Search in Publications

Found 6515 publications

Prediction of Overall Equipment Effectiveness in Assembly Processes Using Machine Learning

János Jósvai Péter Dobra

Publication Name: Strojnicky Casopis Journal of Mechanical Engineering

Publication Date: 2024-11-01

Volume: 74

Issue: 2

Page Range: 57-64

Description:

Nowadays, a lot of data is generated in production and also in the domain of assembly, from which different patterns can be extracted using machine learning methods with the support of data mining. With the support of various modern technical and Information Technology (IT) tools, the recording, storage and processing of large amounts of data is now a routine activity. Based on machine learning, efficiency metrics including Overall Equipment Effectiveness (OEE), can be partially predicted, but industrial companies need more accurate and reliable methods. The analyzed algorithms can be used in general for all production units or machines where production data is recorded by Manufacturing Execution System (MES) or other Enterprise Resource Planning (ERP) systems are available. This paper presents and determinates which most used machine learning methods should be combined with each other in order to achieve a better prediction result.

Open Access: Yes

DOI: 10.2478/scjme-2024-0026

Exploring Fuzzy Signatures in Sensor Fusion: A Comparative Study with the Complementary Filter

Áron Ballagi Ahmet Mehmet Karadeniz Laszlo T. Koczy

Publication Name: Cinti 2024 IEEE 24th International Symposium on Computational Intelligence and Informatics Proceedings

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 69-74

Description:

Sensing has become a pivotal element in the development of autonomous systems with the advancement of the technology. These systems operate on a sense-think-act cycle to execute tasks, necessitating the integration of multiple sensors. The challenge of synthesizing meaningful information from diverse data sources escalates with the complexity of the data. This study tackles the issue of sensor data complexity by investigating the potential of Fuzzy Signatures, which are promising in handling complex data due to their hierarchical structures. The main goal is to present a concept for sensor fusion based on Fuzzy Signatures, which may facilitate their use in autonomous system tasks. To demonstrate this concept, accelerometer and gyroscope data are utilized, with results compared to those from a Complementary Filter providing insight into the sensor fusion capabilities of Fuzzy Signatures. The study also underscores the importance of aggregation operators in Fuzzy Signatures, focusing on the Max and WRAO (weighted relevance aggregation operator) aggregation operators. The potential to employ various aggregation operators or to develop new ones for specific applications is highlighted. The findings indicate that Fuzzy Signatures could be an effective solution for sensor fusion challenges, offering prospects for enhancement and broader application in autonomous systems.

Open Access: Yes

DOI: 10.1109/CINTI63048.2024.10830837

ENERGY ANALYSIS OF BUILDINGS WITH LARGE GLAZED SURFACES

T. Horváth Zsolt Szűrös Rita Rebeka Ördög

Publication Name: Iet Conference Proceedings

Publication Date: 2024-01-01

Volume: 2024

Issue: 8

Page Range: 58-64

Description:

Modern architecture has brought new opportunities with the development of industry and technology. Among other things, it has become possible to visually connect the interior and exterior spaces with transparent structures, while providing climatic separation. Since the first modern buildings of Frank Lloyd Wright and Mies van der Rohe, large glazed surface buildings have gained considerable ground. Through the examination of a case study, the research looks for the answer to which of the possible structural solutions for buildings with large surfaces of glass are double or triple glazing, the use of internal or external, or fixed or movable shading is it more beneficial from a building energy point of view, in order to create the comfort of the interior space. The tests were carried out according to the calculations of the 7/2006 TNM decree and also according to the rules of the 9/2023 ÉKM decree, in force from November 2023.

Open Access: Yes

DOI: 10.1049/icp.2024.2682

Empirical white noise processes and the subjective probabilistic approaches

András Rövid Péter Várlaki László Palkovics

Publication Name: Periodica Polytechnica Transportation Engineering

Publication Date: 2019-11-15

Volume: 48

Issue: 1

Page Range: 19-30

Description:

The paper discusses the identification of the empirical white noise processes generated by deterministic numerical algorithms. The introduced fuzzy-random complementary approach can identify the inner hidden correlational patterns of the empirical white noise process if the process has a real hidden structure of this kind. We have shown how the characteristics of auto-correlated white noise processes change as the order of autocorrelation increases. Although in this paper we rely on random number generators to get approximate white noise processes, in our upcoming research we are planning to turn the focus on physical white noise processes in order to validate our hypothesis.

Open Access: Yes

DOI: 10.3311/PPtr.15165

Complex Framework for Condition Assessment of Residential Buildings

Ádám Bukovics Ferenc Lilik Balazs Lukacs Laszlo T. Koczy

Publication Name: Lecture Notes in Civil Engineering

Publication Date: 2024-01-01

Volume: 444

Issue: Unknown

Page Range: 97-108

Description:

In the big cities of Europe large-scale construction of apartment buildings took place at the end of the 19th and at the beginning of the 20th century. In the process, buildings were created based on unique plans, but very similar to each other, containing similar technological solutions and built from similar building materials. Over the past 100 years, some of the buildings have been continuously maintained, while the condition of other buildings has deteriorated significantly. The renovation of these buildings has now become necessary and in many cases, unavoidable. In the current economic and energy situation, it is important that maintenance or conversion is carried out in a sustainable manner to the necessary extent. The method and extent of the interventions can be provided in a uniform manner with help of a computer system. We have developed a condition assessment and decision support model and algorithm that can be used for this purpose. We call it Complex Building’s Decision Support System based on Fuzzy Signatures (CBDF system). We use fuzzy signature-based model to handle uncertainties, inaccuracies and possibly missing data that occur during the condition assessment. The presented decision model prepares the status assessment based on 4 main components (project info, knowledge base, preparatory work process, fuzzy system). After defining the objectives (e.g., general condition assessment, evaluation from the perspective of accident prevention, examination of the possibility of roof installation), the system requests the necessary data and generates the fuzzy signature required for the condition assessment of the given building. Based on the input data for the specific project and the knowledge base, the decision model searches for failures and anomalies in the building based on the preparatory work process, manages the existing uncertainties and inaccuracies, and determines the load bearing surplus of the examined load bearing structures. Using the existing information and conclusions, based on various fuzzy set-based descriptors and aggregation operators, the condition assessment is prepared, and then, if necessary, the intervention proposal as well. The final goal of the decision model is to put a tool in the hands of experts examining the condition of buildings, which can be used to prepare uniform and objective assessments (also suitable for ranking) and to reduce error in condition assessment.

