Abstract

Motor imagery (MI) based brain-computer interface (BCI) is a research hotspot and has attracted lots of attention. Within this research topic, multiple MI classification is a challenge due to the difficulties caused by time-varying spatial features across different individuals. To deal with this challenge, we tried to fuse brain functional connectivity (BFC) and one-versus-the-rest filter-bank common spatial pattern (OVR-FBCSP) to improve the robustness of classification. The BFC features were extracted by phase locking value (PLV), representing the brain inter-regional interactions relevant to the MI, whilst the OVR-FBCSP is used to extract the spatial-frequency features related to the MI. These diverse features were then fed into a multi-kernel relevance vector machine (MK-RVM). The dataset with three motor imagery tasks (left hand MI, right hand MI, and feet MI) was used to assess the proposed method. Experimental results not only showed that the cascade structure of diverse feature fusion and MK-RVM achieved satisfactory classification performance (average accuracy: 83.81%, average kappa: 0.76), but also demonstrated that BFC plays a supplementary role in the MI classification. Moreover, the proposed method has a potential to be integrated into multiple MI online detection owing to the advantage of strong time-efficiency of RVM.

Highlights

  • Motor imagery (MI) is the imagination of actions and is associated with a specific activation in the brain

  • We propose a cascade structure of oneversus-the-rest filter-bank common spatial pattern (OVRFBCSP) method and multi-kernel relevance vector machine (MK-RVM) for the classification of three imagery movements

  • The results demonstrated that the combination of FBCSP and phase locking value (PLV) can extract discriminative features of both spatial-frequency and brain inter-regional interactions relevant to MI tasks

Read more

Summary

Introduction

Motor imagery (MI) is the imagination of actions and is associated with a specific activation in the brain. MI has been widely used in sport training, neurological rehabilitation, and brain-computer interface (BCI). The EEG-based MI BCI can enable a user to control a system based on the user’s imagery movements of limbs [1]. The MI BCI can be used in the stroke rehabilitation training [2]. Due to the high temporal resolution and non-invasive recording manner, EEG is widely used in brain studies and BCI applications. The brain activity recorded via EEG can be classified depending

Objectives
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call