A Novel RL-assisted Deep Learning Framework for Task-informative Signals Selection and Classification for Spontaneous BCIs
This work addresses the challenge of improving intention identification in spontaneous BCIs for users, though it appears incremental as it builds upon existing deep-learning methods.
The paper tackles the problem of selecting task-relevant EEG signal segments for brain-computer interfaces by formulating it as a Markov decision process and proposing a reinforcement-learning mechanism combined with deep learning. The result is statistically significant performance improvements in motor imagery classification, as validated on a public dataset.
In this work, we formulate the problem of estimating and selecting task-relevant temporal signal segments from a single EEG trial in the form of a Markov decision process and propose a novel reinforcement-learning mechanism that can be combined with the existing deep-learning based BCI methods. To be specific, we devise an actor-critic network such that an agent can determine which timepoints need to be used (informative) or discarded (uninformative) in composing the intention-related features in a given trial, and thus enhancing the intention identification performance. To validate the effectiveness of our proposed method, we conducted experiments with a publicly available big MI dataset and applied our novel mechanism to various recent deep-learning architectures designed for MI classification. Based on the exhaustive experiments, we observed that our proposed method helped achieve statistically significant improvements in performance.