Search Everything

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

Publications - 6515

Artificial Intelligence Based Insulin Sensitivity Prediction for Personalized Glycaemic Control in Intensive Care

Balázs Benyó J. Geoffrey Chase Bálint Szabó Katalin Kovács Yahia Anane Ákos Szlávecz Béla Paláncz

Publication Name: IFAC Papersonline

Publication Date: 2020-01-01

Volume: 53

Issue: 2

Page Range: 16335-16340

Description:

Stress-induced hyperglycaemia is a frequent complication in the intensive therapy that can be safely and efficiently treated by using the recently developed model-based tight glycaemic control (TGC) protocols. The most widely applied TGC protocol is the STAR (Stochastic-TARgeted) protocol which uses the insulin sensitivity (SI) for the assessment of the patients state. The patient-specific metabolic variability is managed by the so-called stochastic model allowing the prediction of the 90% confidence interval of the future SI value of the patients. In this paper deep neural network (DNN) based methods (classification DNN and Mixture Density Network) are suggested to implement the patient state prediction. The deep neural networks are trained by using three years of STAR treatment data. The methods are validated by comparing the prediction statistics with the reference data set. The prediction accuracy was also compared with the stochastic model currently used in the clinical practice. The presented results proved the applicability of the neural network based methods for the patient state prediction in the model based clinical treatment. Results suggest that the methods' prediction accuracy was the same or better than the currently used stochastic model. These results are the initial successful step in the validation process of the proposed methods which will be followed by in-silico simulation trials.

Open Access: Yes

DOI: 10.1016/j.ifacol.2020.12.659

Impact of measurement and test parameters on the rpm-sweep test accuracy of e-motors

Balázs Vehovszky Zoltán Gazdagh D. Acs

Publication Name: 54th International Congress and Exposition on Noise Control Engineering Internoise 2025

Publication Date: 2025-01-01

Volume: 4

Issue: Unknown

Page Range: 70-77

Description:

The electrification of the vehicle industry has led to a significant increase in the demand for innovative vibration testing. The RPM-sweep experiments of e-motors and e-drives are considered to be fundamental, as they provide valuable vibration and durability data for further analysis. The aim is to model the behavior of rotating-dynamic systems throughout their life cycles. However, inaccuracies in the definition of measurement and test parameters can result inaccurate transfer functions, ultimately reducing the accuracy and reliability of the test results. This paper focuses on two critical parameters: frequency resolution and RPM-sweep rate. Both of these parameters have a significant impact on the amplitude response of the system and can lead to substantial distortion of the FRFs. In this study, we characterize these distortions and propose a method to ensure that the error introduced by the chosen frequency resolution and RPM-sweep rate remains below a predefined threshold value. In addition to the theoretical derivation, we demonstrate the application of this method using real measurement data. This research aims to address the challenges associated with NVH testing in the context of the electrification of the vehicle industry, providing a valuable contribution to the development of more accurate and reliable testing methodologies.

Open Access: Yes

DOI: 10.3397/IN_2025_1062472

Influence of frequency resolution in case of frequency response function measurement in structural dynamics

Balázs Vehovszky Zoltán Gazdagh

Publication Name: Acta Technica Jaurinensis

Publication Date: 2021-11-24

Volume: 14

Issue: 4

Page Range: 508-520

Description:

Frequency resolution is an essential parameter in acoustical testing, even if we are using numerical or experimental method, for example when determining frequency response function (FRF) of a dynamic mechanical system, or executing modal analysis based on the FRFs. Finer resolution leads to more accurate results, at the expense of longer calculation/measurement process and larger data size. This parameter is generally set based on rules of thumb, prior practice or with big margin for safety. This results in waste time and data storage if the required frequency resolution is overestimated, or even significant errors in the results, if it is underestimated. Present paper offers a direct, method for the conscious determination of optimal frequency resolution. It is based fully on theoretical considerations, and investigates amplitude and phase distortion at resonances as target parameters. Beside defining the steps of the process, it is tested on a real structure, and the results are presented as well, proving the applicability and the appropriateness of the method. With this method, development engineers get a practical tool for adjusting the parameters of dynamic measurements and simulations.

Open Access: Yes

DOI: 10.14513/actatechjaur.00618

Transformation of traditional assembly lines into interoperable CPPS for MES: An OPC UA enabled scenario

G. Pedone János Jósvai Norbert Szántó Gergő Monek B. Háy

Publication Name: Procedia Manufacturing

Publication Date: 2020-01-01

Volume: 54

Issue: Unknown

Page Range: 118-123

Description:

The exploitation of I4.0 paradigm requires the availability of adequate information across all engineering and production value chains, which is the result of aggregation and fusion of data from various heterogeneous sources, often under real-time conditions. On the one hand, this comprises a challenge for the provision of an efficient, secure and dependable information management infrastructure. On the other hand, system architects must find solutions to assure interoperability on both syntactical and semantic level with reasonable engineering costs. In this paper authors present the research outcomes related to the conceptualization of a generalized information model and a service architecture, for the transformation and integration of typical third-party, stand-alone industrial equipment-FESTO prolog-factory in the specific-into an OPC UA enhanced, Industry 4.0 interoperable CPPS for new generations of Manufacturing Execution Systems. Aim of the discussed approach is to define basic but general guidelines of applicability for the definition, modelling and provision of standardized, Industry 4.0 compliant, CPPS-based industrial services, starting off from a typical legacy industrial environment.

