Key result
A proposed method using Empirical Mode Decomposition and a stacked BiLSTM network achieved an accuracy of 82.26% in decoding finger imagined movements of the right hand from MI-EEG signals.
Why the study?
Small and noisy MI-EEG signals from hand-finger imagined movements are less frequently used in BCI systems because they are difficult to classify.
A novel framework using EMD and stacked BiLSTM successfully decodes noisy MI-EEG signals for imagined finger movements with 82.26% accuracy.
Answers are grounded in this paper and cite their sources.
May aid BCI decoding of subtle finger MI-EEG; leaves open validation in prospective trials.
Motor Imagery Electroencephalogram (MI-EEG) signals are widely used in Brain-Computer Interfaces (BCI). MI-EEG signals of large limbs movements have been explored in recent researches because they deliver relevant classification rates for BCI systems. However, smaller and noisy signals corresponding to hand-finger imagined movements are less frequently used because they are difficult to classify. This study proposes a method for decoding finger imagined movements of the right hand. For this purpose, MI-EEG signals from C3, Cz, P3, and Pz sensors were carefully selected to be processed in the proposed framework. Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals. At the same time, the sequence classification is performed by a stacked Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed method was evaluated using k-fold cross-validation on a public dataset, obtaining an accuracy of 82.26%.
No takes yet. Share an insight, caveat, or question.
Mwata-Velu et al. (2021) studied Motor Imagery Electroencephalogram (MI-EEG) decoding. Empirical Mode Decomposition (EMD) and stacked BiLSTM network was evaluated on Classification accuracy of decoding finger imagined movements. A proposed method using Empirical Mode Decomposition and a stacked BiLSTM network achieved an accuracy of 82.26% in decoding finger imagined movements of the right hand from MI-EEG signals.
Synapse has enriched 10 related papers. Consider them for comparative context: