Search Everything

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

Publications - 6289

A new domain decomposition for B-spline neural networks

Cristiano L. Cabrita António E. Ruano László T. Kóczy

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

Publication Date: 2010-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

B-spline Neural Networks (BSNNs) belong to the class of networks termed grid or lattice-based associative memories networks (AMN). The grid is a key feature since it allows these networks to exhibit relevant properties which make them efficient in solving problems namely, functional approximation, non-linear system identification, and on-line control. The main problem associated with BSNNs is that the model complexity grows exponentially with the number of input variables. To tackle this drawback, different authors developed heuristics for functional decomposition, such as the ASMOD algorithm or evolutionary approaches [2]. In this paper, we present a complementary approach, by allowing the properties of B-spline models to be achieved by non-full grids. This approach can be applied either to a single model or to an ASMOD decomposition. Simulation results show that comparable results, in terms of approximations can be obtained with less complex models. © 2010 IEEE.

Open Access: Yes

DOI: 10.1109/IJCNN.2010.5596648

Classification of fullerene isomers using local topological descriptors

Eniko Bitay István László Tomislav Došlić Tamás Réti

Publication Name: Materials Science Forum

Publication Date: 2010-01-01

Volume: 659

Issue: Unknown

Page Range: 447-451

Description:

A method for the structural classification of fullerenes via graph invariants is presented. These graph invariants (called edge-parameters) represent the 9 different types of bonds existing in fullerenes between two neighbouring carbon atoms and they are also applicable to classify the fullerene isomers into equivalence classes. Discriminating performance of edge-parameters has been tested on the sets of C40 and C66 fullerene isomers. It is shown that the stability of C40 and C66 isomers can be efficiently predicted using a novel topological descriptor (Ω) defined as a function of four appropriately selected edge parameters. © (2010) Trans Tech Publications.

Open Access: Yes

DOI: 10.4028/www.scientific.net/MSF.659.447

Selection of straw waste reinforced sustainable polymer composite using a multi-criteria decision-making approach

Imre Fekete László Lendvai Tej Singh Sándor K. Jakab

Publication Name: Biomass Conversion and Biorefinery

Publication Date: 2024-09-01

Volume: 14

Issue: 17

Page Range: 21007-21017

Description:

The valorization of straw waste as a sustainable and eco-friendly resource in polymer composites is critical for resource recycling and environmental preservation. Therefore, many research works are being carried out regarding the development of wheat straw-based polymer composites to identify the reinforcing potential of these sustainable resources. In this study, three different sizes of wheat straw fibers (60–120 mesh, 35–60 mesh, and 18–35 mesh) were used, and their different ratios (0, 2.5, 5, 10, and 20% by weight) were systematically investigated for the physical and mechanical properties of polypropylene-based sustainable composites. The results indicated that the evaluated composites’ properties are strongly dependent on the quantity and size of the utilized wheat straw. Therefore, a preference selection index was applied to rank the developed sustainable polymer composites to select the best composition. Various properties of the composite materials were considered as criteria for ranking the alternatives, namely tensile strength and modulus, flexural stress at conventional deflection and flexural modulus, impact strength, density, water absorption, material cost, and carbon footprint. The decision-making analysis suggests the alternative with wheat straw content of 20 wt.% (35–60 mesh size) dominating the performance by maximizing the beneficial criteria and minimizing the non-beneficial criteria, making it the most suitable alternative. This study will significantly help formulation designers to deal with the amount and size issues when developing polymeric composites.

Open Access: Yes

DOI: 10.1007/s13399-023-04132-w

Motion control and communication of cooperating intelligent robots by fuzzy signatures

Tamás D. Gedeon Áron Ballagi László T. Kóczy

Publication Name: IEEE International Conference on Fuzzy Systems

Publication Date: 2009-12-10

Volume: Unknown

Issue: Unknown

Page Range: 1073-1078

Description:

This paper presents two examples of usage of fuzzy signatures in the field of mobile robotics. The first shows a complex lateral drift control method base on fuzzy signatures. This method inspects the motion system of the robot as a whole, unlike as simple parts of a complex system. The state space is written down by fuzzy signatures which add up flexibility, adaptability and learning ability to the system. In the second experiment a new communication approach is investigated for intelligent cooperation of autonomous mobile robots. Effective, fast and compact communication is one of the most important cornerstones of a high-end cooperating system. In this paper we propose a fuzzy communication system where the codebooks are built up by fuzzy signatures. We use cooperating autonomous mobile robots to solve some logistic problems. ©2009 IEEE.

Open Access: Yes

DOI: 10.1109/FUZZY.2009.5277207

Genotyping of a SORCS2 polymorphism and behavioural trait associations in newly developed laying hen populations

Eszter Zsédely Károly Tempfli Hidas András Erika Lencsés-Varga Szálai Klaudia Almási Anita Orbán Attila Sárvári Loretta Csilla Ágnes Bali Papp

Publication Name: Magyar Allatorvosok Lapja

Publication Date: 2021-06-01

Volume: 143

Issue: 6

Page Range: 351-358

Description:

Background: Cage-free egg production methods are advancing in the European Union due to stringent housing regulations, animal welfare and consumer pressure. A changing production environment requests novel adaptation strategies of which the development of specific layer hybrids or strains is notably promising. Cage-free housing systems allow for a rather complete expression of social behaviour in laying hen populations; however, increasing stress, aggression and feather pecking are considered as major consequences. Objectives: This study aimed to detect a recently described SORCS2 polymorphism in newly developed Hungarian laying hen populations and observe potential associations with behavioural traits. Cage-free housing technologies with or without outdoor acces were also compared. Materials and Methods: Occurrence of behavioural traits were individually recorded for 119 hens. A novel PCR-RFLP method was developed and applied for SORCS2 genotyping with Rsal endonuclase. Results and Discussion: The SORCS2 polymorphism was present In the Hungarian populations, Callele frequencies varied between 75.1-85.5%. Homozygous TT genotype was the least prevalent across the three experimental populations with frequencies 2.2-4.2%. The experimental hybrid populations demonstrated different (p < 0.05) levels of aggression and activity related behavioural patterns. Homozygous CC animals showed more cases of aggressive behaviour compared to other genotypes. Feather pecking was more common In populations with outdoor access compared to the closed barn system (p < 0.05). The social behaviour of laying hens Is affected by many factors in an Immensely complex system. Selection efficiency on behaviour can be improved with a more profound knowledge on Its genetics.

