A Brain-Machine Interface Based on ERD/ERS for an Upper-Limb Exoskeleton Control (2016)
Open in webOpen in zoteroOpen pdf
1 Abstract
To recognize the user’s motion intention, brain-machine interfaces (BMI) usually decode movements from cortical activity to control exoskeletons and neuroprostheses for daily activities. The aim of this paper is to investigate whether self-induced variations of the electroencephalogram (EEG) can be useful as control signals for an upper-limb exoskeleton developed by us. A BMI based on event-related desynchronization/synchronization (ERD/ERS) is proposed. In the decoder-training phase, we investigate the offline classification performance of left versus right hand and left hand versus both feet by using motor execution (ME) or motor imagery (MI). The results indicate that the accuracies of ME sessions are higher than those of MI sessions, and left hand versus both feet paradigm achieves a better classification performance, which would be used in the online-control phase. In the online-control phase, the trained decoder is tested in two scenarios (wearing or without wearing the exoskeleton). The MI and ME sessions wearing the exoskeleton achieve mean classification accuracy of 84.29% ± 2.11% and 87.37% ± 3.06%, respectively. The present study demonstrates that the proposed BMI is effective to control the upper-limb exoskeleton, and provides a practical method by non-invasive EEG signal associated with human natural behavior for clinical applications.
2 NOTES
In this paper the authors propose a BCI, using ERS/ERD to identify the time period and best frequency band for each subject, which was then used for feature and extraction and classification (using many models, from which LDA using 80%-20% train-test ration achieved the best results). The ERS/ERD in here was used for electrodes C3, Cz and C4, and it showed, for ME and MI of right hand and left hand, a significant ERD and post-movement ERS over the contralateral side, however, only a weak ERS was seen over the ipsilateral side and at the Cz electrode. The problem is that ERD is observed from around 1-4 s after cue and ERS mainly around 7-8 s, so the whole signal is required. The best frequency band are the usual ones, for some subject 1 was 8-12 Hz, for subject 2 was 18-22 Hz, for subject 4 was 14-18 Hz, and for subject 3 was 12-16 Hz. But essentially, they all fall within the 8-32 Hz band that is usually applied. Of course, a filter-bank with a range of 4 Hz would make sure that they all have the best bands separated. Overall, their application and depth on the use of ERD/ERS is commendable, certainly a great paper to be used as reference, but their results was nothing astonishing.