Uncertainty Detection and Reduction in Neural Decoding of EEG Signals

TL;DR

This paper introduces UNCER, a model that estimates and reduces uncertainty in EEG neural decoding, improving reliability in brain-computer interface applications by combining Bayesian methods and data augmentation.

Contribution

It presents a novel uncertainty estimation and reduction framework for EEG decoding that integrates dropout and Bayesian neural networks without altering existing architectures.

Findings

Significant improvement in uncertainty estimation accuracy.

Effective reduction of decoding uncertainty through data augmentation.

Enhanced reliability of EEG decoding in BCI applications.

Abstract

EEG decoding systems based on deep neural networks have been widely used in decision making of brain computer interfaces (BCI). Their predictions, however, can be unreliable given the significant variance and noise in EEG signals. Previous works on EEG analysis mainly focus on the exploration of noise pattern 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 estimation to incorporate both the uncertainty in the input signal and the uncertainty in the model parameters. We further proposed a data augmentation based approach for uncertainty reduction. The model can be integrated into current widely used EEG neural decoders without change of architecture. 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 on the quality of estimated uncertainty and the effectiveness of uncertainty reduction.