Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients
In this paper, a novel methodology for enhanced classification of functional near-infrared spectroscopy (fNIRS) signals utilizable in a two-class [motor imagery (MI) and rest; mental rotation (MR) and rest] brain–computer interface (BCI) is presented. First, fNIRS signals corresponding to MI and MR...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2017-07-01
|
Series: | Frontiers in Neurorobotics |
Subjects: | |
Online Access: | http://journal.frontiersin.org/article/10.3389/fnbot.2017.00033/full |
id |
doaj-29a95559a13f4d30b2197257e7cc0932 |
---|---|
record_format |
Article |
spelling |
doaj-29a95559a13f4d30b2197257e7cc09322020-11-24T22:36:41ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182017-07-011110.3389/fnbot.2017.00033253477Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model CoefficientsNauman Khalid Qureshi0Noman Naseer1Farzan Majeed Noori2Farzan Majeed Noori3Hammad Nazeer4Rayyan Azam Khan5Sajid Saleem6Department of Mechatronics Engineering, Air University, Islamabad, PakistanDepartment of Mechatronics Engineering, Air University, Islamabad, PakistanDepartment of Mechatronics Engineering, Air University, Islamabad, PakistanDepartment of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Coimbra, PortugalDepartment of Mechatronics Engineering, Air University, Islamabad, PakistanDepartment of Mechatronics Engineering, Air University, Islamabad, PakistanFaculty of Engineering and Computer Sciences, National University of Modern Languages, Islamabad, PakistanIn this paper, a novel methodology for enhanced classification of functional near-infrared spectroscopy (fNIRS) signals utilizable in a two-class [motor imagery (MI) and rest; mental rotation (MR) and rest] brain–computer interface (BCI) is presented. First, fNIRS signals corresponding to MI and MR are acquired from the motor and prefrontal cortex, respectively, afterward, filtered to remove physiological noises. Then, the signals are modeled using the general linear model, the coefficients of which are adaptively estimated using the least squares technique. Subsequently, multiple feature combinations of estimated coefficients were used for classification. The best classification accuracies achieved for five subjects, for MI versus rest are 79.5, 83.7, 82.6, 81.4, and 84.1% whereas those for MR versus rest are 85.5, 85.2, 87.8, 83.7, and 84.8%, respectively, using support vector machine. These results are compared with the best classification accuracies obtained using the conventional hemodynamic response. By means of the proposed methodology, the average classification accuracy obtained was significantly higher (p < 0.05). These results serve to demonstrate the feasibility of developing a high-classification-performance fNIRS-BCI.http://journal.frontiersin.org/article/10.3389/fnbot.2017.00033/fullfunctional near-infrared spectroscopybrain–computer interfacegeneral linear modelleast squares estimationadaptive estimationsupport vector machine |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nauman Khalid Qureshi Noman Naseer Farzan Majeed Noori Farzan Majeed Noori Hammad Nazeer Rayyan Azam Khan Sajid Saleem |
spellingShingle |
Nauman Khalid Qureshi Noman Naseer Farzan Majeed Noori Farzan Majeed Noori Hammad Nazeer Rayyan Azam Khan Sajid Saleem Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients Frontiers in Neurorobotics functional near-infrared spectroscopy brain–computer interface general linear model least squares estimation adaptive estimation support vector machine |
author_facet |
Nauman Khalid Qureshi Noman Naseer Farzan Majeed Noori Farzan Majeed Noori Hammad Nazeer Rayyan Azam Khan Sajid Saleem |
author_sort |
Nauman Khalid Qureshi |
title |
Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients |
title_short |
Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients |
title_full |
Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients |
title_fullStr |
Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients |
title_full_unstemmed |
Enhancing Classification Performance of Functional Near-Infrared Spectroscopy- Brain–Computer Interface Using Adaptive Estimation of General Linear Model Coefficients |
title_sort |
enhancing classification performance of functional near-infrared spectroscopy- brain–computer interface using adaptive estimation of general linear model coefficients |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neurorobotics |
issn |
1662-5218 |
publishDate |
2017-07-01 |
description |
In this paper, a novel methodology for enhanced classification of functional near-infrared spectroscopy (fNIRS) signals utilizable in a two-class [motor imagery (MI) and rest; mental rotation (MR) and rest] brain–computer interface (BCI) is presented. First, fNIRS signals corresponding to MI and MR are acquired from the motor and prefrontal cortex, respectively, afterward, filtered to remove physiological noises. Then, the signals are modeled using the general linear model, the coefficients of which are adaptively estimated using the least squares technique. Subsequently, multiple feature combinations of estimated coefficients were used for classification. The best classification accuracies achieved for five subjects, for MI versus rest are 79.5, 83.7, 82.6, 81.4, and 84.1% whereas those for MR versus rest are 85.5, 85.2, 87.8, 83.7, and 84.8%, respectively, using support vector machine. These results are compared with the best classification accuracies obtained using the conventional hemodynamic response. By means of the proposed methodology, the average classification accuracy obtained was significantly higher (p < 0.05). These results serve to demonstrate the feasibility of developing a high-classification-performance fNIRS-BCI. |
topic |
functional near-infrared spectroscopy brain–computer interface general linear model least squares estimation adaptive estimation support vector machine |
url |
http://journal.frontiersin.org/article/10.3389/fnbot.2017.00033/full |
work_keys_str_mv |
AT naumankhalidqureshi enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT nomannaseer enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT farzanmajeednoori enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT farzanmajeednoori enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT hammadnazeer enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT rayyanazamkhan enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients AT sajidsaleem enhancingclassificationperformanceoffunctionalnearinfraredspectroscopybraincomputerinterfaceusingadaptiveestimationofgenerallinearmodelcoefficients |
_version_ |
1725718838961504256 |