Search Everything

Tip: Search using "First Name + Last Name", e.g.
János Kiss instead of Kiss János.

Publications - 6278

Adaptive few-shot tiny neural systems for real-time traffic intensity prediction in smart cities

Dragan Pamucar Aanjankumar Sureshkumar Rajesh Kumar Dhanaraj Maragatharajan Muthusamy Aanjankumar Sureshkumar Maragatharajan Muthusamy Rajesh Kumar Dhanaraj Balakannan sirumolasi Paramasivam

Publication Name: ICT Express

Publication Date: 2025-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The rapid evolution of urban mobility and smart city demands an intelligent transportation system which can make real-time decisions using lightweight and adaptive AI models. This research introduces a novel application of tiny machine learning which will combine the features of Few-shot learning algorithm and it will classify the traffic intensity levels on regional traffic data. By converting the traffic volume into three dynamic classes (Low/ Medium/ High), a compact neural network model is trained on episodic few-shot tasks that can mimic real-world low-data learning conditions. The proposed work supports open set classification which is more suitable for detecting unknown traffic behavior analysis by considering the previous day traffic level and how the future traffic intensity level can be predicted effectively. The accuracy of the proposed method is compared with the existing methods which lie with the baseline CNN (90 %) and SVM (89 %). But the average episode accuracy achieved through the proposed model is 95.2 % which makes this model promising for low-power edge deployment in intelligent transportation system.

Open Access: Yes

DOI: 10.1016/j.icte.2025.08.010

Large scale simulations of the euler equations on GPU clusters

Manfred Liebmann Craig C. Douglas Zoltán Horváth Gundolf Haase

Publication Name: Proceedings 9th International Symposium on Distributed Computing and Applications to Business Engineering and Science Dcabes 2010

Publication Date: 2010-11-05

Volume: Unknown

Issue: Unknown

Page Range: 50-54

Description:

The paper investigates the scalability of a parallel Euler solver, using the Vijayasundaram method, on a GPU cluster with 32 Nvidia Geforce GTX 295 boards. The aim of this research is to enable large scale fluid dynamics simulations with up to one billion elements. We investigate communication protocols for the GPU cluster to compensate for the slow Gigabit Ethernet network between the GPU compute nodes and to maintain overall efficiency. A diesel engine intake-port and a nozzle, meshed in different resolutions, give good real world examples for the scalability tests on the GPU cluster. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/DCABES.2010.17

Fabrication of Europium-Doped Barium Titanate/Polystyrene Polymer Nanocomposites Using Ultrasonication-Assisted Method: Structural and Optical Properties

Diwakar Padalia László Lendvai Prabhakar Bhandari Pawan Kumar Lalit Ranakoti Tej Singh Umesh Kumar

Publication Name: Polymers

Publication Date: 2022-11-01

Volume: 14

Issue: 21

Page Range: Unknown

Description:

In the current work, europium-doped barium titanate particles were used as filler material and polystyrene was used as a matrix to fabricate Ba1−3x/2EuxTiO3/PS polymer nanocomposites with x = 0, 0.005, 0.015 and 0.025. A solid-state reaction was used to synthesize filler particles and the solvent evaporation method was used to form polymer nanocomposites. The effects of ultrasonic treatment were also studied in the formation of nanocomposite materials. The quantitative and qualitative studies were conducted using X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), field emission scanning electron microscopy (FE-SEM), and ultraviolet-visible (UV-Vis) characterization techniques. The XRD data and FTIR data confirm the incorporation of filler particles in the polymer matrix. FE-SEM data confirms that the particles are in the nanophase. The optical band gap was directly affected by the filler particles and it started to reduce as Eu concentration started to increase.

Open Access: Yes

DOI: 10.3390/polym14214664

Material Models to Study the Effect of Fines in Sandy Soils Based on Experimental and Numerical Results

Ammar N. Alnmr

Publication Name: Acta Technica Jaurinensis

Publication Date: 2021-11-24

Volume: 14

Issue: 4

Page Range: 651-680

Description:

Choosing and calibrating a robust and accurate soil material model (constitutive model) is the first important step in geotechnical numerical modelling. A less accurate model leads to poor results and more difficulty estimating true behaviour in the field. Subsequent design work is compromised and may lead to dangerous and costly mistakes. In this research, laboratory experimental results were used as a basis to evaluate several soil material models offered in Plaxis2D software. The deciding feature of the soil model was how well it could represent effects of percentage of fine material within sandy soils to simulate its behaviour. Results indicate that the Hardening Soil (HS) model works well when the percentage of fine (soft) materials is less than 10%. Above that level, the Soft Soil model (SS) becomes the most suitable. Finally, some important conclusions about this research and recommendations for future research are highlighted.

Open Access: Yes

DOI: 10.14513/actatechjaur.00625

Integration of BIM in architecture and structural engineering education through common projects

T. Horváth János Szép Kitti Karolyfi Dóra Szalai

Publication Name: Acta Technica Jaurinensis

Publication Date: 2021-11-24

Volume: 14

Issue: 4

Page Range: 424-439

Description:

Building Information Modeling (BIM) is one of the most significant developments in architecture and civil engineering in recent years, therefore it becomes increasingly important to promote its integration into university education. Currently, several universities worldwide offer BIM courses in architecture and civil engineering programs, while many others are under the process of integrating BIM into their curricula. The goal of this research is the implementation of BIM into higher education (Széchenyi István University, Hungary) by integrating the architectural, structural, and mechanical engineering disciplines. An important advantage of the university is that the architecture and civil engineering programs belong to the same faculty, which allows students to work together on common projects. A new course was performed in the previous semester, in which the students are designing contemporary buildings as case studies. In this paper, the results of the integration process are presented and evaluated based on the trainers’ and students’ experiences.

