Search in Publications

Found 6674 publications

Adaptive Highway Traffic Management: A Reinforcement Learning Approach for Variable Speed Limit Control with Random Anomalies

Bálint Kővári Bálint Pelenczei István Gellért Knáb László Palkovics Tamás Bécsi

Publication Name: Proceedings of the International Conference on Informatics in Control Automation and Robotics

Publication Date: 2024-01-01

Volume: 2

Issue: Unknown

Page Range: 117-124

Description:

Efficient traffic flow management on highway scenarios is crucial for ensuring safety and minimizing emissions through the reduction of so-called shockwave effects. In this paper, we propose a novel approach based on cooperative Multi Agent Reinforcement Learning for optimizing traffic flow, utilizing Variable Speed Limit Control in dynamic simulation environments with random anomalies. Our method leverages Reinforcement Learning to adaptively adjust speed limits on distinct road sections in response to alternating traffic conditions, thereby improving not only general traffic flow parameters, but also reducing sustainability measures overall. Through extensive simulations in a Simulation of Urban MObility environment, we demonstrate the superiority of our approach in enhancing traffic flow efficiency and robustness compared to alternative solutions found in literature. Our findings reveal an enhanced performance of RL-based VSL control over traditional approaches due to its generalizability, which contributes to the progression of Intelligent Transportation Systems by presenting a proactive and adaptable resolution for highway traffic management within dynamic real-world contexts.

Open Access: Yes

DOI: 10.5220/0012920700003822

Unveiling the mechanisms and implications: how artificial intelligence drives green growth in China’s Huaihe River Ecological Economic Belt under the carbon neutrality agenda

Laszlo Vasa Hasan Dincer Xin Zhao Ziqi Wang

Publication Name: Carbon Footprints

Publication Date: 2025-09-01

Volume: 4

Issue: 3

Page Range: Unknown

Description:

Amidst the backdrop of global climate warming and China’s proactive chase of its carbon peak and carbon neutrality goals, the Huaihe River Basin (HRB), a region of significant strategic importance in the heartland and eastern expanse of the nation is confronted with formidable challenges, including high energy consumption and severe environmental pollution. Despite its substantial contributions to economic development, the traditional development model of the HRB conflicts with the principles of green development, necessitating the urgent exploration of innovative pathways to sustainable progress. Through a comprehensive review of scholarly literature and rigorous theoretical analysis, this study demonstrates that artificial intelligence (AI) can significantly drive green development by enhancing eco-innovation and optimizing industrial structures. Using a panel dataset from 27 cities in the Huaihe River Ecological Economic Belt (HEB) from 2010 to 2022, this study employs a bidirectional fixed-effects model to analyze the repercussions of AI on green development. The baseline regression results show that for every one-unit increase in AI development level (AIDL), HEB’s urban green development level significantly increases by 0.087. This positive influence is further confirmed through robustness tests. We found that AI can indirectly influence the mechanism and pathway of green development through intermediate variables. AI drives green development indirectly through two pathways: green technology innovation and the rationalization of the industrial structure, with a total explanatory power of 56.7% (R2 = 0.812). Based on these findings, we propose vigorously promoting the green effects of AI, refining industrial structures, and leveraging mediating effects to foster sustainable regional development. These insights offer novel perspectives for the green development of the HRB but also provide valuable references for the green transformation of other areas with similar challenges.

Open Access: Yes

DOI: 10.20517/cf.2025.9

Expanded Applicability: Multi-Agent Reinforcement Learning-Based Traffic Signal Control in a Variable-Sized Environment

Bálint Kővári Bálint Pelenczei István Gellért Knáb László Palkovics Tamás Bécsi

Publication Name: Proceedings of the International Conference on Informatics in Control Automation and Robotics

Publication Date: 2024-01-01

Volume: 2

Issue: Unknown

Page Range: 15-25

Description:

During the development of modern cities, there is a strong demand articulated for the sustainability of progress. Since transportation is one of the main contributors to greenhouse gas emissions, the modernization and efficiency of transportation are key issues in the development of livable cities. Increasing the number of lanes does not always provide a solution and often is not feasible for various reasons. In such cases, Intelligent Transportation Systems are applied primarily in urban environments, mostly in the form of Traffic Signal Control. The majority of modern cities already employ adaptive traffic signals, but these largely utilize rule-based algorithms. Due to the stochastic nature of traffic, there arises a demand for cognitive decision-making that enables event-driven characteristics with the assistance of machine learning algorithms. While there are existing solutions utilizing Reinforcement Learning to address the problem, further advancements can be achieved in various areas. This paper presents a solution that not only reduces emissions and enhances network throughput but also ensures universal applicability regardless of network size, owing to individually tailored state representation and rewards.

