Motion Artifact Removal from EEG Signals Using the Motion-Net Deep Learning Algorithm

Electroencephalography (EEG) is vital in brain signal analysis, with mobile EEG (mo-EEG) extending its utility to movement scenarios. However, mo-EEG is highly susceptible to motion artifacts, degrading signal quality. This study introduces Motion-Net, a subject-specific CNN-based framework for removing motion artifacts from EEG signals. Unlike prior generalized or simulated approaches, Motion-Net is trained and tested separately per subject using real EEG recordings with ground-truth references. The model incorporates visibility graph (VG) features, providing structural information that improves performance with smaller datasets. Across three experimental setups, Motion-Net achieved an average motion artifact reduction percentage ( η ) of 86% ±4.13, a SNR improvement of 20 ±4.47 dB, and a Mean Absolute Error (MAE) of 0.20 ±0.16. These results show that VG features enhance model learning and stability, and establish Motion-Net as the first subject-specific deep learning framework for robust motion artifact removal in mobile EEG. • Development of Motion-Net, a CNN-based deep learning model for subject-specific motion artifact removal from EEG signals. • First study to apply visibility graph (VG) features for EEG motion artifact removal, enhancing model accuracy on smaller datasets. • Evaluation of Motion-Net on a dataset with real-world motion artifacts, demonstrating an artifact reduction percentage ( η ) of 86% ±4.13 and an SNR improvement of 20 ±4.47 dB. • Motion-Net’s performance validated across three experimental setups, showing that separate encoding of VG features improves artifact removal consistency and signal integrity. • Potential application of Motion-Net in mobile EEG setups for improved data quality in naturalistic settings.