Search in Publications

Found 6327 publications

A transfer learning approach for the classification of liver cancer

Belal Al-Khateeb Fatimah I. Abdulsahib Ĺaszĺo T. Ḱoczy Szilvia Nagy

Publication Name: Journal of Intelligent Systems

Publication Date: 2023-01-01

Volume: 32

Issue: 1

Page Range: Unknown

Description:

Problem: The frequency of liver cancer is rising worldwide, and it is a common, deadly condition. For successful treatment and patient survival, early and precise diagnosis is essential. The automated classification of liver cancer using medical imaging data has shown potential outcome when employing machine and deep learning (DL) approaches. To train deep neural networks, it is still quite difficult to obtain a large and diverse dataset, especially in the medical field. Aim: This article classifies liver tumors and identifies whether they are malignant, benign tumor, or normal liver. Methods: This study mainly focuses on computed tomography scans from the Radiology Institute in Baghdad Medical City, Iraq, and provides a novel transfer learning (TL) approach for the categorization of liver cancer using medical images. Our findings show that the TL-based model performs better at classifying data, as in our method, high-level characteristics from liver images are extracted using pre-trained convolutional neural networks compared to conventional techniques and DL models that do not use TL. Results: The proposed method using models of TL technology (VGG-16, ResNet-50, and MobileNetV2) successfully achieves high accuracy, sensitivity, and specificity in identifying liver cancer, making it an important tool for radiologists and other healthcare professionals. The experiment results show that the diagnostic accuracy in the VGG-16 model is up to 99%, ResNet-50 model 100%, and 99% total classification accuracy was attained with the MobileNetV2 model. Conclusion: This proves the improvement of models when working on a small dataset. The use of new layers also showed an improvement in the performance of the classifiers, which accelerated the process.

Open Access: Yes

DOI: 10.1515/jisys-2023-0119

Green Generation(s): the Generational Peculiarities of the Environmental Attitude

Nikolett Gyurián Nagy Nikolett Gyurián Nagy

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 199-204

Description:

Making consumption sustainable has become indispensable nowadays and is a necessary step in development. Several studies are dealing with the environmental attitude of consumers. Scientists are interested in the generational differences as well. However, there is still a gap that proves the difference between generations. More studies have examined how age affects environmental values. For example, this topic was examined in 6 countries between 1991 and 2017 in the framework of the European Values Study (EVS). Nowadays, generation Z may be regarded as the most environment-conscious. On the other hand, different results also came to light, which proves that however apparent the environmental efforts of generations Z and Y are, they still do not occupy the first rank in reducing the ecological footprint. The aim of the study is that based on a sample consisting of 2224 Hungarian people, an answer can be given to the question of whether age can really determine environmental attitude and whether generational differences occur in „thinking green”. The focus of the study is the wide-range examination of the environmental attitude. The basis of the study is, for example, socially conscious consumer behaviour and ecologically conscious consumer behaviour. Besides this, such background factors also appear in the study, which may affect the attitude and behaviour, such as optimism, pessimism, motives and other influencing factors.

Open Access: Yes

DOI: 10.3303/CET23107034

Fuzzy Inference System-like Aggregation Operator for Fuzzy Signatures

Adam Bukovics Ferenc Lilik Ĺaszĺo T. Ḱoczy

Publication Name: Studies in Computational Intelligence

Publication Date: 2023-01-01

Volume: 1040

Issue: Unknown

Page Range: 93-101

Description:

This paper deals with a novel fuzzy aggregation operator. This aggregation operator is suggested to such fuzzy signatures, where the correlation between the leafs or branches can not be handled by classical operators as weighted relevance aggregation operator or weighted generalized mean, more with fuzzy rules. This paper presents the suggested Fuzzy inference system-like aggregation operator (FISAO), shows its axiomatic conformity and depicts its use through an experimental example.

Open Access: Yes

DOI: 10.1007/978-3-031-07707-4_12

Tejsavbaktérium-izolátumok egyes probiotikus tulajdonságainak in vitro vizsgálata

Judit Süle Zoltán Hatvan Z. Kerényi László Varga

Publication Name: Elelmiszervizsgalati Kozlemenyek

Publication Date: 2023-01-01

Volume: 69

Issue: 1

Page Range: 4337-4349

Description:

No description provided

Open Access: Yes

DOI: 10.52091/EVIK-2023/1-2-HUN

Investigation of the Effects of Biodegradable and Compostable Polymers as Sources of Microplastics on the Water-Soil Continuum: A Review

Gergely Zoltán Macher Dalma Bódizs Kornélia Horváth Anett Bedő

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 307-312

Description:

The amount of research and publications related to microplastic pollution has been steadily increasing in recent years, but at the same time, our current knowledge on the topic is still based on occasional point measurements. As a result of these point measurements, it becomes obvious that new research areas and disciplines are also connected to the topic of microplastics. Various biotic and abiotic processes can cause microplastics to enter the environment and spread within it. All of these mechanisms can arise from the moisture conditions of the tested medium, temperature differences, or even from the decomposing and transforming activities of microorganisms. The rise of biodegradable and compostable plastic bags can also be considered a source of this kind since polymer products labelled as environmentally friendly can be identified as secondary sources during their decomposition processes. Therefore, both industrial and household compost can contain microscopic polymer residues, the application of which involves a potential risk of environmental pollution. In recent years, several international studies have dealt with various aspects of the degradation of these products, including the use of problems caused by residual microplastics and their environmental effects. The focus of our paper is not on the development of a new scientific methodology but a summary of the current situation formed through research results dealing with the current environmental safety and environmental health risks of microplastic pollution caused by biodegradable polymers.

