@inproceedings{MTMT:33191477,
	title = {Knowledge Enriched Schema Matching Framework for Heterogeneous Data Integration},
	url = {https://m2.mtmt.hu/api/publication/33191477},
	author = {Ma, Chuangtao and Molnár, Bálint and Tarcsi, Ádám and Benczúr, András, id},
	booktitle = {2022 IEEE 2nd Conference on Information Technology and Data Science (CITDS)},
	doi = {10.1109/CITDS54976.2022.9914350},
	unique-id = {33191477},
	year = {2022},
	pages = {183-188},
	orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883}
}

@inproceedings{MTMT:31894102,
	title = {Comparison of two technologies for digital payments: challenges and future directions},
	url = {https://m2.mtmt.hu/api/publication/31894102},
	author = {Galena, Pisoni and Molnár, Bálint and Tarcsi, Ádám},
	booktitle = {Online Engineering and Society 4.0},
	doi = {10.1007/978-3-030-82529-4_46},
	unique-id = {31894102},
	abstract = {Digital payments are dramatically increasing around the world.
		Global non-cash payments has observed an increased by 60% since 2015.
		This rapid growth has been a results of technological innovation and increased
		presence of regulation. Digital payments oer exciting opportunities
		and many banks and other nancial institutions have been innovating
		in the domain. Established nancial institutions, also also non-nancial
		institution such as start ups or technology companies, are contributing
		signicantly to nancial technology innovation in the payments market.
		This article provides a comparison of two technological innovations and
		challenges, provides the basis for a conceptual framework on how to compare
		innovative digital payments solutions, such as future directions in
		the evolving payments landscape.},
	year = {2022},
	pages = {478-484},
	orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883}
}

@article{MTMT:32635463,
	title = {Adatelemzési folyamat és keretrendszer a közigazgatás számára},
	url = {https://m2.mtmt.hu/api/publication/32635463},
	author = {Bogacsovics, Gergő and Hajdu, András and Harangi, Balázs and Lakatos, István and Lakatos, Róbert and Szabó, Marianna and Tiba, Attila and Tóth, János and Tarcsi, Ádám},
	doi = {10.54200/kt.v1i2.24},
	journal-iso = {KÖZIGAZGATÁSTUD},
	journal = {KÖZIGAZGATÁSTUDOMÁNY},
	volume = {1},
	unique-id = {32635463},
	abstract = {A mesterséges intelligencia utóbbi évtizedben bekövetkezett ugrásszerű fejlődése az azt támogató hardveres és szoftveres platformok folyamatos bővülésével az adatelemzést is új szintre emelte. Ez a szintlépés alapvetően úgy értelmezhető leginkább, hogy egyre kevésbé szükséges a feldolgozó modellek precíz meghatározása, mivel már a most rendelkezésre álló eszközök képesek biztosítani, hogy pusztán a nyers input adatok megfelelő szolgáltatásával és az elérni kívánt cél meghatározásával az effektív elemzést végző eljárás – általában neurális háló architektúra – már egy gépi tanulási folyamaton keresztül automatikusan kerüljön kialakításra. Mivel ez a trend a jövőben várhatóan tovább fog erősödni, az elemzési eljárásokat célszerű úgy felépíteni, hogy ebbe a keretrendszerbe illeszkedjenek. Ennek megfelelően hangsúlyt kell fektetni a feldolgozni kívánt, potenciálisan különféle területekről származó adatbázisok olyan előfeldolgozására, amelyet követően a teljes adatkészlet átadható az elemző architektúrának. Mivel az elemzés eredményének értelmezhetőségét emberi felhasználásra is alkalmassá kell tenni, ezért tipikusan vizualizációs technikákat alkalmazhatunk erre a célra. Értelemszerűen a vizualizációs technikát is a hatékonyság miatt a teljes elemzési keretrendszerbe érdemes integrálni, azaz a vizualizációs eszköz közvetlenül ráépül az elemzőarchitektúra kimenetére, illetve annak belső adatábrázolására, amennyiben például a bemeneti adatok közötti összefüggések bemutatása is hasznos a döntéshozás indoklásához.},
	keywords = {Adatelemzés; keretrendszer; adatelemzési terv},
	year = {2021},
	eissn = {2786-1910},
	pages = {146-158},
	orcid-numbers = {Harangi, Balázs/0000-0003-4405-2040}
}

@article{MTMT:32239388,
	title = {Data Science for Finance. Best-Suited Methods and Enterprise Architectures},
	url = {https://m2.mtmt.hu/api/publication/32239388},
	author = {Pisoni, Galena and Molnár, Bálint and Tarcsi, Ádám},
	doi = {10.3390/asi4030069},
	journal-iso = {APPL SYST INNOV},
	journal = {APPLIED SYSTEM INNOVATION},
	volume = {4},
	unique-id = {32239388},
	year = {2021},
	eissn = {2571-5577},
	orcid-numbers = {Pisoni, Galena/0000-0002-3266-1773; Molnár, Bálint/0000-0001-5015-8883}
}

