Search in Publications
Found 5157 publications
Localization robustness improvement for an autonomous race car using multiple extended Kalman filters
Publication Name: Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Publication Date: 2025-08-01
Volume: 239
Issue: 9
Page Range: 3771-3783
Description:
In this paper, we introduce a vehicle localization method designed for the SZEnergy race car, which competes in the Shell Eco-marathon. The proposed method comprises four different extended Kalman filter-based localization algorithms and a selection algorithm that determines the most suitable one based on vehicle speed, GNSS availability, and signal quality. The low-speed Kalman filters are based on a kinematic vehicle model while the high-speed variants are based on a dynamic vehicle model. Several measurements were performed during test maneuvers to evaluate the performance of the filters. The proposed method succesfully handles sensor miscalibration and GNSS outages.
Open Access: Yes
Adaptive Sign Language Recognition for Deaf Users: Integrating Markov Chains with Niching Genetic Algorithm
Publication Name: AI Switzerland
Publication Date: 2025-08-01
Volume: 6
Issue: 8
Page Range: Unknown
Description:
Sign language recognition (SLR) plays a crucial role in bridging the communication gap between deaf individuals and the hearing population. However, achieving subject-independent SLR remains a significant challenge due to variations in signing styles, hand shapes, and movement patterns among users. Traditional Markov Chain-based models struggle with generalizing across different signers, often leading to reduced recognition accuracy and increased uncertainty. These limitations arise from the inability of conventional models to effectively capture diverse gesture dynamics while maintaining robustness to inter-user variability. To address these challenges, this study proposes an adaptive SLR framework that integrates Markov Chains with a Niching Genetic Algorithm (NGA). The NGA optimizes the transition probabilities and structural parameters of the Markov Chain model, enabling it to learn diverse signing patterns while avoiding premature convergence to suboptimal solutions. In the proposed SLR framework, GA is employed to determine the optimal transition probabilities for the Markov Chain components operating across multiple signing contexts. To enhance the diversity of the initial population and improve the model’s adaptability to signer variations, a niche model is integrated using a Context-Based Clearing (CBC) technique. This approach mitigates premature convergence by promoting genetic diversity, ensuring that the population maintains a wide range of potential solutions. By minimizing gene association within chromosomes, the CBC technique enhances the model’s ability to learn diverse gesture transitions and movement dynamics across different users. This optimization process enables the Markov Chain to better generalize subject-independent sign language recognition, leading to improved classification accuracy, robustness against signer variability, and reduced misclassification rates. Experimental evaluations demonstrate a significant improvement in recognition performance, reduced error rates, and enhanced generalization across unseen signers, validating the effectiveness of the proposed approach.
Open Access: Yes
DOI: 10.3390/ai6080189
Exploring Generation Z’s Acceptance of Artificial Intelligence in Higher Education: A TAM and UTAUT-Based PLS-SEM and Cluster Analysis
Publication Name: Education Sciences
Publication Date: 2025-08-01
Volume: 15
Issue: 8
Page Range: Unknown
Description:
In recent years, the rapid growth of artificial intelligence (AI) has significantly transformed higher education, particularly among Generation Z students who are more open to new technologies. Tools such as ChatGPT are increasingly being used for learning, yet empirical research on their acceptance, especially in Hungary, is limited. This study aims to explore the psychological, technological, and social factors that influence the acceptance of AI among Hungarian university students and to identify different user groups based on their attitudes. The methodological novelty lies in combining two approaches: partial least-squares structural equation modelling (PLS-SEM) and cluster analysis. The survey, based on the TAM and UTAUT models, involved 302 Hungarian students and examined six dimensions of AI acceptance: perceived usefulness, ease of use, attitude, social influence, enjoyment and behavioural intention. The PLS-SEM results show that enjoyment (β = 0.605) is the strongest predictor of the intention to use AI, followed by usefulness (β = 0.167). All other factors also had significant effects. Cluster analysis revealed four groups: AI sceptics, moderately open users, positive acceptors, and AI innovators. The findings highlight that the acceptance of AI is shaped not only by functionality but also by user experience. Educational institutions should, therefore, provide enjoyable and user-friendly AI tools and tailor support to students’ attitude profiles.