Open Access: Yes

DOI: 10.14513/actatechjaur.00641

Three level fuzzy signature based decision methodology for packaging system design

Peter Foldesi Adrienn Buruzs Kata Vöröskoi Gergő Fogarasi László T. Kóczy

Publication Name: Journal of Automation Mobile Robotics and Intelligent Systems

Publication Date: 2020-01-01

Volume: 14

Issue: 2

Page Range: 99-105

Description:

In the field of logistics packaging, companies have to take decisions on determining the optimal packaging solutions and expenses. The decisions often involve a choice between one-way (disposable) and reusable (returnable) packaging solutions. Even nowadays, in most cases the decisions are made based on traditions and mainly consider the material and investment costs. Although cost is an important factor, it might not be sufficient for finding the optimal solution. Traditional (two-valued) logic is not suitable for modelling this problem, so here the application of a fuzzy approach, because of the metrical aspects, a fuzzy signature approach is considered. In this paper three different fuzzy signatures connected by fuzzy rules modelling the packaging decision are suggested, based on logistics expert opinions, in order to support the decision making process of choosing the right packaging system. Two real life examples are also given, one in the field of customer packaging and one in industrial packaging.

Open Access: Yes

DOI: 10.14313/JAMRIS/2-2020/25

Entity-relation enhanced bidirectional information fusion for relational triples extraction

Dragan Pamucar Mingming Kong Yuan Rong Chao Zhang Haoran Liao Xianjun Tian Vladimir Simic

Publication Name: Engineering Applications of Artificial Intelligence

Publication Date: 2026-01-01

Volume: 163

Issue: Unknown

Page Range: Unknown

Description:

Relational triple extraction refers to identifying triples consisting of entities and relations form unstructured texts. The existing studies usually adopt an unidirectional extraction strategy, which fails to fully explore the semantic information related to entities and relations. And they rely heavily on initial extraction results when conducting multi-step extraction. To address this issue, we propose a novel Entity-Relation Enhanced Bidirectional Information Fusion approach (ER-EBIF). Specifically, we adopt a bidirectional extraction strategy of ”entity-to-relation” and ”relation-to-entity” to identify triples. One branch extracts potential relations, then extracts entities associated with those relations. The other branch initially extracts the potential subjects and objects as well as subsequently extracts relations between pairs of entities consisting of subjects and objects. Moreover, the contextual information is enhanced with a self-attention mechanism by integrating the information of potential relations and potential entities to better exploit the semantic information of entities and relations. Extensive experimental results on various datasets show that ER-EBIF exhibits better performance than other baselines and effectiveness in addressing the issue of dependency on initial results in multi-step extraction.

Open Access: Yes

DOI: 10.1016/j.engappai.2025.113033

Challenges of Corporate Ecological Footprint Calculations in the SME Sector in Hungary: Case Study Evidence from Six Hungarian Small Enterprises

Cecília Szigeti Áron Szennay L. Radácsi J. Lisányi Endréné Beke J. R.Polák Weldon

Publication Name: Agroecological Footprints Management for Sustainable Food System

Publication Date: 2020-01-01

Volume: Unknown

Issue: Unknown

Page Range: 345-363

Description:

Scientific and social discourse examines primarily the environmental performance of large enterprise actors. Although these large enterprises usually operate on an international level, over half of the added value created in the European Union and thus over half of the environmental damage are generated by small- and medium-sized enterprises (SME). Nevertheless, while the tools and expertise required to measure environmental performance are available for large enterprises, the SME sector has only limited access to these tools. s part of our research, we have developed an ecological footprint (EF) calculator applicable to the specificities of the SME sector, which has been tested on six Hungarian companies operating in different sectors and organisational frameworks. The test results indicate that the managerial information system of partnerships includes all the main inputs that are necessary to estimate a company’s EF. However, in the case of sole proprietorships, most of the required data can only be acquired by estimation. Our EF calculations on analysed firms cannot be considered as representative data. But on the base of the case studies, we can suggest that our EF calculator for SMEs is suitable to take a more comprehensive survey on EF of Hungarian and international firms, in order to generate sectoral benchmarks. Ecological footprint among analysed enterprises ranged between 5102 and 263,589 global square metres. It is caused mainly by (1) the sector (e.g. constructions have generally larger footprints than office activities) and (2) the size, expressed in number of employees or value added. To increase transparency of the environmental performance of the SME sector, we recommend that the supplementary annex of partnerships includes the main input data necessary for the calculation of the EF in a comparable and consistent way, in natural units of measurement. With such information and our calculator, it would be possible to determine the average environmental impact of the individual sectors, which would provide an appropriate starting point for the environmental investments of enterprises.

Open Access: Yes

DOI: 10.1007/978-981-15-9496-0_11

Az élet természeti alapjainak védelmi rendszerei

Gergely Horváth

Publication Name: Tarsadalomkutatas

Publication Date: 2013-12-01

Volume: 31

Issue: 4

Page Range: 386-402

Description:

Environmental protection, habitat protection, protection of the living world and nature conservation share the same foundations. All these four protective systems make an effort - with an aim of protecting the society - to protect "the natural bases of life", which are threatened by damaging and over-consuming by humankind. The aspect of organisations (subjective side), the special environmental organs make an essential part of the system of protection. Finally, the specific protective device of nature conservation and habitat protection, the zone system of protected areas gets into the focus of the examination, which also can be considered as a complex defensive system of the natural bases of life.

Open Access: Yes

DOI: 10.1556/Tarskut.31.2013.4.6