1
|
Freudenburg ZV, Branco MP, Leinders S, van der Vijgh BH, Pels EGM, Denison T, van den Berg LH, Miller KJ, Aarnoutse EJ, Ramsey NF, Vansteensel MJ. Sensorimotor ECoG Signal Features for BCI Control: A Comparison Between People With Locked-In Syndrome and Able-Bodied Controls. Front Neurosci 2019; 13:1058. [PMID: 31680806 PMCID: PMC6805728 DOI: 10.3389/fnins.2019.01058] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2019] [Accepted: 09/20/2019] [Indexed: 01/10/2023] Open
Abstract
The sensorimotor cortex is a frequently targeted brain area for the development of Brain-Computer Interfaces (BCIs) for communication in people with severe paralysis and communication problems (locked-in syndrome; LIS). It is widely acknowledged that this area displays an increase in high-frequency band (HFB) power and a decrease in the power of the low frequency band (LFB) during movement of, for example, the hand. Upon termination of hand movement, activity in the LFB band typically shows a short increase (rebound). The ability to modulate the neural signal in the sensorimotor cortex by imagining or attempting to move is crucial for the implementation of sensorimotor BCI in people who are unable to execute movements. This may not always be self-evident, since the most common causes of LIS, amyotrophic lateral sclerosis (ALS) and brain stem stroke, are associated with significant damage to the brain, potentially affecting the generation of baseline neural activity in the sensorimotor cortex and the modulation thereof by imagined or attempted hand movement. In the Utrecht NeuroProsthesis (UNP) study, a participant with LIS caused by ALS and a participant with LIS due to brain stem stroke were implanted with a fully implantable BCI, including subdural electrocorticography (ECoG) electrodes over the sensorimotor area, with the purpose of achieving ECoG-BCI-based communication. We noted differences between these participants in the spectral power changes generated by attempted movement of the hand. To better understand the nature and origin of these differences, we compared the baseline spectral features and task-induced modulation of the neural signal of the LIS participants, with those of a group of able-bodied people with epilepsy who received a subchronic implant with ECoG electrodes for diagnostic purposes. Our data show that baseline LFB oscillatory components and changes generated in the LFB power of the sensorimotor cortex by (attempted) hand movement differ between participants, despite consistent HFB responses in this area. We conclude that the etiology of LIS may have significant effects on the LFB spectral components in the sensorimotor cortex, which is relevant for the development of communication-BCIs for this population.
Collapse
Affiliation(s)
- Zachary V Freudenburg
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Mariana P Branco
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Sacha Leinders
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Benny H van der Vijgh
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Elmar G M Pels
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Timothy Denison
- Department of Engineering Science, University of Oxford, Oxford, United Kingdom
| | - Leonard H van den Berg
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Kai J Miller
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Erik J Aarnoutse
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Nick F Ramsey
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Mariska J Vansteensel
- UMC Utrecht Brain Center, Department of Neurology & Neurosurgery, University Medical Center Utrecht, Utrecht, Netherlands
| |
Collapse
|
2
|
She Q, Hu B, Luo Z, Nguyen T, Zhang Y. A hierarchical semi-supervised extreme learning machine method for EEG recognition. Med Biol Eng Comput 2018; 57:147-157. [DOI: 10.1007/s11517-018-1875-3] [Citation(s) in RCA: 25] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2017] [Accepted: 12/22/2017] [Indexed: 10/28/2022]
|
3
|
Lee M, Park CH, Im CH, Kim JH, Kwon GH, Kim L, Chang WH, Kim YH. Motor imagery learning across a sequence of trials in stroke patients. Restor Neurol Neurosci 2018; 34:635-45. [PMID: 26410210 DOI: 10.3233/rnn-150534] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
PURPOSE In brain-computer interfaces (BCIs), electrical brain signals during motor imagery are utilized as commands connecting the brain to a computer. To use BCI in patients with stroke, unique brain signal changes should be characterized during motor imagery process. This study aimed to examine the trial-dependent motor-imagery-related activities in stroke patients. METHODS During the recording of electroencephalography (EEG) signals, 12 chronic stroke patients and 11 age-matched healthy controls performed motor imagery finger tapping at 1.3 sec intervals. Trial-dependent brain signal changes were assessed by analysis of the mu and beta bands. RESULTS Neuronal activity in healthy controls was observed over bilateral hemispheres at the mu and beta bands regardless of changes in the trials, whereas neuronal activity in stroke patients was mainly seen over the ipsilesional hemisphere at the beta band. With progression to repeated trials, healthy controls displayed a decrease in cortical activity in the contralateral hemisphere at the mu band and in bilateral hemispheres at the beta band. In contrast, stroke patients showed a decreasing trend in cortical activity only over the ipsilesional hemisphere at the beta band. CONCLUSIONS Trial-dependent changes during motor imagery learning presented in a different manner in stroke patients. Understanding motor imagery learning in stroke patients is crucial for enhancing the effectiveness of motor-imagery-based BCIs.