Open Access: Yes

DOI: 10.3303/CET23107052

Overview of XBRL Taxonomy Usage for Structured Sustainability Reporting in European Filings

Árpád Tóth Alex Suta Péter Molnár Bence Lukács Loránd Kedves Orsolya Pintes

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 577-582

Description:

The increasing requirement for businesses to disclose sustainability information digitally has prompted significant changes in the content and format of Environmental, Social, and Governance (ESG) disclosures. However, companies mandated to adapt to these changes face technological and information challenges regarding ‘what’ and ‘how’ to report. For European filers, the Corporate Sustainability Reporting Directive (CSRD) and its requirements, the European Sustainability Reporting Standards (ESRS), along with the International Financial Reporting Standards (IFRS S1 and S2), propose the use of the eXtensible Business Reporting Language (XBRL) as the anticipated technical solution for the digital data structure. The objective of this paper is to provide a methodological framework for effectively navigating the complex and interrelated concepts relevant to stakeholders. Rather than relying on cumbersome textual guides, this framework leverages an examination of existing taxonomies to offer readers insights into the essential glossary of disclosures and metrics considered crucial by official regulatory sources. Furthermore, the research discusses the emphasis on qualitative and narrative disclosures in ESG reporting and their feasibility of comparable results. Employing this methodology facilitates the implementation of corporate case studies and enables the analysis of mass amounts of future annual reports for comprehensive sustainability performance measurement.

Open Access: Yes

DOI: 10.3303/CET23107097

Learning Stable and Robust Linear Parameter-Varying State-Space Models

R. Toth Ruigang Wang Chris Verhoek

Publication Name: Proceedings of the IEEE Conference on Decision and Control

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: 1348-1353

Description:

This paper presents two direct parameterizations of stable and robust linear parameter-varying state-space (LPV-SS) models. The model parametrizations guarantee a priori that for all parameter values during training, the allowed models are stable in the contraction sense or have their Lipschitz constant bounded by a user-defined value γ. Furthermore, since the parametrizations are direct, the models can be trained using unconstrained optimization. The fact that the trained models are of the LPV-SS class makes them useful for, e.g., further convex analysis or controller design. The effectiveness of the approach is demonstrated on an LPV identification problem.

Open Access: Yes

DOI: 10.1109/CDC49753.2023.10384260

The Effect of the Dam-building Activity of the Eurasian Beaver (Castor fiber) on Changes in the Soil Moisture Conditions and Vegetation Associations of the Beaver Meadows in the Valley of Ablánc-stream

Gergely Zoltán Macher Dalma Bódizs Anett Bedő

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 319-324

Description:

Nowadays, more information is available about the activities of the Eurasian beaver (Castor fiber) as an ecosystem engineer species and the resulting ecosystem services. The environment-shaping activity of beavers not only affects the bed conditions of a given body of water but also affects the degree of diversity of the vegetation and fauna surrounding it. The research published in connection with this topic has only in recent years begun to deal more intensively with the condition characterisation and function analysis of the flooded areas under constant beaver influence, called beaver meadows. The focus of this paper is the investigation of beaver meadows directly connected to the dam system consisting of 19 beaver dams located along the Ablánc stream. The research examines the effect of the activity of the beaver colony, which has been continuously monitored for almost two years, on the soil moisture conditions of the beaver meadows in the Natura 2000 nature conservation area and to what extent this is reflected in the characteristics of the plant community. The focus of the analysis is the vertical distribution of soil moisture in the upper soil layer. During the vegetation mapping, 10 squares were designated to determine plant community parameters. High soil moisture values were detected in the examined quadrates, which varied between 39.0 φ% and a maximum of 50.0 φ%. A significant number of taxa could be identified - such as Myosoton aquaticum and Petasites hybridus - whose primary ecological requirements are a permanent wet environment and continuous water impact.

Open Access: Yes

DOI: 10.3303/CET23107054

SELF-ASSESSMENT OR PEER ASSESSMENT? WHICH IS BETTER PREDICTOR OF TEST RESULTS

Nárcisz Kulcsár

Publication Name: Sefi 2023 51st Annual Conference of the European Society for Engineering Education Engineering Education for Sustainability Proceedings

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: 703-709

Description:

Internationally accredited engineering programmes are becoming increasingly important in the internationalisation agenda of universities. ABET has highlighted transversal skills in its accreditation criteria for engineering degrees. Preferred transferable skills include the ability of students to reflect on their own performance, the ability to give constructive feedback and the ability to make judgements. Students' self- and peer-assessment was examined in the context of a basic mathematics course. During the maths midterm tests, students self-assessed on each task, and assessed another student's test. These assessments were compared with the points given by the teacher. 84% of students overestimated their actual performance and more than 60% of them overestimated their peer's performance, and both overestimations were low. According to students' opinion, peer assessment is as easy as self-assessment, it is not easier for them to spot mistakes in other people's work than in their own. The research results showed significant difference in the accuracy of peer and self-assessment, peer assessment is closer to teacher evaluation than self-assessment. Contrary to our previous research, now we did not find a significant correlation between students' performance and assessment accuracy in the first test. One reason for this may be that these students have failed this subject at least once. As further learning is only possible once we have identified what needs to be learned, the ability to assess the gained knowledge as accurately as possible is appreciating. In addition to meeting accreditation requirements, the different type of assessments' cognitive and affective effects on learning outcomes make it a good choice for classroom use.

Open Access: Yes

DOI: 10.21427/HTNS-KS58