Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation

Anirban Chowdhary, Haider Raza, Yogesh K. Meena, Ashish Dutta, Girijesh Prasad

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A major issue in electroencephalogram (EEG) based brain-computer interfaces (BCIs) is the intrinsic non-stationarities in the brain waves, which may degrade the performance of the classifier, while transitioning from calibration to feedback generation phase. The non-stationary nature of the EEG data may cause its input probability distribution to vary over time, which often appear as a covariate shift. To adapt to the covariate shift, we had proposed an adaptive learning method in our previous work and tested it on offline standard datasets. This paper presents an online BCI system using previously developed covariate shift detection (CSD)-based adaptive classifier to discriminate between mental tasks and generate neurofeedback in the form of visual and exoskeleton motion. The CSD test helps prevent unnecessary retraining of the classifier. The feasibility of the developed online-BCI system was first tested on 10 healthy individuals, and then on 10 stroke patients having hand disability. A comparison of the proposed online CSD-based adaptive classifier with conventional non-adaptive classifier has shown a significantly (p≤0.01) higher classification accuracy in both the cases of healthy and patient groups. The results demonstrate that the online CSD-based adaptive BCI system is superior to the non-adaptive BCI system and it is feasible to be used for actuating hand exoskeleton for the stroke-rehabilitation applications.
LanguageEnglish
Pages1070-1080
JournalIEEE Transactions on Cognitive and Developmental Systems
Volume10
Issue number4
Early online date25 Dec 2017
DOIs
Publication statusPublished - Dec 2018

Fingerprint

Brain computer interface
End effectors
Patient rehabilitation
Classifiers
Feedback
Electroencephalography
Probability distributions
Brain
Exoskeleton (Robotics)
Calibration

Keywords

  • Adaptive learning
  • Brain-computer interface
  • Covariate shift detection
  • Hand-exoskeleton
  • Neurorehabilitation.

Cite this

@article{15b834a1e65247d59d5082d2eae4bc68,
title = "Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation",
abstract = "A major issue in electroencephalogram (EEG) based brain-computer interfaces (BCIs) is the intrinsic non-stationarities in the brain waves, which may degrade the performance of the classifier, while transitioning from calibration to feedback generation phase. The non-stationary nature of the EEG data may cause its input probability distribution to vary over time, which often appear as a covariate shift. To adapt to the covariate shift, we had proposed an adaptive learning method in our previous work and tested it on offline standard datasets. This paper presents an online BCI system using previously developed covariate shift detection (CSD)-based adaptive classifier to discriminate between mental tasks and generate neurofeedback in the form of visual and exoskeleton motion. The CSD test helps prevent unnecessary retraining of the classifier. The feasibility of the developed online-BCI system was first tested on 10 healthy individuals, and then on 10 stroke patients having hand disability. A comparison of the proposed online CSD-based adaptive classifier with conventional non-adaptive classifier has shown a significantly (p≤0.01) higher classification accuracy in both the cases of healthy and patient groups. The results demonstrate that the online CSD-based adaptive BCI system is superior to the non-adaptive BCI system and it is feasible to be used for actuating hand exoskeleton for the stroke-rehabilitation applications.",
keywords = "Adaptive learning, Brain-computer interface, Covariate shift detection, Hand-exoskeleton, Neurorehabilitation.",
author = "Anirban Chowdhary and Haider Raza and Meena, {Yogesh K.} and Ashish Dutta and Girijesh Prasad",
year = "2018",
month = "12",
doi = "10.1109/TCDS.2017.2787040",
language = "English",
volume = "10",
pages = "1070--1080",
journal = "IEEE Transactions on Cognitive and Developmental Systems",
issn = "2379-8920",
number = "4",

}

Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation. / Chowdhary, Anirban; Raza, Haider; Meena, Yogesh K.; Dutta, Ashish; Prasad, Girijesh.

In: IEEE Transactions on Cognitive and Developmental Systems, Vol. 10, No. 4, 12.2018, p. 1070-1080.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation

AU - Chowdhary, Anirban

AU - Raza, Haider

AU - Meena, Yogesh K.

AU - Dutta, Ashish

AU - Prasad, Girijesh

PY - 2018/12

Y1 - 2018/12

N2 - A major issue in electroencephalogram (EEG) based brain-computer interfaces (BCIs) is the intrinsic non-stationarities in the brain waves, which may degrade the performance of the classifier, while transitioning from calibration to feedback generation phase. The non-stationary nature of the EEG data may cause its input probability distribution to vary over time, which often appear as a covariate shift. To adapt to the covariate shift, we had proposed an adaptive learning method in our previous work and tested it on offline standard datasets. This paper presents an online BCI system using previously developed covariate shift detection (CSD)-based adaptive classifier to discriminate between mental tasks and generate neurofeedback in the form of visual and exoskeleton motion. The CSD test helps prevent unnecessary retraining of the classifier. The feasibility of the developed online-BCI system was first tested on 10 healthy individuals, and then on 10 stroke patients having hand disability. A comparison of the proposed online CSD-based adaptive classifier with conventional non-adaptive classifier has shown a significantly (p≤0.01) higher classification accuracy in both the cases of healthy and patient groups. The results demonstrate that the online CSD-based adaptive BCI system is superior to the non-adaptive BCI system and it is feasible to be used for actuating hand exoskeleton for the stroke-rehabilitation applications.

AB - A major issue in electroencephalogram (EEG) based brain-computer interfaces (BCIs) is the intrinsic non-stationarities in the brain waves, which may degrade the performance of the classifier, while transitioning from calibration to feedback generation phase. The non-stationary nature of the EEG data may cause its input probability distribution to vary over time, which often appear as a covariate shift. To adapt to the covariate shift, we had proposed an adaptive learning method in our previous work and tested it on offline standard datasets. This paper presents an online BCI system using previously developed covariate shift detection (CSD)-based adaptive classifier to discriminate between mental tasks and generate neurofeedback in the form of visual and exoskeleton motion. The CSD test helps prevent unnecessary retraining of the classifier. The feasibility of the developed online-BCI system was first tested on 10 healthy individuals, and then on 10 stroke patients having hand disability. A comparison of the proposed online CSD-based adaptive classifier with conventional non-adaptive classifier has shown a significantly (p≤0.01) higher classification accuracy in both the cases of healthy and patient groups. The results demonstrate that the online CSD-based adaptive BCI system is superior to the non-adaptive BCI system and it is feasible to be used for actuating hand exoskeleton for the stroke-rehabilitation applications.

KW - Adaptive learning

KW - Brain-computer interface

KW - Covariate shift detection

KW - Hand-exoskeleton

KW - Neurorehabilitation.

U2 - 10.1109/TCDS.2017.2787040

DO - 10.1109/TCDS.2017.2787040

M3 - Article

VL - 10

SP - 1070

EP - 1080

JO - IEEE Transactions on Cognitive and Developmental Systems

T2 - IEEE Transactions on Cognitive and Developmental Systems

JF - IEEE Transactions on Cognitive and Developmental Systems

SN - 2379-8920

IS - 4

ER -