Collapse
Affiliation(s)
- Minji Lee
- Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences and Technology, Sungkyunkwan University, Irwon-dong, Gangnam-gu, Seoul, Republic of Korea
| | - Chang-Hyun Park
- Department of Physical and Rehabilitation Medicine, Center for Prevention & Rehabilitation, Heart Vascular and Stroke, Samsung Medical Center, Sungkyunkwan University School of Medicine, Irwon-dong, Gangnam-gu, Seoul, Republic of Korea
| | - Chang-Hwan Im
- Department of Biomedical Engineering, Hanyang University, Haengdang 1-dong, Seongdong-gu, Seoul, Republic of Korea
| | - Jung-Hoon Kim
- Department of Biomedical Engineering, Hanyang University, Haengdang 1-dong, Seongdong-gu, Seoul, Republic of Korea
| | - Gyu-Hyun Kwon
- Center for Bionics, Korea Institute of Science and Technology (KIST), Wolgok 2-dong, Seongbuk-gu, Seoul, Republic of Korea
| | - Laehyun Kim
- Center for Bionics, Korea Institute of Science and Technology (KIST), Wolgok 2-dong, Seongbuk-gu, Seoul, Republic of Korea
| | - Won Hyuk Chang
- Department of Physical and Rehabilitation Medicine, Center for Prevention & Rehabilitation, Heart Vascular and Stroke, Samsung Medical Center, Sungkyunkwan University School of Medicine, Irwon-dong, Gangnam-gu, Seoul, Republic of Korea
| | - Yun-Hee Kim
- Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences and Technology, Sungkyunkwan University, Irwon-dong, Gangnam-gu, Seoul, Republic of Korea.,Department of Physical and Rehabilitation Medicine, Center for Prevention & Rehabilitation, Heart Vascular and Stroke, Samsung Medical Center, Sungkyunkwan University School of Medicine, Irwon-dong, Gangnam-gu, Seoul, Republic of Korea
| |
Collapse
|
4
|
Kumar S, Mamun K, Sharma A. CSP-TSM: Optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI. Comput Biol Med 2017; 91:231-242. [PMID: 29100117 DOI: 10.1016/j.compbiomed.2017.10.025] [Citation(s) in RCA: 51] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2017] [Revised: 10/08/2017] [Accepted: 10/23/2017] [Indexed: 11/18/2022]
Abstract
BACKGROUND Classification of electroencephalography (EEG) signals for motor imagery based brain computer interface (MI-BCI) is an exigent task and common spatial pattern (CSP) has been extensively explored for this purpose. In this work, we focused on developing a new framework for classification of EEG signals for MI-BCI. METHOD We propose a single band CSP framework for MI-BCI that utilizes the concept of tangent space mapping (TSM) in the manifold of covariance matrices. The proposed method is named CSP-TSM. Spatial filtering is performed on the bandpass filtered MI EEG signal. Riemannian tangent space is utilized for extracting features from the spatial filtered signal. The TSM features are then fused with the CSP variance based features and feature selection is performed using Lasso. Linear discriminant analysis (LDA) is then applied to the selected features and finally classification is done using support vector machine (SVM) classifier. RESULTS The proposed framework gives improved performance for MI EEG signal classification in comparison with several competing methods. Experiments conducted shows that the proposed framework reduces the overall classification error rate for MI-BCI by 3.16%, 5.10% and 1.70% (for BCI Competition III dataset IVa, BCI Competition IV Dataset I and BCI Competition IV Dataset IIb, respectively) compared to the conventional CSP method under the same experimental settings. CONCLUSION The proposed CSP-TSM method produces promising results when compared with several competing methods in this paper. In addition, the computational complexity is less compared to that of TSM method. Our proposed CSP-TSM framework can be potentially used for developing improved MI-BCI systems.
Collapse
Affiliation(s)
- Shiu Kumar
- Department of Electronics, Instrumentation and Control, School of Electrical & Electronics Engineering, College of Engineering, Science and Technology, Fiji National University, Suva, Fiji; School of Engineering and Physics, Faculty of Science, Technology and Environment, The University of the South Pacific, Suva, Fiji.
| | - Kabir Mamun
- School of Engineering and Physics, Faculty of Science, Technology and Environment, The University of the South Pacific, Suva, Fiji.
| | - Alok Sharma
- School of Engineering and Physics, Faculty of Science, Technology and Environment, The University of the South Pacific, Suva, Fiji; Institute for Integrated and Intelligent Systems (IIIS), Griffith University, Brisbane, Australia; RIKEN Center for Integrative Medical Sciences, Yokohama 230-0045, Japan.