Open Access: Yes
Socio-political determinants of circular economy behavior: A cross-sectional analysis across Italy
Publication Name: Socio Economic Planning Sciences
Publication Date: 2025-08-01
Volume: 100
Issue: Unknown
Page Range: Unknown
Description:
The circular economy (CE) has emerged as a crucial alternative to the traditional linear economic model, which relies on resource extraction, production, and waste disposal, resulting in significant environmental degradation and resource depletion. In contrast, the CE emphasizes resource efficiency through practices such as reusing, repairing, refurbishing, and recycling, providing both environmental and economic benefits. This study investigates the complex interaction between socio-political factors and individual-level CE practices in Italy, addressing gaps in existing research that primarily focus on specific consumer behaviors or demographic characteristics. Particularly, utilizing probit and multivariate probit analyses on the 2021 AVQ “Aspects of Daily Life” dataset from ISTAT, the research examines how socio-political involvement, budget constraints, positive educational externalities, and demographic factors influence CE behaviors. The findings reveal that socio-political factors, particularly political trust in local governments, significantly influence circular practices, with higher trust associated with greater adoption of sustainable transportation and local products, while lower political engagement correlates with increased waste and reduced sustainability, highlighting the need for targeted educational initiatives and localized policies to promote a circular economy effectively.
Open Access: Yes
Water Insecurity and Development Cooperation: Hungary’s Engagement in Africa
Publication Name: Grassroots Journal of Natural Resources
Publication Date: 2025-08-01
Volume: 8
Issue: 2
Page Range: 1-27
Description:
The Sustainable Development Report 2023 showed that 2.2 billion people lacked access to safely managed drinking water in 2022, with 703 million unable to access even basic services. In addition to this, the Afrobarometer’s 2024 survey indicated that Sub-Saharan Africa water supply was ranked among the top governance challenges in 39 surveyed countries. This study explores regional and urban–rural disparities in access to drinking water, while also assessing the scope and geography of Hungary’s water-related development cooperation on the continent. The methodology combines quantitative indicators from the UNICEF–WHO Joint Monitoring Programme with geospatial visualization techniques. The analysis reveals substantial inequalities in rural Eastern Africa, over 97 million people rely on surface water or unimproved sources, while Middle Africa reports more than 55 million in the same categories. In contrast, urban areas in Northern Africa show significantly better outcomes, with over 111 million having access to safely managed drinking water. These figures highlight persistent spatial divides and the critical need for targeted investment in rural service provision. Hungarian development engagement was examined through project records from the Ministry of Foreign Affairs and Trade, alongside publicly available data from Hungarian NGOs and private sector actors. The study finds that Hungary has contributed to water-related initiatives in countries such as the Democratic Republic of the Congo, Ghana, and Uganda, but has had limited involvement in other severely affected countries, including Niger (31% unsafe access), Madagascar (42%), and the Central African Republic (37%). This study addresses a significant research gap since the intersection of Hungarian development cooperation and African water security has received minimal scholarly attention to date. By offering a comprehensive, data-driven analysis of both African water access and Hungary’s related foreign engagement, the research contributes to the understanding of potential synergies and future avenues for international collaboration in this field.
Open Access: Yes
Blockchain and Smart Cities: Co-Word Analysis and BERTopic Modeling
Publication Name: Smart Cities
Publication Date: 2025-08-01
Volume: 8
Issue: 4
Page Range: Unknown
Description:
Highlights: What are the main findings? Blockchain plays a foundational role in supporting secure, interoperable infrastructure for key urban services, particularly through integration with IoT, edge computing, and smart contracts. Research has shifted from general blockchain exploration to sector-specific applications, including decentralized healthcare, energy trading, smart mobility, and drone coordination. What is the implication of the main finding? Blockchain enables cross-sectoral innovation in smart cities by enhancing transparency, data integrity, and trust across complex urban systems. As both a technological and ethical infrastructure, blockchain supports the development of secure, resilient, and sustainable smart city ecosystems aligned with Industry 5.0 values. This paper explores the intersection of blockchain technology and smart cities to support the transition toward decentralized, secure, and sustainable urban systems. Drawing on co-word analysis and BERTopic modeling applied to the literature published between 2016 and 2025, this study maps the thematic and technological evolution of blockchain in urban environments. The co-word analysis reveals blockchain’s foundational role in enabling secure and interoperable infrastructures, particularly through its integration with IoT, edge computing, and smart contracts. These systems underpin critical urban services such as transportation, healthcare, energy trading, and waste management by enhancing data privacy, authentication, and system resilience. The application of BERTopic modeling further uncovers a shift from general technological exploration to more specialized and sector-specific applications. These include real-time mobility systems, decentralized healthcare platforms, peer-to-peer energy exchanges, and blockchain-enabled drone coordination. The results demonstrate that blockchain increasingly supports cross-sectoral innovation, enabling transparency, trust, and circular flows in urban systems. Overall, the current study identifies blockchain as both a technological backbone and an ethical infrastructure for smart cities that supports secure, adaptive, and sustainable urban development.
