Detection of movement-related cortical potentials based on subject-independent training

Imran Khan Niazi,Mads Jochumsen,Jørgen Feldbæk Nielsen,Kim Dremstrup,Ning Jiang,Dario Farina

doi:10.1007/s11517-012-1018-1

Abstract

To allow a routinely use of brain–computer interfaces (BCI), there is a need to reduce or completely eliminate the time-consuming part of the individualized training of the user. In this study, we investigate the possibility of avoiding the individual training phase in the detection of movement intention in asynchronous BCIs based on movement-related cortical potential (MRCP). EEG signals were recorded during ballistic ankle dorsiflexions executed (ME) or imagined (MI) by 20 healthy subjects, and attempted by five stroke subjects. These recordings were used to identify a template (as average over all subjects) for the initial negative phase of the MRCPs, after the application of an optimized spatial filtering used for pre-processing. Using this template, the detection accuracy (mean ± SD) calculated as true positive rate (estimated with leave-one-out procedure) for ME was 69 ± 21 and 58 ± 11 % on single trial basis for healthy and stroke subjects, respectively. This performance was similar to that obtained using an individual template for each subject, which led to accuracies of 71 ± 6 and 55 ± 12 % for healthy and stroke subjects, respectively. The detection accuracy for the MI data was 65 ± 22 % with the average template and 60 ± 13 % with the individual template. These results indicate the possibility of detecting movement intention without an individual training phase and without a significant loss in performance.

Highlights

A brain–computer interface (BCI) provides an alternative communication channel for healthy or disabled users from their brains to external environment
We investigate the possibility of avoiding the individual training phase in the detection of movement intention in asynchronous brain–computer interfaces (BCI) based on movement-related cortical potential (MRCP)
The true positive rate (TPR) (%) and false positives (FPs) per minute of the global detector (GD) with TST1 and TST2 as test data set and the individualized detector (ID) are presented in Fig. 2 for healthy subjects and stroke patients

Summary

Introduction

A brain–computer interface (BCI) provides an alternative communication channel for healthy or disabled users from their brains to external environment. A BCI system can detect changes of the state of mind from the on-going EEG and control an external device (e.g., text-entry system, prosthesis, and computer game). Since no peripheral nerves or muscles are involved in this process, BCI systems may be used as an assistive technology for patients with severe motor disabilities, such as stroke or locked-in patients [4]. In classic BCI approaches, the systems require extensive, sometimes frustrating, training by the subjects [1, 6]. A subject-independent calibration (training) of a BCI system has been proposed for a two-class classification task [7]

Methods

Results

Conclusion