Четкин Егор
Младший научный сотрудник
Публикации с аффилиацией МЭГ-центра
2024
2.
Chetkin, Egor I.; Kozyrsky, Bogdan L.; Shishkin, Sergei L. (2024). Unconditional EEG Synthesis Based on Diffusion Models for Sound Generation. 2024 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON). Novosibirsk State University, 30 Sep – 2 Oct, 2024. 416-420. https://doi.org/10.1109/sibircon63777.2024.10758527
@conference{Chetkin2024,
title = {Unconditional EEG Synthesis Based on Diffusion Models for Sound Generation},
author = {Egor I. Chetkin and Bogdan L. Kozyrsky and Sergei L. Shishkin},
doi = {10.1109/sibircon63777.2024.10758527},
year = {2024},
date = {2024-09-30},
urldate = {2024-09-30},
booktitle = {2024 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)},
pages = {416-420},
address = {Novosibirsk State University, 30 Sep – 2 Oct, 2024},
abstract = {Classifiers used in brain-computer interfaces based on the electroencephalography (EEG) typically demonstrate rel-atively low performance, which is a serios obstacle for making them a practical technology. One of the most important limitations that prevents improving EEG classification is the scarcity of the EEG data. Thus, generation of synthetic data could help to enhance classification. Recently, diffusion models were applied time for time series generation and first steps were made in generating synthetic EEG data using them. Here, we introduce MultiChan Wavegrad, a novel diffusion model designed specifically for multichannel EEG data generation. We describe its architecture and preliminary results of its testing using the BCI competition IV 2a dataset with the EEG recorded during motor imagery. The data generated by MultiChanWaveGrad possessed some resemblance to the real EEG data, although did not reproduce the EEG characteristics well enough. Finally, we discuss possible future directions for improving its performance and possibly making it a useful tool for data augmentation, especially for improving training of BCI classifiers.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Classifiers used in brain-computer interfaces based on the electroencephalography (EEG) typically demonstrate rel-atively low performance, which is a serios obstacle for making them a practical technology. One of the most important limitations that prevents improving EEG classification is the scarcity of the EEG data. Thus, generation of synthetic data could help to enhance classification. Recently, diffusion models were applied time for time series generation and first steps were made in generating synthetic EEG data using them. Here, we introduce MultiChan Wavegrad, a novel diffusion model designed specifically for multichannel EEG data generation. We describe its architecture and preliminary results of its testing using the BCI competition IV 2a dataset with the EEG recorded during motor imagery. The data generated by MultiChanWaveGrad possessed some resemblance to the real EEG data, although did not reproduce the EEG characteristics well enough. Finally, we discuss possible future directions for improving its performance and possibly making it a useful tool for data augmentation, especially for improving training of BCI classifiers.
2023
1.
Chetkin, Egor I.; Shishkin, Sergei L.; Kozyrskiy, Bogdan L. (2023). Bayesian Opportunities for Brain–Computer Interfaces: Enhancement of the Existing Classification Algorithms and Out-of-Domain Detection. Algorithms, 16(9), 429. https://doi.org/10.3390/a16090429
@article{Chetkin2023,
title = {Bayesian Opportunities for Brain–Computer Interfaces: Enhancement of the Existing Classification Algorithms and Out-of-Domain Detection},
author = {Egor I. Chetkin and Sergei L. Shishkin and Bogdan L. Kozyrskiy},
url = {https://megmoscow.ru/wp-content/uploads/pubs/10.3390_a16090429.pdf},
doi = {10.3390/a16090429},
issn = {1999-4893},
year = {2023},
date = {2023-09-08},
urldate = {2023-09-08},
journal = {Algorithms},
volume = {16},
number = {9},
pages = {429},
publisher = {MDPI AG},
abstract = {Bayesian neural networks (BNNs) are effective tools for a variety of tasks that allow for the estimation of the uncertainty of the model. As BNNs use prior constraints on parameters, they are better regularized and less prone to overfitting, which is a serious issue for brain–computer interfaces (BCIs), where typically only small training datasets are available. Here, we tested, on the BCI Competition IV 2a motor imagery dataset, if the performance of the widely used, effective neural network classifiers EEGNet and Shallow ConvNet can be improved by turning them into BNNs. Accuracy indeed was higher, at least for a BNN based on Shallow ConvNet with two of three tested prior distributions. We also assessed if BNN-based uncertainty estimation could be used as a tool for out-of-domain (OOD) data detection. The OOD detection worked well only in certain participants; however, we expect that further development of the method may make it work sufficiently well for practical applications.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Bayesian neural networks (BNNs) are effective tools for a variety of tasks that allow for the estimation of the uncertainty of the model. As BNNs use prior constraints on parameters, they are better regularized and less prone to overfitting, which is a serious issue for brain–computer interfaces (BCIs), where typically only small training datasets are available. Here, we tested, on the BCI Competition IV 2a motor imagery dataset, if the performance of the widely used, effective neural network classifiers EEGNet and Shallow ConvNet can be improved by turning them into BNNs. Accuracy indeed was higher, at least for a BNN based on Shallow ConvNet with two of three tested prior distributions. We also assessed if BNN-based uncertainty estimation could be used as a tool for out-of-domain (OOD) data detection. The OOD detection worked well only in certain participants; however, we expect that further development of the method may make it work sufficiently well for practical applications.