Ocular artifacts are a major source of contamination in electroencephalogram (EEG) signals, thereby reducing the quality of information. Artifact removal methods play a vital role in the proper interpretation and analysis of actual brain information. This paper emphasizes the importance of identifying artifacts before their removal to preserve neural information by proposing two advanced source decomposition-based models, namely empirical mode decomposition (EMD) and empirical wavelet transform (EWT). In this study, both EWT and EMD were utilized for artifact identification and to estimate the reference artifact signals. Identified artifacts were removed using a normalized least mean square (NLMS) based adaptive filtering (AF) technique. To test and compare the efficacy of the developed models, an open source EEGdenoiseNet dataset was utilized in this study. The results obtained suggest that the empirical wavelet transform and adaptive filter-based model performed better, with an average improvement in signal-to-noise ratio (SNR) of 9.21 dB and an average correlation coefficient (CC) value of 0.836734. The proposed models were further validated on real EEG data from the BCI Competition 2008 Graz dataset A, where EWT-AF achieved higher SNR compared to EMD-AF. The proposed work also aligns with Sustainable Development Goal (SDG) 3.

Artifacts remain a major challenge in electroencephalogram (EEG) recordings, often degrading the accuracy of clinical diagnosis, brain computer interface (BCI) systems, and cognitive research. Although recent deep learning approaches have advanced EEG denoising, most still struggle to model long-range dependencies, maintain computational efficiency, and generalize to unseen artifact types. To address these challenges, this study proposes MDSC-VA, an efficient denoising framework that integrates multi-scale (M) depth-wise separable convolution (DSConv), variational autoencoder-based (VAE) latent encoding, and a multi-head self-attention mechanism. This unified architecture effectively balances denoising accuracy and model complexity while enhancing generalization to unseen artifact types. Comprehensive evaluations on three open-source EEG datasets, including EEGdenoiseNet, a Motion Artifact Contaminated Multichannel EEG dataset, and the PhysioNet EEG Motor Movement/Imagery dataset, demonstrate that MDSC-VA consistently outperforms state-of-the-art methods, achieving a higher signal-to-noise ratio (SNR), lower relative root mean square error (RRMSE), and stronger correlation coefficient (CC) values. Moreover, the model preserved over 99% of the dominant neural frequency band power, validating its ability to retain physiologically relevant rhythms. These results highlight the potential of MDSC-VA for reliable clinical EEG interpretation, real-time BCI systems, and advancement towards sustainable healthcare technologies in line with SDG-3 (Good Health and Well-Being).

1. An electroencephalogram (EEG) can be used to study the human brain and provide valuable information applicable across various fields. Scientific and medical research, brain-computer interfaces (...