Open Access: Yes

DOI: 10.5220/0012920800003822

Data Enrichment with Climate Reanalysis Data and Machine Learning for Analyzing Supply Adequacy in Renewable Power Systems

Adrienn Dineva Rita Fleiner Ágnes Gerse

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: 167-172

Description:

To overcome the limitations in using historical time series data for the supply adequacy analysis of renewable power systems, a data enhancement process is implemented allowing for a temporal enrichment of the available historical data. The methodology is based on the direct conversion of gridded climate reanalysis time series into aggregate output estimates where the simulated aggregate output is estimated by machine learning and historical power system data are used as training and testing data set. As a case study, the data enrichment methodology was accomplished with Hungarian power system data. From the enriched wind and solar electricity generation time series, availability statistics were derived that can be integrated into analytical probabilistic adequacy risk assessment models to describe the availability of wind and solar energy as aggregate, multi-state units.

Open Access: Yes

DOI: 10.1109/CINTI63048.2024.10830913

VR supported outer space education

Istvan Gulyas Laszlo Kadocsa Gyorgy Molnar

Publication Name: 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics Sami 2024 Proceedings

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 229-236

Description:

The basic aim of the research presented in this paper was a complex evaluation of a practical space exercise supported by virtual tools, with a special focus on the role of VR technology and the software used. The research also examined technological and methodological aspects such as the effectiveness of VR lab exercises, the quality of online learning materials and software, and the role of instructors. The methodology of our research was based on attitudinal analysis and descriptive statistical analysis, an important part of which was an evaluation of the VR software used, which not only characterises the current situation but also determines future development directions. As a result of our research, we can conclude that VR technology, especially 3D visualisation and interactive exercises, have proven to be particularly important in the learning process, but the future of VT technology in education is still perceived by students as somewhat uncertain due to infrastructural and resource constraints. Furthermore, our research results show that there is a need to improve the IT infrastructure and further optimize VR software, as well as a need for future research on resource allocation and technology integration beyond the pedagogical effectiveness of VR technology.

Open Access: Yes

DOI: 10.1109/SAMI60510.2024.10432907

First report of Rhodococcus fascians causing leafy gall on Iberis sempervirens in Hungary

László Palkovics Zoltán Bozsó András Künstler János Ágoston Judit Kolozsváriné Nagy Ildikó Schwarczinger Dénes Dlauchy Lóránt Király József Fodor

Publication Name: Phytopathologia Mediterranea

Publication Date: 2024-01-01

Volume: 63

Issue: 3

Page Range: 465-473

Description:

In spring of 2023, leafy gall symptoms were detected on plants of evergreen candytuft (Iberis sempervirens ‘Pink Ice’) in Hungary. Bacteria isolated from gall-like tissues of short, stunted shoots, and showing a characteristic appearance on selective culture media were investigated using bacteriological and molecular methods, and phylogenetic analysis. Nucleotide sequences of the 16S rRNA gene, fasD and vicA genes were determined. Pathogenicity of selected isolates was confirmed on garden pea (Pisum sativum ‘Tristar’). Characterization of the investigated isolates indicated the presence of Rhodococcus fascians in I. sempervirens. This is the first report identifying the causal agent of leafy gall from this plant in Hungary.

Open Access: Yes

DOI: 10.36253/phyto-15357

Comparison of three artificial intelligence methods for predicting 90% quantile interval of future insulin sensitivity of intensive care patients

Balazs Benyo J. Geoffrey Chase Bálint Szabó Katalin Kovacs Omer S. Alkhafaf Ameer B. Alsultani Akos Szlavecz Béla Paláncz

Publication Name: IFAC Journal of Systems and Control

Publication Date: 2024-12-01

Volume: 30

Issue: Unknown

Page Range: Unknown

Description:

Insulin dosing of hyperglycemic patients in the intensive care unit (ICU) is a complex and nonlinear clinical control problem. Recent model-based glycemic control protocols predict a patient-specific and time-specific future insulin sensitivity distribution, which defines the future patient state in response to insulin and nutrition inputs. The prediction methods provide a 90% confidence interval for a future insulin sensitivity distribution for a given time horizon, making the prediction problem more specific compared to common prediction problems where the aim is to predict the expected value of the given stochastic parameter. This study proposes three alternative artificial intelligence-based insulin sensitivity prediction methods to improve the prediction accuracy and make prediction parameters better fit the clinical requirements. The proposed prediction methods use different neural network models: a classification deep neural network model, a Mixture Density Network model, and a Quantile Regression-based model. A large patient data set was used to create the neural network models, including 2357 patients and 92646 blood glucose measurements from three clinical sites (Christchurch, New Zealand, Gyula, Hungary, and Liege, Belgium). Prediction accuracy was assessed by statistical metrics expressing clinical requirements, as well as via validated in-silico virtual patient simulations comparing the clinical performance of a proven glycaemic control protocol using the alternative prediction methods to assess impact on glycemic control performance and thus the need for these alternative models.

