Making More Sense of Human Intention Detection via Reconstruction Models

Movement intention recognition paves the path to developing Brain-Computer Interface(BCI)applications.Current research mostly focuses on questions like"which hand is intended to move".While answering questions like"whether a hand is intended to move"is more desirable for widely realworld applications,because we cannot continuously perform intention tasks during usage,and the gap periods may cause unintended operation resulting in system failures.However,this kind of intention detection task is more difficult,since for a"whether"problem,it is hard to know what the"not"situation is and consequently to acquire training samples for the"not"situation.Furthermore,the occurrence of genuine intentions is comparatively scarce and unexpected,making the intention detection task hard and computation-consuming.To tackle this problem,we propose a Reconstruction-based Intention Detection(RID)framework,which utilises a reconstruction model to represent a high-level abstraction of EEG signals and leverages the reconstruction errors to determine"whether"there is a movement intention.Our framework is not only theoretically flexible and robust to any sophisticated real-world scenarios but also hand-crafted feature and domain knowledge free.Comprehensive experiments on detecting movement intention tasks with different reconstruction models demonstrate the promising performance of the proposed reconstruction intention detection framework.