Search in Publications

Found 6374 publications

Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland: A case-study in Syria

Glory O. Enaruvbe Bashar Bashir Safwan Mohammed Firas Alsilibe Szilárd Szabó Luc Cimusa Kulimushi Mona Barakat Ali Jouhra Abdullah Alsalman

Publication Name: Land Degradation and Development

Publication Date: 2023-06-01

Volume: 34

Issue: 10

Page Range: 2896-2911

Description:

The development of new techniques, such as machine learning (ML), can provide better insight into the processes and drivers of soil erosion and runoff. However, the performance of these techniques to assess soil erosion in agricultural landscapes is poorly understood. The aim of this study was to evaluate the performance of four machine learning algorithms, generalized linear model (GLM), Random Forest (RF), elastic net regression (EN) and multiple adaptive regression splines (MARS), in predicting soil erosion and runoff in Syria. Soil erosion and runoff were measured on three experimental plots (2.25 m × 1.50 m × 0.50 m, 0.10 m depth in the soil), combined with three different slopes and land use types: RS (8%, olive), SS (12%, citrus), KS (20%, pomegranate). Both erosion and runoff were determined after rainfall events of >10 mm between October 2019 and April 2020. Based on 24 effective rainfall events, the average soil erosion was 0.18 ± 0.14 kg m−2 per event in KS, 0.14 ± 0.11 kg m−2 per event in SS, and 0.12 ± 0.10 kg/m2 per event in RS. Regression analysis indicated strong relationship between the rainfalls and the runoff, the highest connection was recorded in the KS plot (r2 = 0.85; p < 0.05 n = 24). The analysis of covariance indicated that only the runoff had a significant impact on soil erosion (p = 0.02) with a medium effect (ε2p = 0.26). However, the impacts of rainfall events and slope categories on soil erosion were limited (ε2p < 0.01) and not significant (p > 0.05). ML techniques were usually efficient in the prediction, the RF and MARS models were the most accurate: RF had the strongest correlation with the measured values (r = 0.85) with a low estimation error (0.06 kg m−2), but MARS's standard deviation (SD) was closer to the recorded values' SD. GLM and EN were the weakest predictor models. Modeled values of the slightest slope (8%) had the worst accuracies, and the predictions of the 12% slope were the best in all models. This study provides important insights into the usefulness of machine learning techniques and algorithms in predicting the rate of soil erosion and runoff in agricultural dominated landscapes. We highlighted that the RF and MARS algorithms were better predictors of soil erosion and runoff in the coastal region of Syria.

Open Access: Yes

DOI: 10.1002/ldr.4655

Component based hardware-software system for fuzzy controlling of automated vehicles

A. Geresdi L. Siroki T. Pápai Laszlo T. Koczy

Publication Name: Proceedings of Sefi and Igip Joint Annual Conference 2007 Joining Forces in Engineering Educations Towards Excellence

Publication Date: 2007-01-01

Volume: Unknown

Issue: Unknown

Page Range: 397-398

Description:

No description provided

Open Access: Yes

DOI: DOI not available

Comparison of magnesium determination methods on Hungarian soils

Csaba Centeri Renato Kalocsai G. Milics Zsolt Biró Viktoria Vona A. J. Kovács Gergely Jakab Zsolt Giczi

Publication Name: Soil and Water Research

Publication Date: 2020-01-01

Volume: 15

Issue: 3

Page Range: 173-180

Description:

Magnesium is one of the most important nutrient elements. Soils are tested for magnesium in many countries with several extractants. Each country has its own validated methods, best-suited for its soils. The current study was designed to compare different magnesium content measuring methods with 80 Hungarian samples. The magnesium content was determined by the potassium chloride (1 M KCl 1:10), Mehlich 3 and CoHex (cobalt hexamine trichloride) methods. The maximum, mean and median values resulting from all the Mg determination methods showed the following order of measured magnitude: KCl < CoHex < M3.

Open Access: Yes

DOI: 10.17221/92/2019-SWR

Strengthening policy goals to support dual careers of athletes in a Hungarian region: Opportunities for competence development through education

Adrienn Dernóczy-Polyák Sándor Remsei Csaba Konczos

Publication Name: International Journal of Innovative Research and Scientific Studies

Publication Date: 2025-01-01

Volume: 8

Issue: 3

Page Range: 4335-4346

Description:

This study examines the effectiveness of dual career programs for athletes in the Western Transdanubian Region among high school students. The aim of this research is to analyze the possibilities for developing the competencies necessary for a successful dual career and to assess the coherence between policy support and educational development. Using an online questionnaire, a cross-sectional survey was conducted among 596 secondary school students in two cities, distinguishing and comparing sport-oriented and non-sport-oriented institutions. The research examined the practical implementation of dual career guidance programs and the effectiveness of school sport support. The results confirmed that more than half of the respondents had not participated in any formal dual career support program. While sports-oriented schools showed higher levels of support, non-sport-oriented schools showed a significant lack of such programs. Despite the high aspirations of students to continue their sporting careers after high school, and the ambition of a significant number of students to become professional athletes, the majority have not received training or guidance on how to build a dual career. Instead, most relied on their families or themselves. The study concludes by calling for a rethink of the framework for dual career support systems to better align policy with practice.

Open Access: Yes

DOI: 10.53894/ijirss.v8i3.7508

An Investigation of Historic Transportation Infrastructure Preservation and Improvement through Historic Building Information Modeling

János Szép Kitti Karolyfi Nóra Géczy Rnin Salah

Publication Name: Infrastructures

Publication Date: 2024-07-01

Volume: 9

Issue: 7

Page Range: Unknown

Description:

Historical transportation infrastructures (HTIs) like railways and bridges are essential to our cultural heritage. However, the preservation and enhancement of these structures pose significant challenges due to their complex nature and the need for modern upgrades. Historic building information modeling (HBIM) has emerged as a solution, facilitating the documentation, restoration, and maintenance of historic transportation assets. The purpose of the proposed work is to provide a systematic review of research findings on the application of HBIM in historic transportation infrastructure, highlighting its role in capturing intricate architectural details and supporting decision making for preservation efforts. A series of case studies in which HBIM has been instrumental in preserving historic transportation infrastructure are investigated and analyzed using a comprehensive literature review method. Furthermore, future directions in HBIM research are proposed, identifying potential applications and recommending areas for further investigation. Additionally, this paper suggests HBIM’s potential to balance modernization demands with the conservation needs of historic transportation infrastructure, providing policymakers and stakeholders with insightful strategies for sustainable heritage management.

Open Access: Yes

DOI: 10.3390/infrastructures9070114

Takagi-sugeno fuzzy control models for large scale logistics systems

Gabriella Orbán Istvan A. Harmati Peter Varlaki

Publication Name: Isciii 07 3rd International Symposium on Computational Intelligence and Intelligent Informatics Proceedings

Publication Date: 2007-01-01

Volume: Unknown

Issue: Unknown

Page Range: 199-203

Description:

Requirements, such as adaptive behavior, learning ability and self regulative features, that have to be met by modern logistic systems, need the construction of such control systems that are able to control the basic processes and also to develop and improve the material and information system by automating the control processes. For controlling the logistical systems the papers propose the application of LPV structure by which non-linear systems can be controlled on the basis of linear control theories. The proposal points out that the priorities of different states are of great importance when generating the logical rules of operation. For resolving the difficulties of constructing mathematical algorithms fuzzy sets are suggested, so in the control model a Takagi-Sugeno solution is proposed, that can describe multi-input multi-output, non-linear, dynamic systems like logistical systems. © 2007 IEEE.

Open Access: Yes

DOI: 10.1109/ISCIII.2007.367389

Inequality in educational returns in Hungary

No authors available

Publication Name: Education, Occupation and Social Origin: A Comparative Analysis of the Transmission of Socio-Economic Inequalities

Publication Date: 2016-04-29

Volume:

Issue:

Page Range: 49-64

Description:

Open Access: No

DOI: DOI not available

Classification of plantar foot alterations by fuzzy cognitive maps against multi-layer perceptron neural network

Miklós F. Hatwágner Antonio Hernandez-Zavala Silvia L. Chaparro-Cardenas Julian Andres Ramirez-Bautista Laszlo T. Koczy Jorge A. Huerta-Ruelas

Publication Name: Biocybernetics and Biomedical Engineering

Publication Date: 2020-01-01

Volume: 40

Issue: 1

Page Range: 404-414

Description:

Load distribution analysis on foot surface allows knowing human mechanical behavior and aids the doctor in the detection of gait disorders like, the risk of foot ulcerations, leg discrepancy, and footprint alterations. Plantar pressure data combined with techniques that use integral reasoning produce easy understanding medical tools for assisting in treatment, early detection, and the development of preventive strategies. The present research compares the classification of human plantar foot alterations using Fuzzy Cognitive Maps (FCM) trained by Genetic Algorithm (GA) against a Multi-Layer Perceptron Neural Network (MLPNN). One hundred and fifty-one subject volunteers (aged 7–77) were classified previously with the flat foot (n = 70) and cavus foot (n = 81) by specialized physicians of the Piédica diagnostic center. The trial walking was conducted using plantar pressure platforms FreeMed®. The foot surface was divided into 14 areas that included toe 1 st to 5th, metatarsal joint 1st to 5th, lateral midfoot, medial midfoot, lateral heel, and medial heel. Pressure data were normalized for each area. Better performance in the classification using small amounts of data were found by using Fuzzy rather than non-Fuzzy approach.

Open Access: Yes

DOI: 10.1016/j.bbe.2019.12.008

Cloud spot instance price forecasting multi-headed models tuned using modified PSO

Nebojsa Bacanin Dragan Pamucar Luka Jovanovic Miodrag Zivkovic Ali Elsadai Mohamed Salb Vladimir Simic

Publication Name: Journal of King Saud University Science

Publication Date: 2024-12-01

Volume: 36

Issue: 11

Page Range: Unknown

Description:

The increasing dependence and demands on cloud infrastructure have brought to light challenges associated with cloud instance pricing. The often unpredictable nature of demand as well as changing costs of supplying a reliable instance can leave companies struggling to appropriately budget to support a healthy cash flow while maintaining operating costs. This work explores the potential of multi-headed recurrent architectures to forecast cloud instance prices based on historical and instance data. Two architectures are explored, long short-term memory (LSTM) and gated recurrent unit (GRU) networks. A modified optimizer is introduced and tested on a publicly available Amazon elastic compute cloud dataset. The GRU model, enhanced by the proposed modified approach, had the most impressive outcomes with an MAE score of 0.000801. Results have undergone meticulous statistical validation with the best-performing models further analyzed using explainable artificial intelligence techniques to provide further insight into model reasoning and information on feature importance.

Open Access: Yes

DOI: 10.1016/j.jksus.2024.103473