Harsha Battapady1, Peter Lin2, Tom Holroyd3, Mark Hallett2, Xuedong Chen4, Ding-Yu Fei1, Ou Bai5. 1. EEG & BCI Laboratory, Department of Biomedical Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA. 2. Human Motor Control Section, Medical Neurological Branch, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA. 3. MEG Core Facility, National Institute of Mental Health, Bethesda, MD 20892, USA. 4. State Key Laboratory of Digital Manufacturing Equipment & Technology, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China. 5. EEG & BCI Laboratory, Department of Biomedical Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA; Human Motor Control Section, Medical Neurological Branch, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA. Electronic address: obai@vcu.edu.
Abstract
OBJECTIVE: To test whether human intentions to sustain or cease movements in right and left hands can be decoded reliably from spatially filtered single-trial magnetoencephalographic (MEG) signals for motor execution and motor imagery. METHODS: Seven healthy volunteers, naïve to BCI technology, participated in this study. Signals were recorded from 275-channel MEG, and synthetic aperture magnetometry (SAM) was employed as the spatial filter. The four-class classification was performed offline. Genetic algorithm based Mahalanobis linear distance (GA-MLD) and direct-decision tree classifier (DTC) techniques were adopted for the classification through 10-fold cross-validation. RESULTS: Through SAM imaging, strong and distinct event-related desynchronization (ERD) associated with sustaining, and event-related synchronization (ERS) patterns associated with ceasing of right and left hand movements were observed in the beta band (15-30Hz) on the contralateral hemispheres for motor execution and motor imagery sessions. Virtual channels were selected from these areas of high activity for the corresponding events as per the paradigm of the study. Through a statistical comparison between SAM-filtered virtual channels from single-trial MEG signals and basic MEG sensors, it was found that SAM-filtered virtual channels significantly increased the classification accuracy for motor execution (GA-MLD: 96.51+/-2.43%) as well as motor imagery sessions (GA-MLD: 89.69+/-3.34%). CONCLUSION: Multiple movement intentions can be reliably detected from SAM-based spatially filtered single-trial MEG signals. SIGNIFICANCE: MEG signals associated with natural motor behavior may be utilized for a reliable high-performance brain-computer interface (BCI) and may reduce long-term training compared with conventional BCI methods using rhythm control.
OBJECTIVE: To test whether human intentions to sustain or cease movements in right and left hands can be decoded reliably from spatially filtered single-trial magnetoencephalographic (MEG) signals for motor execution and motor imagery. METHODS: Seven healthy volunteers, naïve to BCI technology, participated in this study. Signals were recorded from 275-channel MEG, and synthetic aperture magnetometry (SAM) was employed as the spatial filter. The four-class classification was performed offline. Genetic algorithm based Mahalanobis linear distance (GA-MLD) and direct-decision tree classifier (DTC) techniques were adopted for the classification through 10-fold cross-validation. RESULTS: Through SAM imaging, strong and distinct event-related desynchronization (ERD) associated with sustaining, and event-related synchronization (ERS) patterns associated with ceasing of right and left hand movements were observed in the beta band (15-30Hz) on the contralateral hemispheres for motor execution and motor imagery sessions. Virtual channels were selected from these areas of high activity for the corresponding events as per the paradigm of the study. Through a statistical comparison between SAM-filtered virtual channels from single-trial MEG signals and basic MEG sensors, it was found that SAM-filtered virtual channels significantly increased the classification accuracy for motor execution (GA-MLD: 96.51+/-2.43%) as well as motor imagery sessions (GA-MLD: 89.69+/-3.34%). CONCLUSION: Multiple movement intentions can be reliably detected from SAM-based spatially filtered single-trial MEG signals. SIGNIFICANCE: MEG signals associated with natural motor behavior may be utilized for a reliable high-performance brain-computer interface (BCI) and may reduce long-term training compared with conventional BCI methods using rhythm control.
Authors: M Taniguchi; A Kato; N Fujita; M Hirata; H Tanaka; T Kihara; H Ninomiya; N Hirabuki; H Nakamura; S E Robinson; D Cheyne; T Yoshimine Journal: Neuroimage Date: 2000-09 Impact factor: 6.556
Authors: J R Wolpaw; N Birbaumer; W J Heetderks; D J McFarland; P H Peckham; G Schalk; E Donchin; L A Quatrano; C J Robinson; T M Vaughan Journal: IEEE Trans Rehabil Eng Date: 2000-06
Authors: Jonathan R Wolpaw; Niels Birbaumer; Dennis J McFarland; Gert Pfurtscheller; Theresa M Vaughan Journal: Clin Neurophysiol Date: 2002-06 Impact factor: 3.708
Authors: Carolin A Ruf; Daniele De Massari; Adrian Furdea; Tamara Matuz; Chiara Fioravanti; Linda van der Heiden; Sebastian Halder; Niels Birbaumer Journal: Front Neurosci Date: 2013-03-07 Impact factor: 4.677
Authors: Minkyu Ahn; Sangtae Ahn; Jun H Hong; Hohyun Cho; Kiwoong Kim; Bong S Kim; Jin W Chang; Sung C Jun Journal: Front Hum Neurosci Date: 2013-12-06 Impact factor: 3.169