Open Access: Yes

DOI: 10.1007/978-3-031-48461-2_9

Key Aspects on the Biology, Ecology and Impacts of Johnsongrass [Sorghum halepense (L.) Pers] and the Role of Glyphosate and Non-Chemical Alternative Practices for the Management of This Weed in Europe

Ilias S. Travlos Gerasimos Peteinatos Panagiotis J. Kanatas Goran Malidza Gabor Kukorelli Jose M. Montull Nikolina Cheimona Stavros Zannopoulos Nikolaos Antonopoulos M. N. Dogan

Publication Name: Agronomy

Publication Date: 2019-11-05

Volume: 9

Issue: 11

Page Range: Unknown

Description:

Sorghum halepense (L.) Pers is a common and noxious worldwide weed of increasing distribution in many European countries. In the present review, information on the biology, ecology, agricultural, economic and environmental impact of johnsongrass is given, and the current status of this weed in Europe is discussed. Furthermore, special attention is given to the important role of field trials using glyphosate to control weeds in arable and perennial crops in many European countries. Some of the factors which affect control efficacy and should be taken into account are also discussed. Finally, several non-chemical alternative methods (cultural, mechanical, thermal, biological, etc.) for johnsongrass management are also presented. The adoption of integrated weed management (IWM) techniques such as glyphosate use, crop rotation, and deep tillage is strongly recommended to control plant species that originate from both seed and rhizomes.

Open Access: Yes

DOI: 10.3390/agronomy9110717

ModRTU InjectX: A Command Injection Simulation Tool for Industrial Cybersecurity Research

Zoltán Dobrády Timót Hidvégi Szilvia Nagy

Publication Name: 60th International Scientific Conference on Information Communication and Energy Systems and Technologies Icest 2025 Proceedings

Publication Date: 2025-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

ModRTU_InjectX is a Python-based research tool with a graphical user interface, specifically designed for real-time monitoring, analysis, and command injection simulation within Modbus RTU industrial communication systems. The platform enables users to craft custom data packets and inject them into the serial communication channel using event-driven logic, effectively modelling realistic cyberattack scenarios. All communication is logged and can be exported in structured formats, making the system ideal for creating annotated datasets for training and validating machine learning-based intrusion detection systems. The tool supports parallel injection block configurations, evaluates attack effectiveness, and provides detailed statistical summaries. ModRTU_InjectX serves as a valuable contribution to the research infrastructure for industrial cybersecurity.

Open Access: Yes

DOI: 10.1109/ICEST66328.2025.11098380

Function approximation capability of a novel fuzzy flip-flop based Neural Network

László Gál Rita Lovassy Laszlo T. Koczy

Publication Name: Proceedings of the International Joint Conference on Neural Networks

Publication Date: 2009-11-18

Volume: Unknown

Issue: Unknown

Page Range: 1900-1907

Description:

The function approximation capability of various connectionist systems has been one of the most interesting problems. A method for constructing Multilayer Perceptron Neural Networks (MLP NN) with the aid of fuzzy operations based flip-flops able to approximate single and multiple variable functions is proposed. This paper introduces the concept of fuzzy flip-flop based neural network, particularly by deploying three types of fuzzy flip-flops as neurons. A comparative study of feedbacked fuzzy J-K and two kinds of fuzzy D flip-flops used as neurons, based on fuzzy algebraic, Yager, Dombi, Hamacher and Frank operations is given. Simulation results are presented for several test functions. © 2009 IEEE.

Open Access: Yes

DOI: 10.1109/IJCNN.2009.5178849

A Comparative Evaluation of Classical and Deep Learning-Based Visual Odometry Methods for Autonomous Vehicle Navigation †

Janos Hollosi Armand Nagy

Publication Name: Engineering Proceedings

Publication Date: 2025-01-01

Volume: 113

Issue: 1

Page Range: Unknown

Description:

This study introduces a comprehensive benchmarking framework for evaluating visual odometry (VO) methods, combining classical, learning-based, and hybrid approaches. We assess 52 configurations—spanning 19 keypoint detectors, 21 descriptors, and 4 matchers—across two widely used benchmark datasets: KITTI and EuRoC. Six key trajectory metrics, including Absolute Trajectory Error (ATE) and Final Displacement Error (FDE), provide a detailed performance comparison under various environmental conditions, such as motion blur, occlusions, and dynamic lighting. Our results highlight the critical role of feature matchers, with the LightGlue–SIFT combination consistently outperforming others across both datasets. Additionally, learning-based matchers can be integrated with classical pipelines, improving robustness without requiring end-to-end training. Hybrid configurations combining classical detectors with learned components offer a balanced trade-off between accuracy, robustness, and computational efficiency, making them suitable for real-world applications in autonomous systems and robotics.

Open Access: Yes

DOI: 10.3390/engproc2025113016