Open Access: Yes

DOI: DOI not available

Utility of time factor in logistic optimization

Peter Foldesi Edit Süle

Publication Name: Proceedings 2009 3rd International Workshop on Soft Computing Applications Sofa 2009

Publication Date: 2009-11-25

Volume: Unknown

Issue: Unknown

Page Range: 209-214

Description:

The paper deals with the investigation of the critical factor of the supply chain, with regards to time. The literature review can give a background to understand and handle the reasons and consequences of the growing importance of time. It analyses the time- and place-value of products and it evaluates time by showing theoretical functions as well. By using utility functions to represent the value of various delivery-times for the different participants in the supply chain, including the final customers, it proves through the Kano-model, that the choices, behaviour and willingness of payment of time-sensitive and non time-sensitive consumers are different for varying lead times, so for optimization soft computing techniques must be applied. © 2009 IEEE.

Open Access: Yes

DOI: 10.1109/SOFA.2009.5254851

Supersonic flow simulation on IBM cell processor based emulated digital cellular neural networks

Sándor Kocsárdi Zoltán Nagy András Kiss Árpád Csík

Publication Name: Proceedings IEEE International Symposium on Circuits and Systems

Publication Date: 2009-10-26

Volume: Unknown

Issue: Unknown

Page Range: 1225-1228

Description:

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. In this field, one of the most exciting areas is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. In engineering applications the temporal evolution of non-ideal, compressible fluids is quite often modeled by the system of Navier-Stokes equations. They are a coupled set of nonlinear hyperbolic partial differential equations and form a relatively simple, yet efficient model of compressible fluid dynamics. Unfortunately the necessity of the coupled multi-layered computational structure with nonlinear, space-variant templates does not make it possible to utilize the huge computing power of the analog Cellular Neural Network Universal Machine (CNN-UM) chips. To improve the performance of our solution emulated digital CNN-UM implemented on IBM Cell Broadband Engine has been used. The goal is to perform the operations with the highest possible parallelism. ©2009 IEEE.

Open Access: Yes

DOI: 10.1109/ISCAS.2009.5117983

Effect of bacterial inoculation on co-composting of lavender (Lavandula angustifolia Mill.) waste and cattle manure

E. Lakatos Ágnes Nagy Babett Greff András Sáhó Jenő Szigeti László Varga

Publication Name: 3 Biotech

Publication Date: 2021-06-01

Volume: 11

Issue: 6

Page Range: Unknown

Description:

The primary purpose of this study was to investigate the influence of Cellulomonas flavigena and Streptomyces viridosporus, as a bacterial inoculant, on the compostability of post-extraction lavender waste. The major physicochemical, microbiological, and biological properties of the composting materials were monitored for 161 days. The technology developed was shown to improve the compostability of recalcitrant herbal residues. The use of lavender waste beneficially affected the composting process by extending the thermophilic phase, accelerating the degradation of organic matter, and elevating the viable counts of useful microorganisms; however, adverse effects were also observed, including an increased carbon-to-nitrogen ratio (19.05) and a decreased germination index (93.4%). Bacterial inoculation was found to preserve the nitrogen content (2.50%) and improve the efficiency of biodegradation. The Salmonella- and Escherichia coli-free final composting products were mature, stable, and ready for soil application. To the authors’ knowledge, no previous research has investigated the compostability of lavender waste. Likewise, this is the first study that has used strains of C. flavigena and S. viridosporus in combination to facilitate a composting process.

Open Access: Yes

DOI: 10.1007/s13205-021-02860-2

Detection of Bus Driver Mobile Phone Usage Using Kolmogorov-Arnold Networks

Áron Ballagi Szabolcs Fischer János Hollósi Gabor Kovacs Viktor Nagy

Publication Name: Computers

Publication Date: 2024-09-01

Volume: 13

Issue: 9

Page Range: Unknown

Description:

This research introduces a new approach for detecting mobile phone use by drivers, exploiting the capabilities of Kolmogorov-Arnold Networks (KAN) to improve road safety and comply with regulations prohibiting phone use while driving. To address the lack of available data for this specific task, a unique dataset was constructed consisting of images of bus drivers in two scenarios: driving without phone interaction and driving while on a phone call. This dataset provides the basis for the current research. Different KAN-based networks were developed for custom action recognition tailored to the nuanced task of identifying drivers holding phones. The system’s performance was evaluated against convolutional neural network-based solutions, and differences in accuracy and robustness were observed. The aim was to propose an appropriate solution for professional Driver Monitoring Systems (DMS) in research and development and to investigate the efficiency of KAN solutions for this specific sub-task. The implications of this work extend beyond enforcement, providing a foundational technology for automating monitoring and improving safety protocols in the commercial and public transport sectors. In conclusion, this study demonstrates the efficacy of KAN network layers in neural network designs for driver monitoring applications.

Open Access: Yes

DOI: 10.3390/computers13090218