@mastersthesis{MTMT:34529745,
	title = {Development of Brain-Computer Interfaces by using Deep Learning Technologies},
	url = {https://m2.mtmt.hu/api/publication/34529745},
	author = {Köllőd, Csaba Márton},
	doi = {10.15774/PPKE.ITK.2024.001},
	publisher = {PPKE},
	unique-id = {34529745},
	year = {2024},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709}
}

@article{MTMT:34141034,
	title = {Closed loop BCI system for Cybathlon 2020},
	url = {https://m2.mtmt.hu/api/publication/34141034},
	author = {Köllőd, Csaba Márton and Adolf, András and Márton, Gergely and Wahdow, Moutz and Fadel, Ward and Ulbert, István},
	doi = {10.1080/2326263X.2023.2254463},
	journal-iso = {BRAIN-COMP INTERF},
	journal = {BRAIN-COMPUTER INTERFACES},
	volume = {10},
	unique-id = {34141034},
	issn = {2326-263X},
	year = {2023},
	eissn = {2326-2621},
	pages = {114-128},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@article{MTMT:34028020,
	title = {Deep Comparisons of Neural Networks from the EEGNet Family},
	url = {https://m2.mtmt.hu/api/publication/34028020},
	author = {Köllőd, Csaba Márton and Adolf, András and Iván, Kristóf and Márton, Gergely and Ulbert, István},
	doi = {10.3390/electronics12122743},
	journal = {ELECTRONICS (SWITZ)},
	volume = {12},
	unique-id = {34028020},
	abstract = {A preponderance of brain–computer interface (BCI) publications proposing artificial neural networks for motor imagery (MI) electroencephalography (EEG) signal classification utilize one of the BCI Competition datasets. However, these databases encompass MI EEG data from a limited number of subjects, typically less than or equal to 10. Furthermore, the algorithms usually include only bandpass filtering as a means of reducing noise and increasing signal quality. In this study, we conducted a comparative analysis of five renowned neural networks (Shallow ConvNet, Deep ConvNet, EEGNet, EEGNet Fusion, and MI-EEGNet) utilizing open-access databases with a larger subject pool in conjunction with the BCI Competition IV 2a dataset to obtain statistically significant results. We employed the FASTER algorithm to eliminate artifacts from the EEG as a signal processing step and explored the potential for transfer learning to enhance classification results on artifact-filtered data. Our objective was to rank the neural networks; hence, in addition to classification accuracy, we introduced two supplementary metrics: accuracy improvement from chance level and the effect of transfer learning. The former is applicable to databases with varying numbers of classes, while the latter can underscore neural networks with robust generalization capabilities. Our metrics indicated that researchers should not disregard Shallow ConvNet and Deep ConvNet as they can outperform later published members of the EEGNet family.},
	year = {2023},
	eissn = {2079-9292},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Iván, Kristóf/0000-0003-3637-3979; Ulbert, István/0000-0001-9941-9159}
}

