Search in Publications

Found 6327 publications

Rail Defect Classification with Deep Learning Method

Guoqing Jing Weile Qiang Majid Movahedi Rad Jingru Wang Shiyao Lu

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2022-01-01

Volume: 19

Issue: 6

Page Range: 225-241

Description:

The good condition of railway rails is crucial to ensuring the safe operation of the railway network. At present, the rail flaw detectors are widely used in rail flaw detection, they are typically based on the principle of ultrasonic detection. However, the rail detection results analysis process involves huge manual work and the associated labor costs, with low levels of efficiency. In order to improve the efficiency, accuracy of results analysis and also reduce the labor costs, it is necessary to employ classification of ultrasonic flaw detection B-scan image, based on an artificial intelligence algorithm. Inspired by transformer models, with excellent performance in the field of natural language processing (NLP), some deep learning models differ from traditional convolutional neural networks (CNN), gradually emerge in the field of computer image processing. In order to explore the practicality of this model in the field of computer image processing (vision), in the paper, the Vision Transformer (ViT) is employed to train with rail defect B-scan images data and produce a rail defect classification. The model accuracy is more than 90% with the highest accuracy reaching 98.92%.

Open Access: Yes

DOI: DOI not available

WAYS OF IMPROVING OF ACTIVE CONTOUR METHODS IN COLON-OSCOPY IMAGE SEGMENTATION

Raneem Ismail Szilvia Nagy

Publication Name: Image Analysis and Stereology

Publication Date: 2022-01-01

Volume: 41

Issue: 1

Page Range: 7-23

Description:

As colonoscopy is the standard screening approach for colorectal polyps, and the first step of the correct classification and the efficient automatic diagnostics is the accurate detection and segmentation of the ex-isting polyps, it is worth researching systematically, how colonoscopy databases are responding to two of the most influential variational segmentation methods, the geodesic and Chan–Vese active contour meth-ods. Due to the quality variation of the colonoscopy databases, pre-processing steps are made. Then, 14 various filtered images are evaluated as different inputs for the active contour methods using the Sørensen–Dice Similarity Coefficient as a performance measurement metric. The effects of the initial mask shape and its size together with the number of iterations, contraction bias and smoothness factor are studied. In gen-eral, the Chan–Vese method showed more efficiency to match the actual contour of the polyp than the geodesic one with an initial mask possibly located within the polyp area. Preprocessing such as reflection removal, background subtraction and mean or median filtering can improve the Sørensen–Dice coefficient by up to 0.5

Open Access: Yes

DOI: 10.5566/ias.2604

Juvenile court – the Conqueror of Legal History

Enikő Kovács-Szépvölgyi

Publication Name: Journal on European History of Law

Publication Date: 2022-01-01

Volume: 13

Issue: 1

Page Range: 156-160

Description:

The idea of the title that the juvenile court is the greatest conqueror of legal history comes from a work by renowned criminal lawyer Ferenc Finkey, who quoted Hastings H. Hart’s thoughts about the juvenile court. The Juvenile Court first appeared in Illinois, USA, in 1899, followed by most federal states and several countries on the old continent. The state-and legal life of Hungary, in the broader context of the Central and Eastern European states, is usually interpreted in the framework of the centre-periphery model. Without going into the issue of regulatory delay, it is worth noting that Hungarian legislation caught up with pioneering states with special criminal law regulations introduced in the early 20th century to establish the foundations for other treatment of juvenile offenders. The different treatment in this context refers to different rules from those for adult offenders. The law regulating the juvenile court as a special court entered into force in 1914, supplementing the substantive criminal law provisions with procedural rules.

Open Access: Yes

DOI: DOI not available

Digital Competences of Teachers in the Digitalising Education Sector and in the Smart Learning Environment

Katalin Nagy Gyorgy Molnar

Publication Name: Sisy 2022 IEEE 20th Jubilee International Symposium on Intelligent Systems and Informatics Proceedings

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: 325-330

Description:

In addition to the specific characteristics of the teaching-learning process, we have faced and continue to face a number of challenges and constraints in the digital era. A common set of challenges has been and will continue to be, at the end of 2021, the issue of digital competences, which is one of the main focal points (in addition to the provision of a modern high-capacity server backbone) of the new European Digital Agenda for Education (2021-27). The focus of our paper is therefore on the study of digital competences among teachers. In Hungary, the adapted frameworks based on the central EU Recommendation were published in 2019 and 2020, the first of which was the digital competence framework for teachers based on DigCompEdu. The digital skills and ICT attitudes of teachers play a key role in digital education. In this article, we present the results of a snow-ball sampling based pilot questionnaire administered to practising teachers in addition to a description and overview of the theoretical framework. Our research questionnaire consisted of 34 items, with N=112 respondents providing a scored response to our survey. The questionnaire survey consisted of a total of six sections, and we intend to use the responses and results obtained in our further research, seeking answers to the main research questions.

