Találati lista | Tudóstér

001-es BibID:	BIBFORM130759
Első szerző:	Beregi-Kovács Marcell (Alkalmazott matematikus)
Cím:	Generation of Synthetic Non-Homogeneous Fog by Discretized Radiative Transfer Equation / Beregi-Kovács Marcell; Harangi Balázs; Hajdu András; Gát György
Dátum:	2025
Megjegyzések:	The synthesis of realistic fog in images is critical for applications such as autonomous navigation, augmented reality, and visual effects. Traditional methods based on Koschmieder's law or GAN-based image translation typically assume homogeneous fog distributions and rely on oversimplified scattering models, limiting their physical realism. In this paper, we propose a physics-driven approach to fog synthesis by discretizing the Radiative Transfer Equation (RTE). Our method models spatially inhomogeneous fog and anisotropic multi-scattering, enabling the generation of structurally consistent and perceptually plausible fog effects. To evaluate performance, we construct a dataset of real-world foggy, cloudy, and sunny images and compare our results against both Koschmieder-based and GAN-based baselines. Experimental results show that our method achieves a lower Fréchet Inception Distance (?10% vs. Koschmieder, ?42% vs. CycleGAN) and a higher Pearson correlation (+4% and +21% , respectively), highlighting its superiority in both feature space and structural fidelity. These findings highlight the potential of RTE-based fog synthesis for physically consistent image augmentation under challenging visibility conditions. However, the method's practical deployment may be constrained by high memory requirements due to tensor-based computations, which must be addressed for large-scale or real-time applications.
Tárgyszavak:	Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk radiative transfer equation fog synthesis discretization physical modeling image augmentation inhomogeneous media
Megjelenés:	Journal of Imaging. - 11 : 6 (2025), p. 1-22. -
További szerzők:	Harangi Balázs (1986-) (programtervező matematikus) Hajdu András (1973-) (matematikus, informatikus) Gát György (1961-) (matematikus)
Pályázati támogatás:	EFOP-3.6.2-16-2017-00015 EFOP TKP2021-NKTA-34 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM103625
035-os BibID:	(WOS)000618845500006 (Scopus)85092677334
Első szerző:	Beregi-Kovács Marcell (Alkalmazott matematikus)
Cím:	Efficient Learning of Model Weights via Changing Features During Training / Marcell Beregi-Kovács, Ágnes Baran, András Hajdu
Dátum:	2020
Megjegyzések:	In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features to new ones from a large pool. The main benefit is coming from the fact that opposite to the common practice we do not start training a new model from the scratch, but can keep the already learned weights. This procedure allows the scan of a large feature pool which together with keeping the complexity of the model leads to an increase of the model accuracy within the same training time. The efficiency of our approach is demonstrated in several classic machine learning scenarios including linear regression and neural network-based training. As a specific analysis towards signal processing, we have successfully tested our approach on the database MNIST for digit classification considering single pixel and pixel-pairs intensities as possible features.
ISBN:	9781728110592
Tárgyszavak:	Természettudományok Matematika- és számítástudományok előadáskivonat könyvrészlet machine learning updating model weights linear regression neural networks image classification
Megjelenés:	2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES). - p. 43-48. -
További szerzők:	Baran Ágnes (1972-) (matematikus) Hajdu András (1973-) (matematikus, informatikus)
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM096363
035-os BibID:	(WoS)000654007400005 (Scopus)85107404019
Első szerző:	Bogacsovics Gergő (informatikus)
Cím:	Replacing the SIR epidemic model with a neural network and training it further to increase prediction accuracy / Bogacsovics Gergő, Hajdu András, Lakatos Róbert, Beregi-Kovács Marcell, Tiba Attila, Tomán Henrietta
Dátum:	2021
ISSN:	1787-5021 1787-6117
Tárgyszavak:	Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban folyóiratcikk
Megjelenés:	Annales Mathematicae et Informaticae. - 53 (2021), p. 73-91. -
További szerzők:	Hajdu András (1973-) (matematikus, informatikus) Lakatos Róbert (1986-) (informatikus) Beregi-Kovács Marcell (1995-) (Alkalmazott matematikus) Tiba Attila (1990-) (informatikus, matematikus) Tomán Henrietta (1976-) (matematikus, informatikus)
Pályázati támogatás:	EFOP-3.6.2-16-2017-00015 EFOP ÚNKP-20-4-I Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM116613
035-os BibID:	(Scopus)85178934416
Első szerző:	Harangi Balázs (programtervező matematikus)
Cím:	Composing Diverse Ensembles of Convolutional Neural Networks by Penalization / Balazs Harangi, Agnes Baran, Marcell Beregi-Kovacs, Andras Hajdu
Dátum:	2023
ISSN:	2227-7390
Megjegyzések:	Ensemble-based systems are well known to have the capacity to outperform individual approaches if the ensemble members are sufficiently accurate and diverse. This paper investigates how an efficient ensemble of deep convolutional neural networks (CNNs) can be created by forcing them to adjust their parameters during the training process to increase diversity in their decisions. As a new theoretical approach to reach this aim, we join the member neural architectures via a fully connected layer and insert a new correlation penalty term in the loss function to obstruct their similar operation. With this complementary term, we implement the standard guideline of ensemble creation to increase the members` diversity for CNNs in a more detailed and flexible way than similar existing techniques. As for applicability, we show that our approach can be efficiently used in various classification tasks. More specifically, we demonstrate its performance in challenging medical image analysis and natural image classification problems. Besides the theoretical considerations and foundations, our experimental findings suggest that the proposed technique is competitive. Namely, on the one hand, the classification rate of the ensemble trained in this way outperformed all the individual accuracies of the state-of-the-art member CNNs according to the standard error functions of these application domains. On the other hand, it is also validated that the ensemble members get more diverse and their accuracies are raised by adding the penalization term. Moreover, we performed a full comparative analysis, including other state-of-the-art ensemble-based approaches recommended for the same classification tasks. This comparative study also confirmed the superiority of our method, as it overcame the current solutions.
Tárgyszavak:	Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk ensemble-based network penalization loss function image classification diversity
Megjelenés:	Mathematics. - 11 : 23 (2023), p. 1-19. -
További szerzők:	Baran Ágnes (1972-) (matematikus) Beregi-Kovács Marcell (1995-) (Alkalmazott matematikus) Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:	ÚNKP-21-5-DE-485 Egyéb Bolyai János Kutatási Ösztöndíj MTA
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: