Search

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals suffer substantially from motion artifacts even in ambulatory settings. Signal processing techniques for removing motion artifacts from EEG signals have limitations, and the potential of classical or deep machine-learning algorithms for this task remains largely unexplored. We propose Attention-Guided Operational CycleGAN (AGO-CycleGAN), a novel CycleGAN-based framework to remove motion artifacts and enhance the quality of corrupted EEG signals. It incorporates self-generative operational neurons and an attention-guided Feature Pyramid Network with modified bottlenecks as generators and PatchGAN-based discriminators. AGO-CycleGAN was trained and tested on a single-channel EEG dataset from 23 subjects, using a subject-independent Jackknife cross-validation approach. It outperformed other methods and was evaluated through qualitative and quantitative analysis, employing robust metrics in both temporal and frequency domains. The results indicate its effectiveness in restoring EEG signals affected by severe motion artifacts. AGO-CycleGAN achieves state-of-the-art EEG restoration performance in the temporal domain, gaining improvements in signal-to-noise ratio (ΔSNR) and temporal correlation (η temp) by 26.497 dB and 87.2% , respectively. It also showed excellent performance in preserving the spectral EEG components (delta, theta, alpha, beta, and gamma), evaluated through band power ratio before and after restoration. Spectral correlation (η spec) improved by 93.5% after cleaning the motion artifacts. Qualitative evaluations showed excellently reconstructed clean EEG waveforms upon restoration. Spectral restoration visualized through Power Spectral Density (PSD) plots and per-band topographic maps showed a uniform removal of high-power motion artifact components throughout the spectrum. AGO-CycleGAN significantly outperformed existing techniques in EEG artifact removal and can be extended to multi-channel EEG systems. • This study aims to restore EEG signals from motion artifacts using 1D-CycleGAN. • We use Self-Organized Operational Neural Networks to build the proposed Attention-Guided Operational ‎CycleGAN.‎ • The proposed approach outperforms all competing methods in the relevant literature by a significant margin.‎ • The proposed framework can be modified and reused to restore other physiological waveforms.‎ [ABSTRACT FROM AUTHOR]