@inproceedings{MTMT:32129517,
	title = {EVALUATION OF NEURAL NETWORK COMPRESSION METHODS ON THE RESPIRATORY SOUND DATASET},
	url = {https://m2.mtmt.hu/api/publication/32129517},
	author = {Pál, Tamás and Molnár, Bálint and Tarcsi, Ádám and László, Martin Csongor},
	booktitle = {E-HEALTH 2021},
	unique-id = {32129517},
	year = {2021},
	pages = {118-128},
	orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883}
}

@misc{MTMT:33204654,
	title = {Méhészet és digitalizáció},
	url = {https://m2.mtmt.hu/api/publication/33204654},
	author = {Angyalné Alexy, Márta and Tarcsi, Ádám},
	unique-id = {33204654},
	year = {2020}
}

@inproceedings{MTMT:31834827,
	title = {ACQUIRING BREATHING MOVEMENT AND HEART RATE FROM INERTIAL MEASUREMENT UNITS},
	url = {https://m2.mtmt.hu/api/publication/31834827},
	author = {Martin, Csongor László and Tarcsi, Ádám and Istenes, Zoltán},
	booktitle = {Proceedings of International Conference e-Health 2020},
	unique-id = {31834827},
	year = {2020},
	pages = {227-229}
}

@techreport{MTMT:31830781,
	title = {Knowledge-enriched Schema Mapping: A Preliminary Case Study of e-MedSolution System},
	url = {https://m2.mtmt.hu/api/publication/31830781},
	author = {Ma, Chuangtao},
	editor = {Molnár, Bálint and Tarcsi, Ádám},
	unique-id = {31830781},
	year = {2020},
	orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883; Ma, Chuangtao/0000-0002-6492-2579}
}

@CONFERENCE{MTMT:31814811,
	title = {Lightweight, Length Invariant Models and Dimensionality Reduction in Respiratory Disease Detection},
	url = {https://m2.mtmt.hu/api/publication/31814811},
	author = {Pál, Tamás and Molnár, Bálint and Tarcsi, Ádám},
	booktitle = {Collection of Abstracts},
	unique-id = {31814811},
	abstract = {The detection of respiratory diseases has been an important field of study of respiratory illnesses that are responsible for millions of deaths yearly. Machine learning offers a plethora of methods to preprocess, analyze, and classify such recordings. Approaches that have reduced computational demand are preferred to achieve shorter processing time. Two deep learning models are proposed that are length-invariant and have simpler neural network topologies. With length invariance, the processing time is shortened, as splitting the recordings into equal-sized segments is not necessary anymore. Moreover, extracted spectrograms of the recordings can be reduced in dimensionality by calculating aggregated values along the time axis and using efficient methods like PCA or tSNE. Mel Frequency Cepstral Coefficient (MFCC) spectrograms were extracted. The first deep model is a lightweight dense network that receives as input feature vectors from aggregated spectrograms. Inputs of different dimensionality are compared. The second model is inspired by the 1D MaxPooling architecture by Phan that introduce through the use of global max-pooling layers length invariability into the model. An extra hidden layer and other minor modifications are added that increased the classification performance in the case of this dataset. 2D spectrograms are used as input for this model. The respiratory sound database contains 920 annotated breathing recordings so that this database includes the symptoms of 7 classes of diseases or records that constitute as healthy. The data-set was created by a Portuguese and Greek research group. The data were collected from 126 patients so that these samples extend over through all age groups, namely children, adults, elderly. The data-set is also heavily imbalanced. The proposed deep learning, neural networks are systemically investigated on the before-mentioned data-sets and analysed according to the metrics of the discipline.},
	year = {2020},
	pages = {133-133},
	orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883}
}

@inproceedings{MTMT:31661929,
	title = {Curriculum guidelines for new Fintech Master’s Programmes},
	url = {https://m2.mtmt.hu/api/publication/31661929},
	author = {Molnár, Bálint and Tarcsi, Ádám and Françoise, Baude and Galena, Pisoni and Chan, Nam Ngo and Fabio, Massacci},
	booktitle = {ICETA 2020 18th IEEE International Conference on Emerging eLearning Technologies and Applications PROCEEDINGS},
	unique-id = {31661929},
	abstract = {The advancements within the field of computer
		science in the last years has been enormous. AI cloud services,
		crypto currencies, 5G, autonomous vehicles, smart homes,
		quantum computing, affective computing. The traditional organizational
		model for preparing computer science educators
		should be also following this fast pace and study programs
		should be aligned with recent developments and the latest
		trends in industry. The aim of this article is to present to
		future educational designers examples of one new program
		in the domain of Fintech, and how 3 technical Universities in
		Europe prepared their Fintech Masters degrees.We give further
		suggestions and guidelines for universities how to develop such
		programs.},
	year = {2020},
	pages = {470-474},
	orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883}
}