UNCER: A framework for uncertainty estimation and reduction in neural decoding of EEG signals

EEG decoding systems based on deep neural networks have been widely used in the decision-making of brain-computer interfaces (BCI). Their predictions, however, can be unreliable given the significant vari-ance and noise in EEG signals. Previous works on EEG analysis mainly focus on the exploration of noise patterns in the source signal, while the uncertainty during the decoding process is largely unexplored. Automatically detecting and reducing such decoding uncertainty is important for BCI motor imagery applications such as robotic arm control etc. In this work, we proposed an uncertainty estimation and reduction model (UNCER) to quantify and mitigate the uncertainty during the EEG decoding process. It utilized a combination of dropout oriented method and Bayesian neural network for uncertainty estima-tion to incorporate both the uncertainty in the input signal and the uncertainty in the model parameters. We further proposed an adaptive data augmentation-based approach for uncertainty reduction. The model can be integrated into the current widely used EEG neural decoders without change of the archi-tecture. We performed extensive experiments for uncertainty estimation and its reduction in both intra-subject EEG decoding and cross-subject EEG decoding on two public motor imagery datasets, where the proposed model achieves significant improvement both in the quality of estimated uncertainty and the effectiveness of uncertainty reduction.(c) 2023 Elsevier B.V. All rights reserved.

Automated summary

EEG decoding systems based on deep neural networks are widely used in brain-computer interfaces for decision-making. However, the reliability of their predictions is affected by the variance and noise in EEG signals. Previous studies have focused on noise patterns in the source signal, neglecting the uncertainty during the decoding process. This work proposes an uncertainty estimation and reduction model (UNCER) that incorporates dropout and Bayesian neural network methods to quantify and mitigate decoding uncertainty. The model achieves significant improvement in uncertainty estimation and reduction in motor imagery applications.