An adaptive CSP filter to investigate user independence in a 3-class MI-BCI paradigm

TY - JOUR

T1 - An adaptive CSP filter to investigate user independence in a 3-class MI-BCI paradigm

AU - Costa, Ana P.

AU - Møller, Jakob S.

AU - Iversen, Helle K.

AU - Puthusserypady, Sadasivan

PY - 2018

Y1 - 2018

N2 - This paper describes the implementation of a Brain Computer Interface (BCI) scheme using a common spatial patterns (CSP) filter in combination with a Recursive Least Squares (RLS) approach to iteratively update the coefficients of the CSP filter. The proposed adaptive CSP (ACSP) algorithm is made more robust by introducing regularization using Diagonal Loading (DL), and thus will be able to significantly reduce the length of training sessions when introducing new patients to the BCI system. The system is tested on a 4-class multi-limb motor imagery (MI) data set from the BCI competition IV (2a), and a more complex single limb 3-class MI dataset recorded in-house. The latter dataset is produced to mimic an upper limb rehabilitation session, e.g., after stroke. The findings indicate that when extensive calibration data is available, the ACSP performs comparably to the CSP (kappa value of 0.523 and 0.502, respectively, for the 4-class problem); for reduced calibration sessions, the ACSP significantly improved the performance of the system (up to 4-fold). The proposed paradigm proved feasible and the ACSP algorithm seems to enable a user or semi user independent scenario, where the need for long system calibration sessions without feedback is eliminated.

AB - This paper describes the implementation of a Brain Computer Interface (BCI) scheme using a common spatial patterns (CSP) filter in combination with a Recursive Least Squares (RLS) approach to iteratively update the coefficients of the CSP filter. The proposed adaptive CSP (ACSP) algorithm is made more robust by introducing regularization using Diagonal Loading (DL), and thus will be able to significantly reduce the length of training sessions when introducing new patients to the BCI system. The system is tested on a 4-class multi-limb motor imagery (MI) data set from the BCI competition IV (2a), and a more complex single limb 3-class MI dataset recorded in-house. The latter dataset is produced to mimic an upper limb rehabilitation session, e.g., after stroke. The findings indicate that when extensive calibration data is available, the ACSP performs comparably to the CSP (kappa value of 0.523 and 0.502, respectively, for the 4-class problem); for reduced calibration sessions, the ACSP significantly improved the performance of the system (up to 4-fold). The proposed paradigm proved feasible and the ACSP algorithm seems to enable a user or semi user independent scenario, where the need for long system calibration sessions without feedback is eliminated.

KW - Brain-computer interface (BCI)

KW - Common spatial patterns (CSP)

KW - Diagonal loading (DL) CSP (DLCSP)

KW - Electroencephalography(EEG)

KW - Motor imagery (MI)

KW - Recursive least squares (RLS)

KW - Stroke rehabilitation

U2 - 10.1016/j.compbiomed.2018.09.021

DO - 10.1016/j.compbiomed.2018.09.021

M3 - Journal article

AN - SCOPUS:85054756315

SN - 0010-4825

VL - 103

SP - 24

EP - 33

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

ER -