Dániel Tamás Várkonyi

Dániel Tamás Várkonyi

Auto-generated profile, based on publicly available information

Dániel Tamás Várkonyi

ELTE – Eötvös Loránd University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 September 2022 in Expert Systems with Applications
Verified
Journal Article
Open access
DVDániel Tamás Várkonyi
Dániel Tamás Várkonyi
JSJosé Luis Seixas
José Luis Seixas
THTomáš Horváth
Tomáš Horváth


28 July 2026 in Applied Ontology
Verified
Journal Article
Closed access
PMPaul Kavishe Mushi
Paul Kavishe Mushi
Ismail Seleman MussaIsmail Seleman Mussa
Ismail Seleman Mussa
THTomáš Horváth
Tomáš Horváth
DVDániel T Várkonyi
Dániel T Várkonyi
MAMárta Alexy
Márta Alexy
Precision beekeeping is an emerging domain that utilizes digital technologies and tools, including sensors and artificial intelligence, to enhance the management and sustainability of apiaries. However, the lack of formalized and structured knowledge representation models hinders data integration, interoperability and decision support in the domain. This work presents a precision beekeeping ontology (PBO) designed to represent concepts related to bees, smart devices, monitoring and observation. The ontology was developed by adopting the seven-step methodology using Protégé. Domain understanding and determining the scope of the ontology were based on domain expert knowledge, literature review, standard vocabularies and upper ontologies (DUL, SSN/SOSA, AGROVOC and GEMET). Classes and class hierarchy, object and data properties were carefully defined to capture the concepts and relationships in the domain. Constraints on properties were specified and 74 instances were created based on a Kaggle beehive metrics dataset. 8 competence questions were predefined to determine the scope of knowledge, and later, 6 other related competence questions were defined and successfully executed based on internal hive temperature and hive weight by running SPARQL queries on the Apache Jena-Fuseki server. Domain expert validation and structural evaluation framework were applied and logical consistency was checked by HermiT reasoner in Protégé, using completeness, relevance, accuracy and clarity as evaluation criteria.

13 October 2026 in Applied Ontology
Verified
Journal Article
Closed access
PMPaul Kavishe Mushi
Paul Kavishe Mushi
DVDániel T. Várkonyi
Dániel T. Várkonyi
THTomáš Horváth
Tomáš Horváth
MAMárta Alexy
Márta Alexy
Combined with machine learning techniques, ontologies have recently been applied widely to enhance decision-making, reasoning, knowledge management and representation, and information retrieval in various domains. Likewise, the popularity of ontologies is increasing in the rapidly evolving field of precision agriculture due to the ability to encode general domain knowledge and specialized knowledge of farmers and utilize it within data processing and analytics pipelines. Although the research on ontologies applied to precision agriculture problems is increasing, adopting published solutions is rather cumbersome, mainly due to low reproducibility of these works. This article is intended to survey the current applied research in ontologies within the agricultural domain, by investigating the used methodologies, technologies and evaluation approaches, the availability of the data, ontologies and source codes developed. It was found that the used data sources, the developed ontologies and the developed source codes are available only in 14%, 9% and 7%, respectively, of the selected 85 articles. Additionally, it was found that the applied methodologies, in relation to the issue of reproducibility, the top-down/bottom-up, semi-automatic, seven-step and ontology matching approaches have shown greater potential, while according to the applied technologies, World Wide Web (W3C) have shown greater contribution compared to artificial intelligence (AI).

4 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
WSWadie Skaf
Wadie Skaf
ATArzu Tosayeva
Arzu Tosayeva
DVDániel T. Várkonyi
Dániel T. Várkonyi
Time-Series Forecasting is a powerful data modeling discipline that analyzes historical observations to predict future values of a time-series. It has been utilized in numerous applications, including but not limited to economics, meteorology, and health. In this paper, we use time-series forecasting techniques to model and predict the future incidence of chickenpox. To achieve this, we implement and simulate multiple models and data preprocessing techniques on a Hungary-collected dataset. We demonstrate that the LSTM model outperforms all other models in the vast majority of the experiments in terms of county-level forecasting, whereas the SARIMAX model performs best at the national level. We also demonstrate that the performance of the traditional data preprocessing method is inferior to that of the data preprocessing method that we have proposed.