TY - JOUR
T1 - Current Source Density Estimation Enhances the Performance of Motor-Imagery Related Brain-Computer Interface
AU - Rathee, Dheeraj
AU - Raza, Haider
AU - Prasad, Girijesh
AU - Cecotti, Hubert
PY - 2019/11/29
Y1 - 2019/11/29
N2 - The objective is to evaluate the impact of EEG referencing schemes and spherical surface Laplacian (SSL) methods on the classification performance of motor-imagery (MI)-related brain-computer interface systems. Two EEG referencing schemes: common referencing and common average referencing and three surface Laplacian methods: current source density (CSD), finite difference method, and SSL using realistic head model were implemented separately for pre-processing of the EEG signals recorded at the scalp. A combination of filter bank common spatial filter for features extraction and support vector machine for classification was used for both pairwise binary classifications and four-class classification of MI tasks. The study provides three major outcomes: 1) the CSD method performs better than CR, providing a significant improvement of 3.02% and 5.59% across six binary classification tasks and four-class classification task, respectively; 2) the combination of a greater number of channels at the pre-processing stage as compared with the feature extraction stage yields better classification accuracies for all the Laplacian methods; and 3) the efficiency of all the surface Laplacian methods reduced significantly in the case of a fewer number of channels considered during the pre-processing.
AB - The objective is to evaluate the impact of EEG referencing schemes and spherical surface Laplacian (SSL) methods on the classification performance of motor-imagery (MI)-related brain-computer interface systems. Two EEG referencing schemes: common referencing and common average referencing and three surface Laplacian methods: current source density (CSD), finite difference method, and SSL using realistic head model were implemented separately for pre-processing of the EEG signals recorded at the scalp. A combination of filter bank common spatial filter for features extraction and support vector machine for classification was used for both pairwise binary classifications and four-class classification of MI tasks. The study provides three major outcomes: 1) the CSD method performs better than CR, providing a significant improvement of 3.02% and 5.59% across six binary classification tasks and four-class classification task, respectively; 2) the combination of a greater number of channels at the pre-processing stage as compared with the feature extraction stage yields better classification accuracies for all the Laplacian methods; and 3) the efficiency of all the surface Laplacian methods reduced significantly in the case of a fewer number of channels considered during the pre-processing.
KW - Motor imagery
KW - Brain-computer interface
KW - Preprocessing
KW - Spatial filtering
KW - Spherical surface Laplacian.
UR - https://pure.ulster.ac.uk/en/publications/current-source-density-estimation-enhances-the-performance-of-mot-2
U2 - 10.1109/TNSRE.2017.2726779
DO - 10.1109/TNSRE.2017.2726779
M3 - Article
C2 - 28715332
VL - 25
SP - 2461
EP - 2471
JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering
JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering
SN - 1534-4320
IS - 12
ER -