TY  - CHAP
AU  - Szécsényi, Nándor
ED  - Dunaev, Dmitriy
ED  - Vajk, István
TI  - Reinforcement Learning based Control of Electrical Drives
T2  - Proceedings of the Automation and Applied Computer Science Workshop 2024 : AACS'24
PB  - Budapesti Műszaki Egyetem (BME)
CY  - Budapest
SN  - 9789634219606
PY  - 2024
SP  - 1
PG  - 12
UR  - https://m2.mtmt.hu/api/publication/34994521
ID  - 34994521
LA  - English
DB  - MTMT
ER  - 

TY  - CHAP
AU  - Szécsényi, Nándor
AU  - Stumpf, Péter Pál
ED  - Donsión, Manuel Pérez
TI  - Useability Evaluation of Reinforcement Learning Toolboxes for Electrical Drives
T2  - 22nd International Conference on Renewable Energies and Power Quality (ICREPQ’24)
PB  - European Association for the Development of Renewable Energies, Environment and Power Quality (EA4EPQ)
CY  - Vigo
SN  - 9788409606566
PY  - 2024
PG  - 6
UR  - https://m2.mtmt.hu/api/publication/34900557
ID  - 34900557
N1  - Eredeti megjelenés: https://doi.org/10.52152/3916 [34871088]
LA  - English
DB  - MTMT
ER  - 

TY  - JOUR
AU  - Szécsényi, Nándor
AU  - Stumpf, Péter Pál
TI  - Useability Evaluation of Reinforcement Learning Toolboxes for Electrical Drives
JF  - RENEWABLE ENERGY & POWER QUALITY JOURNAL
J2  - RENEWABLE ENERGY & POWER QUALITY J
VL  - 22
PY  - 2024
IS  - 1
SP  - 89
EP  - 94
PG  - 6
SN  - 2172-038X
DO  - 10.52152/3916
UR  - https://m2.mtmt.hu/api/publication/34871088
ID  - 34871088
N1  - További megjelenés: https://www.icrepq.com/icrepq24/256-24-szecsenyi.pdf [34900557]
LA  - English
DB  - MTMT
ER  - 

TY  - CHAP
AU  - Szécsényi, Nándor
ED  - Vajk, István
ED  - Dunaev, Dmitriy
TI  - Efficient Annotation Methods for Industrial Datasets using Artificial Intelligence
T2  - Proceedings of the Automation and Applied Computer Science Workshop 2023 (AACS'23)
PB  - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék
CY  - Budapest
SN  - 9789634219262
PY  - 2023
SP  - 64
EP  - 75
PG  - 12
UR  - https://m2.mtmt.hu/api/publication/34608877
ID  - 34608877
AB  - Due to the rapid development and growth of Artificial Intelligence in recent times, it is also being used more and more frequently in industrial environments, however there are many problems besides its advantages. One of them is the difficult process of Dataset construction which often involves manual sample annotation. This task is often performed by human labor at larger companies with relative ease, smaller projects or developments however usually lack the necessary resources to do so, thus making it seem advantageous to use Artificial Intelligence, more precisely Deep Learning, for this problem too. Another issue is the asymmetry of these Datasets, as with production lines, the chance of failure is kept very low, resulting in only a few error samples. To overcome these issues and further democratize AI, in this paper, we present 2 latent space-based sampling methods, which based on the acquired results can achieve reasonably good classification performance with only annotating a few 100s of samples. Moreover, to aid in the understanding of the results, the presented techniques are compared to a naive method representing the baseline approach.
LA  - English
DB  - MTMT
ER  -