Open Access: Yes
Mechanism of environmental regulation on energy productivity, energy structure, and carbon emissions: The role of directed technological progress
Publication Name: Energy
Publication Date: 2025-08-01
Volume: 328
Issue: Unknown
Page Range: Unknown
Description:
The mechanism of environmental regulation on energy conservation and carbon reduction in the petrochemical industry through directed technological progress remains uncertain due to the directional characteristics of technology. This paper develops a mechanism framework and employs a panel two-way fixed-effects model to clarify the impact of environmental regulation on directed technological progress and energy conservation, while uncovering its underlying mechanisms. Subsequently, a dynamic Kaya model is constructed, using the Monte Carlo method to determine the required intensity of environmental regulation for China's petrochemical industry to actualize the SSP1-CHN, SSP1, and SSP2 scenarios. The model also simulates the future bias of technological progress, energy utilization, and potential carbon emissions under each scenario. The findings indicate that increasing the intensity of environmental regulation drives technological progress toward energy conservation, thereby enhancing energy-saving biased technological progress, improving energy productivity, and optimizing the energy structure. Furthermore, to actualize the carbon peak by 2030 and carbon neutrality by 2060 under the SSP1-CHN scenario, the annual growth rate of environmental regulation intensity in China's petrochemical industry should be no less than 8 % before 2030 and should be strengthened to 20 % after 2030.This study not only extends the application of directed technological progress theory in the energy field but also provides innovative and practical environmental policy recommendations for the low-carbon development of the global petrochemical industry.
Open Access: Yes
When Industry 5.0 Meets the Circular Economy: A Systematic Literature Review
Publication Name: Circular Economy and Sustainability
Publication Date: 2025-08-01
Volume: 5
Issue: 4
Page Range: 2621-2652
Description:
This paper examines the convergence of Industry 5.0 and the circular economy, emphasizing the role of emerging technologies in promoting sustainability via human-centric approaches. In contrast to Industry 4.0, which prioritizes automation and digitalization, Industry 5.0 stresses the synergistic integration of technology, environmental sustainability, and human collaboration to enhance resource efficiency and minimize waste. Using co-word analysis and BERTopic modeling on 283 journal articles extracted from the Scopus database, this research identifies key trends and themes linking Industry 5.0 and the circular economy. The study findings demonstrate the use of automation, machine learning, and 3D printing in sustainable manufacturing, which aligns with circular economy principles by optimizing resource efficiency and reducing waste. The topic modeling analysis further demonstrates the role of blockchain, cybersecurity, and human-centric AI in enabling closed-loop systems while assuring transparency and accountability in circular production models. The collaboration between humans and machines emerges as a crucial topic highlighting the need for adaptive manufacturing systems to balance productivity and environmental responsibility. The findings indicate that Industry 5.0 increasingly aligns with circular economy goals, paving the way to more sustainable, resilient, and human-centric industrial processes. This study offers valuable insights for academics and practitioners, indicating that the confluence of technology, sustainability, and human involvement will propel the future of industrial innovation.
Open Access: Yes
The role of artificial intelligence in enhancing corporate environmental information disclosure: Implications for energy transition and sustainable development
Publication Name: Energy Economics
Publication Date: 2025-08-01
Volume: 148
Issue: Unknown
Page Range: Unknown
Description:
Global climate and environmental issues pose severe challenges to the sustainable development of human society. As major contributors to environmental pollution and carbon emissions, the quality of enterprises' environmental data has gained significant attention in academic and industrial circles. This study analyzes information from Chinese A-share companies spanning 2012 to 2023 to investigate the pathways through which artificial intelligence (AI) technology influences corporate environmental information disclosure (EID). The results indicate that AI significantly enhances the quality of corporate EID by optimising internal control levels and strengthening external supervision mechanisms. These conclusions have been validated through robustness and endogeneity tests. The heterogeneity analysis further reveals that the promoting effect of AI is more significant in large corporates, corporates in central cities, mature corporates, corporates audited by the Big Four international accounting firms, high-tech corporates, and heavily polluting industries. The study innovatively constructs a dual-path theoretical framework of ‘internal management optimisation–external supervision strengthening’ and integrates macro urban AI indicators with micro enterprise data, contributing new empirical support for the digital transformation and green governance of developing countries. Based on these findings, policymakers should promote the innovative application of AI technology in corporate environmental governance, improving internal control norms, optimising the external supervision system, and implementing a classified guidance strategy for different enterprise attributes, so as to help enterprises achieve low-carbon transformation and sustainable development.
Open Access: Yes