Open Access: Yes

DOI: 10.1016/j.promfg.2021.07.019

Transportation network realization with an optimization method

Tamás Hartványi András Bakó István Szuts

Publication Name: Isciii 09 4th International Symposium on Computational Intelligence and Intelligent Informatics Proceedings

Publication Date: 2009-12-28

Volume: Unknown

Issue: Unknown

Page Range: 81-84

Description:

In connection with the network realization problem the main questions of the algorithm are which edges to choose and what is the budget consequence of that. These problems can be solved by exact optimization methods, but in this case the number of computational steps (additions and comparisons) is an exponential function of the number of nodes. For this reason usually heuristic methods are chosen for solving these problems. Some special problems can be formulated as maximal flow problems. To get the solution we use only maximal flow and shortest route algorithms. Thus we decrease the number of computations, but the size of the network will grow. In this paper we describe this algorithm to solve the network realization problem. Then we give a transportation network realization problem and show how to solve this problem by the some algorithms. © 2009 IEEE.

Open Access: Yes

DOI: 10.1109/ISCIII.2009.5342277

Oestrogens and oestrogenic substances in plant cultivation

Pál Szakál Judit Plutzer Eduard Gubó

Publication Name: Agrokemia Es Talajtan

Publication Date: 2019-01-01

Volume: 68

Issue: 2

Page Range: 385-401

Description:

A compound is oestrogenic, when -even if with low affinity but can bind to oestrogen receptors (ER)- resulting in a biological effect in oestrogen sensitive cells, which are similar to processes caused by the ovarian derived oestrogen hormones. According to literature data, due to slurry irrigation and intensive livestock manure application, due to the direct contact with the land, steroidal oestrogens, including oestrogen E1, oestradiol E2, oestriol E3, and synthetic oestrogen EE2 are ubiquitous in the fertile soil. Plants can accumulate oestrogens in their roots and shoots, which when entering the food chain may have an impact on human health. Slurry can only be applied to agricultural land with the permission of the soil protection authority, which also determines the amount of slurry that can be applied to the area. The different types of slurry differ not only in their nutrient composition but also in their EDC content. Regarding the natural hormone excretion and use of hormonal preparations it is important to consider the sex ratio and age range of livestock in the case of selection. It is important for the future that we carry out toxicological studies and place greater emphasis on the amount and potential effects of hormonal substances released by agricultural side products.

Open Access: Yes

DOI: 10.1556/0088.2019.00002

Minimizing Freshwater Usage in Batch Process Scheduling: S-Graph Approach

Máté Hegyháti Olivér Osz Dominic C.Y. Foo

Publication Name: Process Integration and Optimization for Sustainability

Publication Date: 2021-03-01

Volume: 5

Issue: 1

Page Range: 31-42

Description:

Water is one of the most important natural resources of life. While it is considerably cheap and vastly available currently, except for extreme locations, this is not guaranteed in the future. Being provident with water has multitude of advantages in both short and long term. Using less clean water not only brings immediate financial benefits, it simultaneously reduces wastewater production, related treatment costs, and the impact on the environment. Reducing the water footprint of a batch system is not a trivial task, as water sources and sinks need to be matched not only in quantity and quality, but in time as well. In this paper, the S-graph scheduling framework is extended to address simultaneous scheduling and water minimization in batch processing systems. The proposed approach tackles truly batch processes with a single contaminant, and allows only a single water source to be reused for each sink. The presented algorithm and S-graph extension have been implemented and tested on various case studies from the literature. The results of this paper provide an opportunity for further extensions to address a wider range of problems with multiple contaminants, semi-continuous behavior, cyclic operations, etc.

Open Access: Yes

DOI: 10.1007/s41660-020-00142-7

The Acquisition of Phonological Awareness in Children with Mild General Learning Difficulties: Delayed or Disordered Speech Development?

No authors available

Publication Name: On Under-Reported Monolingual Child Phonology

Publication Date: 2020-01-01

Volume:

Issue:

Page Range: 274-323

Description:

Open Access: No

DOI: DOI not available

Collaborative Knowledge Platform: when the learning route provides data for the Knowledge-based System

Gabriella Haasz Zoltán Baracskai

Publication Name: Knowledge Management Research and Practice

Publication Date: 2022-01-01

Volume: 20

Issue: 6

Page Range: 925-934

Description:

The Digital Age has brought not only new tools but also several new methods. A Collaborative Knowledge Platform with a hybrid intelligent system may be the appropriate base of a knowledge management system to ensure inspiration and new knowledge for a professional group of individuals. The introduced concept contributes to Knowledge Collaboration and Knowledge Engineering. The method is a special form of Knowledge Engineering which involves combining machine learning algorithms with cased-based reasoning and the result is the transformation of personal knowledge to widely adaptable explicit knowledge. Individuals can learn informally while their learning route automatically generates data for reductive reasoning process, which finally leads to the opportunity of experience mining. A concept and an approach are suggested to improve the knowledge collaboration in innovative communities, and a creative problem solving process delivers the outcome in the development of a Knowledge Management System. Finally, some partial results of the design phase of an application are presented.

Open Access: Yes

DOI: 10.1080/14778238.2022.2079567