TY - JOUR AU - Adolf, András AU - Köllőd, Csaba Márton AU - Márton, Gergely AU - Fadel, Ward AU - Ulbert, István TI - The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems JF - BRAIN SCIENCES J2 - BRAIN SCI VL - 14 PY - 2024 IS - 12 PG - 20 SN - 2076-3425 DO - 10.3390/brainsci14121272 UR - https://m2.mtmt.hu/api/publication/35653252 ID - 35653252 AB - Background/Objectives: Accurately classifying Electroencephalography (EEG) signals is essential for the effective operation of Brain-Computer Interfaces (BCI), which is needed for reliable neurorehabilitation applications. However, many factors in the processing pipeline can influence classification performance. The objective of this study is to assess the effects of different processing steps on classification accuracy in EEG-based BCI systems. Methods: This study explores the impact of various processing techniques and stages, including the FASTER algorithm for artifact rejection (AR), frequency filtering, transfer learning, and cropped training. The Physionet dataset, consisting of four motor imagery classes, was used as input due to its relatively large number of subjects. The raw EEG was tested with EEGNet and Shallow ConvNet. To examine the impact of adding a spatial dimension to the input data, we also used the Multi-branch Conv3D Net and developed two new models, Conv2D Net and Conv3D Net. Results: Our analysis showed that classification accuracy can be affected by many factors at every stage. Applying the AR method, for instance, can either enhance or degrade classification performance, depending on the subject and the specific network architecture. Transfer learning was effective in improving the performance of all networks for both raw and artifact-rejected data. However, the improvement in classification accuracy for artifact-rejected data was less pronounced compared to unfiltered data, resulting in reduced precision. For instance, the best classifier achieved 46.1% accuracy on unfiltered data, which increased to 63.5% with transfer learning. In the filtered case, accuracy rose from 45.5% to only 55.9% when transfer learning was applied. An unexpected outcome regarding frequency filtering was observed: networks demonstrated better classification performance when focusing on lower-frequency components. Higher frequency ranges were more discriminative for EEGNet and Shallow ConvNet, but only when cropped training was applied. Conclusions: The findings of this study highlight the complex interaction between processing techniques and neural network performance, emphasizing the necessity for customized processing approaches tailored to specific subjects and network architectures. LA - English DB - MTMT ER - TY - JOUR AU - Wahdow, Moutz AU - Alnaanah, Mahmoud AU - Fadel, Ward AU - Adolf, András AU - Köllőd, Csaba Márton AU - Ulbert, István TI - Multi frequency band fusion method for EEG signal classification JF - SIGNAL IMAGE AND VIDEO PROCESSING J2 - SIGNAL IMAGE VIDEO PROCES VL - 17 PY - 2023 IS - 5 SP - 1883 EP - 1887 PG - 5 SN - 1863-1703 DO - 10.1007/s11760-022-02399-6 UR - https://m2.mtmt.hu/api/publication/33271235 ID - 33271235 AB - 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. LA - English DB - MTMT ER - TY - JOUR AU - Köllőd, Csaba Márton AU - Adolf, András AU - Márton, Gergely AU - Wahdow, Moutz AU - Fadel, Ward AU - Ulbert, István TI - Closed loop BCI system for Cybathlon 2020 JF - BRAIN-COMPUTER INTERFACES J2 - BRAIN-COMP INTERF VL - 10 PY - 2023 IS - 2-4 SP - 114 EP - 128 PG - 15 SN - 2326-263X DO - 10.1080/2326263X.2023.2254463 UR - https://m2.mtmt.hu/api/publication/34141034 ID - 34141034 N1 - Roska Tamás Doctoral School of Sciences and Technology, Budapest, Hungary Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Budapest, Hungary Export Date: 4 June 2024 Correspondence Address: Köllőd, C.; Faculty of Information Technology and Bionics, Hungary; email: kollod.csaba@itk.ppke.hu LA - English DB - MTMT ER - TY - CHAP AU - Fadel, Ward AU - Köllőd, Csaba Márton AU - Wahdow, Moutz AU - Ibrahim, Yahya AU - Ulbert, István ED - Institute of Electrical and Electronics Engineers Incorporated, (IEEE) TI - Multi-Class Classification of Motor Imagery EEG Signals Using Image-Based Deep Recurrent Convolutional Neural Network T2 - 2020 8th International Winter Conference on Brain-Computer Interface (BCI) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9781728147062 PY - 2020 PG - 4 DO - 10.1109/BCI48061.2020.9061622 UR - https://m2.mtmt.hu/api/publication/31318596 ID - 31318596 LA - English DB - MTMT ER - TY - CHAP AU - Fadel, Ward AU - Wahdow, Moutz AU - Köllőd, Csaba Márton AU - Márton, Gergely AU - Ulbert, István ED - Guo, Weisi ED - Mahfuz, Mohammad Upal ED - Lin, Lin ED - Nakano, Tadashi ED - Chen, Yifan TI - Chessboard EEG Images Classification for BCI Systems Using Deep Neural Network T2 - Bio-inspired Information and Communication Technologies: 12th EAI International Conference, BICT 2020 PB - Springer International Publishing CY - Cham SN - 9783030571146 T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, ISSN 1867-8211 ; 329. PY - 2020 SP - 97 EP - 104 PG - 8 DO - 10.1007/978-3-030-57115-3_8 UR - https://m2.mtmt.hu/api/publication/31400880 ID - 31400880 LA - English DB - MTMT ER -