Key result
A multimodal stacked autoencoder approach exploiting inter-modality correlation achieved a classification accuracy of 78.1% for dominance, outperforming single-modality approaches.
A deep autoencoder architecture for joint EEG-EMG data compression and classification reduces signal distortion and improves classification accuracy.
Answers are grounded in this paper and cite their sources.
Demonstrates early feasibility for improving joint EEG-EMG signal processing; leaves open whether.
In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.
No takes yet. Share an insight, caveat, or question.
Said et al. (2017) studied Emotion analysis using physiological signals (n=32). Multimodal stacked autoencoder vs. Unimodal approaches, Discrete Wavelet Transform, Compressed Sensing was evaluated on Classification accuracy for dominance. A multimodal stacked autoencoder approach exploiting inter-modality correlation achieved a classification accuracy of 78.1% for dominance, outperforming single-modality approaches.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: