by Finite Element Method (FEM) by using open source Feel++ software. In the developed FEM model, the windings and the stator are treated as homogeneous medium with equivalent thermal parameters and the effective properties to characterize the thermal behaviour are calculated based on the volume-weighted average over all constituents. In order to check the accuracy of the computed temperatures, experimental tests were performed in the transient-state. The thermal analyses based on the numerical method are compared with the measured results taken from the prototype machine.

Open Access: Yes

DOI: 10.1063/1.5114557

Migration Models Based on Diffusion and Determinants Gradients: Beyond the Gravity Theory

Laszlo Vasa Petro Martyniuk Halyna Mishchuk Slavka Silberg Petro Martyniuk

Publication Name: European Journal of Interdisciplinary Studies

Publication Date: 2025-01-01

Volume: 17

Issue: 2

Page Range: 33-43

Description:

The article proposes an alternative approach to study migration flows based on gravity models. This approach does not reject gravity theory; on the contrary, it expands it to some extent. The relevant models are suggested to be described using diffusion-convection approaches. The intensity of human flows is proposed to identify on the basis of determinant gradients, and the very structure of the domain for studying these processes can be represented as a graph with nodes in the form of continuous areas of social space. The proposed approach is suitable for different dimensions of mobility studying, i.e. permanent migration decisions, touristic flows, academic mobility, transportation etc. The developed conceptual approach and mathematical formalization allow for understanding the patterns of migration applying fundamental principles of mathematic physics for economic processes.

Open Access: Yes

DOI: 10.24818/ejis.2025.12

Comprehensive Analysis of the Factors Affecting the Energy Efficiency of Electric Vehicles and Methods to Reduce Consumption: A Review †

Szabolcs Kocsis Szurke Gábor Saly Ferenc Szauter

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

The increasingly stricter environmental regulations and standards aim to reduce the ecological impact of vehicles and promote the sustainable use of natural resources. Improving the energy efficiency of vehicles has become a priority in recent decades. This is a key issue for vehicle development, production, and operation. Several studies and measurements have been conducted to accurately determine vehicles’ energy consumption. This research has investigated and categorized the factors according to external impacts, losses due to vehicle properties, and the effects of vehicle control and energy reduction methods. A better understanding of these factors is crucial for improving energy efficiency.

Open Access: Yes

DOI: 10.3390/engproc2024079079

Consumer impulse buying in Hungary: A CB-SEM analysis of Hungarian consumer behaviour towards mobile short video applications based on a Chinese reference model

Judit Petra Koltai Tamás Vinkóczi Izabella Mária Végvári Martina Németh

Publication Name: Computers in Human Behavior Reports

Publication Date: 2024-12-01

Volume: 16

Issue: Unknown

Page Range: Unknown

Description:

Mobile Short Video Applications are becoming increasingly popular worldwide. The appropriate content can shape, improve or change consumers' purchasing decisions. This paper examines the attitudinal differences in impulse buying related to the use and acceptance of MSAs by adapting a model already validated in China to Hungarian users. The analysis was conducted using Covariance-Based Structural Equation Modelling (CB-SEM). A structured questionnaire survey of 283 respondents in Hungary shows that the Chinese model cannot fully be applied to Hungary. A major difference between the results of the two models is that in the Hungarian model, perceived expertise shows a positive relationship with flow experience. This indicates that video makers - in the case of Hungarian videos - should produce content including introductory information and the operation of the product. The results suggest that in the case of MSA use in Hungary, perceived expertise affects impulse buying indirectly, but flow experience directly. Flow experience is only influenced by perceived expertise (β = 0.31, ρ < 0.05), with an explained variance of 10%. Flow experience (β = 0.46, ρ < 0.05) with its direct effect on impulse buying behaviour accounts for 21% of the variance. Hungarian and Chinese MSA users have different preferences in terms of content, thus the results provide important information for both international short video creators and companies entering the international market.

Open Access: Yes

DOI: 10.1016/j.chbr.2024.100522