Open Access: Yes

DOI: 10.1016/j.ifacsc.2024.100284

Electrification of oil refineries through multi-objective multi-period graph-theoretical planning: A crude distillation unit case study

Ákos Orosz Bing Shen How Sin Yong Teng Abdulqader Bin Sahl Ferenc Friedler

Publication Name: Journal of Cleaner Production

Publication Date: 2024-01-01

Volume: 434

Issue: Unknown

Page Range: Unknown

Description:

Electrification using renewable energy sources is the key to paving a sustainable and cleaner future for the oil and gas sector, which is known to be a significant carbon dioxide emitter. Nevertheless, the suitability of the electrification designs heavily depends on the seasonal availability of renewable energy sources. This work proposes to use a multi-period graph-theoretical (P-graph) approach to determine the optimal retrofit strategy to achieve electrification with consideration of economic and environmental factors. Both single-period and multi-period models are considered via a graph-theoretical approach to rank and evaluate all the combinatorically feasible electrification pathways based on the overall performance. The effectiveness of the proposed method is developed using a crude distillation unit (CDU) case study adopted from a multinational company. The effectiveness of the proposed method is illustrated using a crude distillation unit (CDU) case study shown in three different scenarios that include prioritizing economic aspect (Scenario 1), prioritizing environmental aspect (Scenario 2), and considering equal importance of both aspects (Scenario 3). For single-period operation, the results showed a mix of natural gas and hydropower energy, exclusive use of onshore wind energy, and a mix of onshore wind energy and biogas cogeneration energy for Scenario 1, Scenario 2, and Scenario 3, respectively. In contrast, the multi-period model also utilized nuclear energy for Scenario 2 and Scenario 3 given the seasonal availability constraint. Following that, a sensitivity analysis is conducted to see the effect of the absence of the most influential energy sources on the optimal solution of each scenario and the top solutions under budget and CO2 emission constraints. Pareto analysis is outlined to offer an understanding of tradeoffs between differently prioritized solutions that decision-makers can select. The combination of the proposed analysis provides a systemic approach towards transforming traditional industries towards a cleaner future via electrification.

Open Access: Yes

DOI: 10.1016/j.jclepro.2023.140179

“What is going on in global goals projects, is agenda filled?” Highlighting circular economy literature within sustainable development goals–review-based

Lóránt Dávid Al Fauzi Rahmat Zoltán Bujdosó

Publication Name: Discover Sustainability

Publication Date: 2024-12-01

Volume: 5

Issue: 1

Page Range: Unknown

Description:

The global goal of development concerns has embraced global action, leading to framework initiatives grounded in future-proof projects. Closely aligned with circular economy (CE) initiatives, which minimize single-use materials and address practices that reflect sustainability concepts, studies are rapidly emerging to identify practices in CE literatures relevant to SDGs. Therefore, a study to identify the CE literatures' contribution towards domains and targets in SDGs is highly urgent. By drawing a total of 4431 as a sampling of final literature analyzed using instrument tools in metrics mapping. Our discovery shows that CE studies contribute to posts in SDGS target achievement, which keeps on increasing. To dive deep into CE research on CE’s relevance to SDGs, it was observed that China’s scholars offered their publications in various viewpoints. Significantly, SDG12 (n = 68.9%) and have exceeded half a percentage of publications covering CE relevance to SDGs, implied that CE studies focused heavily on sustainable consumption and production patterns through actions in reaching SDGs. Followed by SDG7 (n = 6.3%), strongly reinforcing CE provides assessed value in SDGs calling for affordable and sustainable development and energy for all, in line with relied CE actions in considering innovation models to recreate product and energy resource reuse practices in a bid to minimize the adverse impacts for future. Given additional insights on circular economy targets related to SDGs, the research implication was to provide a policy recommendation to encourage the practice of circular economy based on SDGs targets.

Open Access: Yes

DOI: 10.1007/s43621-024-00621-8