@article{MTMT:33271235,
	title = {Multi frequency band fusion method for EEG signal classification},
	url = {https://m2.mtmt.hu/api/publication/33271235},
	author = {Wahdow, Moutz and Alnaanah, Mahmoud and Fadel, Ward and Adolf, András and Köllőd, Csaba Márton and Ulbert, István},
	doi = {10.1007/s11760-022-02399-6},
	journal-iso = {SIGNAL IMAGE VIDEO PROCES},
	journal = {SIGNAL IMAGE AND VIDEO PROCESSING},
	volume = {17},
	unique-id = {33271235},
	issn = {1863-1703},
	abstract = {This paper proposes a novel convolutional neural network (CNN) fusion method for electroencephalography (EEG) motor imagery (MI) signal classification. The method is named MFBF, which stands for multifrequency band fusion. The MFBF method relies on filtering the input signal with different frequency bands and feeding each band signal to a duplicate of a CNN model; then, all duplicates are concatenated to form a fusion model. This paper also introduces the second release of Coleeg software, which is used for evaluation. The MFBF method has the advantage of the flexibility of choosing any model and any number of frequency bands. In the experimental evaluation, the CNN1D model and three frequency bands were used to form the CNN1D_MFBF model, and it was evaluated against the EEGNet_fusion model on three different datasets, which are: Physionet, BCI competition IV-2a, and a dataset from the Hungarian Academy of Sciences Research Centre for Natural Sciences (MTA-TTK). The CNN1D_MFBF model had comparable or better accuracy results with less than one-fifth of the training time, which is a significant advantage for the proposed method.},
	year = {2023},
	eissn = {1863-1711},
	pages = {1883-1887},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@inproceedings{MTMT:34030729,
	title = {Classification of Semi-Automated Labeled MindRove Armband Recorded EMG Data},
	url = {https://m2.mtmt.hu/api/publication/34030729},
	author = {Köllőd, Csaba Márton and Eftimiu, Nikomidisz Jorgosz and Márton, Gergely and Ulbert, István},
	booktitle = {IEEE Joint 22nd International Symposium on COMPUTATIONAL INTELLIGENCE and INFORMATICS and 8th International Conference on Recent Achievements in Mechatronics, Automation, Computer Science and Robotics (CINTI-MACRo 2022)},
	doi = {10.1109/CINTI-MACRo57952.2022.10029540},
	unique-id = {34030729},
	year = {2022},
	pages = {000381-000386},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@inproceedings{MTMT:33631899,
	title = {A surface electromyography dataset for hand gesture recognition},
	url = {https://m2.mtmt.hu/api/publication/33631899},
	author = {Nikomidisz, Eftimiu and Köllőd, Csaba Márton and Ulbert, István and Márton, Gergely},
	booktitle = {IEEE 20th Jubilee International Symposium on Intelligent Systems and Informatics (SISY 2022)},
	doi = {10.1109/SISY56759.2022.10036305},
	unique-id = {33631899},
	year = {2022},
	pages = {115-120},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@{MTMT:31400880,
	title = {Chessboard EEG Images Classification for BCI Systems Using Deep Neural Network},
	url = {https://m2.mtmt.hu/api/publication/31400880},
	author = {Fadel, Ward and Wahdow, Moutz and Köllőd, Csaba Márton and Márton, Gergely and Ulbert, István},
	booktitle = {Bio-inspired Information and Communication Technologies},
	doi = {10.1007/978-3-030-57115-3_8},
	unique-id = {31400880},
	year = {2020},
	pages = {97-104},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@CONFERENCE{MTMT:31345209,
	title = {Multiple SVM based Brain Computer Interface for Cybathlon 2020},
	url = {https://m2.mtmt.hu/api/publication/31345209},
	author = {Köllőd, Csaba Márton and Márton, Gergely and Ulbert, István},
	booktitle = {IBRO Workshop},
	unique-id = {31345209},
	year = {2020},
	pages = {https://www.mitt2020.hu/abstracts},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@inproceedings{MTMT:31318596,
	title = {Multi-Class Classification of Motor Imagery EEG Signals Using Image-Based Deep Recurrent Convolutional Neural Network},
	url = {https://m2.mtmt.hu/api/publication/31318596},
	author = {Fadel, Ward and Köllőd, Csaba Márton and Wahdow, Moutz and Ibrahim, Yahya and Ulbert, István},
	booktitle = {2020 8th International Winter Conference on Brain-Computer Interface (BCI)},
	doi = {10.1109/BCI48061.2020.9061622},
	unique-id = {31318596},
	year = {2020},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709; Ulbert, István/0000-0001-9941-9159}
}

@CONFERENCE{MTMT:31318591,
	title = {Developing of Brain-Computer Interfaces by using Deep Learning technologies},
	url = {https://m2.mtmt.hu/api/publication/31318591},
	author = {Köllőd, Csaba Márton},
	booktitle = {PhD PROCEEDINGSANNUAL ISSUES OF THEDOCTORAL SCHOOLFACULTY OF INFORMATION TECHNOLOGY & BIONICS (2019)},
	unique-id = {31318591},
	year = {2019},
	pages = {22},
	orcid-numbers = {Köllőd, Csaba Márton/0000-0003-3817-6709}
}