Open Access: Yes

DOI: 10.1109/SISY56759.2022.10036290

Comparative Study of the Mechanical Behavior of Concrete Railway Sleeper Mix Design, using Waste Rubber and Glass Materials

Szabolcs Fischer Guoqing Jing Farshad Astaraki Mohammad Siahkouhi Majid Movahedi Rad Chunchao Li

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2022-01-01

Volume: 19

Issue: 6

Page Range: 213-224

Description:

Waste rubber tires and glass powders, are hazardous materials for the environment. One of the methods to consume them, is their application in railway engineering projects. Rubber and glass materials, in this research, are provided from waste tires and glass bottles. Therefore, a modification is conducted to the concrete railway sleeper mix design, incorporated with waste rubber (R) and glass powder (GP). Three mechanical tests, including compressive, flexural and tensile splitting, have been studied on rubber and glass powder concrete specimens. Three different percentages of 5%, 10% and 15% by cement weight, for GP and by fine aggregate volume for R, are investigated herein. The results show that GP concrete has a better performance over the rubber concrete (RC), but lower than Ref. specimens. 5%GP as the best mix design, has compressive, flexural and tensile strengths of 45.4 MPa, 7.5 MPa and 5.82 MPa, respectively. Moreover, these strengths, for compressive and flexural, of 5%GP are about 24% and 6% lower than the Ref. strengths, respectively, while, tensile splitting strength is almost 14% higher than Ref. strength.

Open Access: Yes

DOI: DOI not available

Synthesis of Integrated Vertical Farming Systems with Multiperiodic Resource Availability

Jean Pimentel Ferenc Friedler

Publication Name: Chemical Engineering Transactions

Publication Date: 2022-01-01

Volume: 94

Issue: Unknown

Page Range: 1039-1044

Description:

Vertical farming (VF) has been proposed as an approach to decrease the land required for growing agricultural products. This technique consists of growing produce in vertical orientation within a controlled environment. However, one of the most significant barriers for its implementation is the uncertain economic feasibility, derived from the elevated consumption of energy and the high investment costs. A strategy to enhance VF efficiency proposes its integration with municipal infrastructure, thus establishing closed-loop systems where VF seizes organic waste, manure, CO2, and excess energy from productive plants and local power stations. Because of the economic uncertainty of its development, the optimal synthesis of such a closed-loop system (i.e., the selection and specification of its components, and their connections) is of utmost importance for the implementation of this strategy. The difficulty of the synthesis task arises from the combinatorial nature of the problem and the variability of the resources and market conditions in time. This work employs a graph-theoretic approach for the synthesis of a closed-loop system of VF considering the variability of the resources during multiple periods of operation. The proposed method relies on the P-graph framework which permits the identification of the n-best alternatives for the system’s design, employing the properties of the problem’s structure to enhance the effectiveness of the solution procedure. Consequently, the most cost-effective systems are identified together with their policy of operation for the different periods. This method constitutes a powerful tool for the assessment of systems for VF integration that enhance the sustainability of agricultural activity.

Open Access: Yes

DOI: 10.3303/CET2294173

Modular code generation for creating IoT applications

Gábor Paller Gabor Elo

Publication Name: International Conference on Electrical Computer Communications and Mechatronics Engineering Iceccme 2022

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

This paper builds on an earlier work that aims to generate code for connected digital systems (IoT, Internet of Things). Orcc-IoT was the adaptation of the Orcc dataflow design environment and code generator to the IoT problem area. IoT systems are characterized by heterogeneity of both the software and hardware environments therefore code generators targeting them must be able to handle embedded, client and server enviroments too. The first version of Orcc-IoT provided simplistic code generators. The extensions presented in this paper add embedded and server-side modules and more specialized wireless communication options to test Orcc-IoT's modular architecture.

Open Access: Yes

DOI: 10.1109/ICECCME55909.2022.9987980

Multi-objective Optimization of Electric Motors with a Kriging Surrogate Model

György Istenes Zoltán Horváth

Publication Name: 2022 22nd International Symposium on Electrical Apparatus and Technologies Siela 2022 Proceedings

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Since the electric drive systems are already used in numerous cars and other vehicles as well, the widely varying fields of applications require custom motor design. The most efficient tool for different specified motor designs is the multi-objective optimization tool based on validated simulations. An electrical motor optimization system with a kriging surrogate model based on FEM simulations is developed. The application of this system is presented in this paper. The models and the simulations were created in ANSYS Maxwell and MATLAB. The optimization was performed with the multi-objective genetic optimization algorithm by MATLAB which can be controlled by a simple input-output MATLAB interface.

Open Access: Yes

DOI: 10.1109/SIELA54794.2022.9845694

Experimental Investigation of the Friction Modifying Effects of Different Nanoforms of Graphene Additives in Engine Lubricating Oil

Cs Tóth-Nagy I. Szabó

Publication Name: Fme Transactions

Publication Date: 2022-01-01

Volume: 50

Issue: 2

Page Range: 248-259

Description:

This article presents the results of an experimental investigation of different nanoforms of graphene used as a nano additive in engine lubricating oil. The experiments were carried out on a pin-on-disc tribometer at the Department of Internal Combustion Engines and Propulsions at Széchenyi István University. The paper introduces the experimental equipment and the experimental method and presents the research findings. The paper concludes that fullerene can decrease friction by 7% on average when used as a nano additive in engine lubricating oil. Furthermore, fullerene did not present a sedimentation problem when used as an additive up to 0.25 wt% in lubricant instead of graphene and multiwalled carbon nanotubes. The paper attempts to explain the friction decreasing effect and the possible roles of carbon nano additives in tribological systems.

Open Access: Yes

DOI: 10.5937/fme2201248T