Classification of different reaching movements from the same limb using EEG

Farid Shiman,Ander Ramos-Murguialday,Niels Birbaumer,Nerea Irastorza-Landa,Andrea Sarasola-Sanz,Martin Spüler,Eduardo López-Larraz

doi:10.1088/1741-2552/aa70d2

Abstract

Objective. Brain–computer-interfaces (BCIs) have been proposed not only as assistive technologies but also as rehabilitation tools for lost functions. However, due to the stochastic nature, poor spatial resolution and signal to noise ratio from electroencephalography (EEG), multidimensional decoding has been the main obstacle to implement non-invasive BCIs in real-live rehabilitation scenarios. This study explores the classification of several functional reaching movements from the same limb using EEG oscillations in order to create a more versatile BCI for rehabilitation. Approach. Nine healthy participants performed four 3D center-out reaching tasks in four different sessions while wearing a passive robotic exoskeleton at their right upper limb. Kinematics data were acquired from the robotic exoskeleton. Multiclass extensions of Filter Bank Common Spatial Patterns (FBCSP) and a linear discriminant analysis (LDA) classifier were used to classify the EEG activity into four forward reaching movements (from a starting position towards four target positions), a backward movement (from any of the targets to the starting position and rest). Recalibrating the classifier using data from previous or the same session was also investigated and compared. Main results. Average EEG decoding accuracy were significantly above chance with 67%, 62.75%, and 50.3% when decoding three, four and six tasks from the same limb, respectively. Furthermore, classification accuracy could be increased when using data from the beginning of each session as training data to recalibrate the classifier. Significance. Our results demonstrate that classification from several functional movements performed by the same limb is possible with acceptable accuracy using EEG oscillations, especially if data from the same session are used to recalibrate the classifier. Therefore, an ecologically valid decoding could be used to control assistive or rehabilitation mutli-degrees of freedom (DoF) robotic devices using EEG data. These results have important implications towards assistive and rehabilitative neuroprostheses control in paralyzed patients.

Highlights

Brain–computer interface (BCI) systems can be used to decode brain activity into commands to control external devices [1, 2]
Involvement on descending motor commands was suggested as key mechanism in motor rehabilitation because motor execution/attempt brain activity only was correlated with significant motor improvement compared to motor imagery related brain activity during a proprioceptive BCI rehabilitative intervention [3]
The mean average accuracy across participants increased from the first session (64%) to the fourth session (69%) being this difference non-significant ( p = 0.61)

Summary

Introduction

Brain–computer interface (BCI) systems can be used to decode brain activity into commands to control external devices [1, 2]. Initial EEG-based BCI studies controlling several DoFs were achieved using motor imagery paradigms involving different limbs (e.g. 3D cursor control using hand versus feet versus tongue motor imagery) [9, 10]. New strategies have been used to control multi-DoF robots based on EEG error potentials [11], steady state visual evoked potentials (SSVEPs) [12] and P300 potentials, even in ALS patients [13,14,15] These strategies require attention but ignore motor descending corticospinal volleys, which seems to be key aspect in motor rehabilitation BCIs aiming at restoring natural corticomuscular connections [3]. Other strategies like trajectory decoding [16] might offer a promising solution, albeit methodological challenges [17]

Results

Discussion

Conclusion