| |
Collapse
|
5
|
Park HJ, Kim J, Min B, Lee B. Motor imagery EEG classification with optimal subset of wavelet based common spatial pattern and kernel extreme learning machine. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2017; 2017:2863-2866. [PMID: 29060495 DOI: 10.1109/embc.2017.8037454] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
Performance of motor imagery based brain-computer interfaces (MI BCIs) greatly depends on how to extract the features. Various versions of filter-bank based common spatial pattern have been proposed and used in MI BCIs. Filter-bank based common spatial pattern has more number of features compared with original common spatial pattern. As the number of features increases, the MI BCIs using filter-bank based common spatial pattern can face overfitting problems. In this study, we used eigenvector centrality feature selection method, wavelet packet decomposition common spatial pattern, and kernel extreme learning machine to improve the performance of MI BCIs and avoid overfitting problems. Furthermore, the computational speed was improved by using kernel extreme learning machine.
Collapse
|
6
|
Tian J, Zhang Z. Research on Algorithm for Feature Extraction and Classification of Motor Imagery EEG Signals. BIO WEB OF CONFERENCES 2017. [DOI: 10.1051/bioconf/20170802013] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
|
7
|
Alonso-Valerdi LM, Salido-Ruiz RA, Ramirez-Mendoza RA. Motor imagery based brain-computer interfaces: An emerging technology to rehabilitate motor deficits. Neuropsychologia 2015; 79:354-63. [PMID: 26382749 DOI: 10.1016/j.neuropsychologia.2015.09.012] [Citation(s) in RCA: 31] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2015] [Revised: 09/07/2015] [Accepted: 09/08/2015] [Indexed: 12/16/2022]
Abstract
When the sensory-motor integration system is malfunctioning provokes a wide variety of neurological disorders, which in many cases cannot be treated with conventional medication, or via existing therapeutic technology. A brain-computer interface (BCI) is a tool that permits to reintegrate the sensory-motor loop, accessing directly to brain information. A potential, promising and quite investigated application of BCI has been in the motor rehabilitation field. It is well-known that motor deficits are the major disability wherewith the worldwide population lives. Therefore, this paper aims to specify the foundation of motor rehabilitation BCIs, as well as to review the recent research conducted so far (specifically, from 2007 to date), in order to evaluate the suitability and reliability of this technology. Although BCI for post-stroke rehabilitation is still in its infancy, the tendency is towards the development of implantable devices that encompass a BCI module plus a stimulation system.
Collapse
Affiliation(s)
- Luz Maria Alonso-Valerdi
- Escuela de Ingeniería y Ciencias, Tecnológico de Monterrey - Campus Ciudad de México, Calle del Puente No. 222 Col. Ejidos de Huipulco, Tlalpan, C.P. 14380 Ciudad de México, Mexico.
| | - Ricardo Antonio Salido-Ruiz
- Departamento de Ciencias Computacionales, División de Electrónica y Computación, Centro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Boulevard Gral. Marcelino García Barragán 1421, Olímpica, C.P. 44430 Guadalajara, Jalisco, Mexico.
| | - Ricardo A Ramirez-Mendoza
- Escuela de Ingeniería y Ciencias, Tecnológico de Monterrey - Campus Ciudad de México, Calle del Puente No. 222 Col. Ejidos de Huipulco, Tlalpan, C.P. 14380 Ciudad de México, Mexico.
| |
Collapse
|
8
|
Enhanced performance by time-frequency-phase feature for EEG-based BCI systems. ScientificWorldJournal 2014; 2014:420561. [PMID: 25045733 PMCID: PMC4087262 DOI: 10.1155/2014/420561] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2014] [Revised: 05/18/2014] [Accepted: 06/02/2014] [Indexed: 11/17/2022] Open
Abstract
We introduce a new motor parameter imagery paradigm using clench speed and clench force motor imagery. The time-frequency-phase features are extracted from mu rhythm and beta rhythms, and the features are optimized using three process methods: no-scaled feature using “MIFS” feature selection criterion, scaled feature using “MIFS” feature selection criterion, and scaled feature using “mRMR” feature selection criterion. Support vector machines (SVMs) and extreme learning machines (ELMs) are compared for classification between clench speed and clench force motor imagery using the optimized feature. Our results show that no significant difference in the classification rate between SVMs and ELMs is found. The scaled feature combinations can get higher classification accuracy than the no-scaled feature combinations at significant level of 0.01, and the “mRMR” feature selection criterion can get higher classification rate than the “MIFS” feature selection criterion at significant level of 0.01. The time-frequency-phase feature can improve the classification rate by about 20% more than the time-frequency feature, and the best classification rate between clench speed motor imagery and clench force motor imagery is 92%. In conclusion, the motor parameter imagery paradigm has the potential to increase the direct control commands for BCI control and the time-frequency-phase feature has the ability to improve BCI classification accuracy.
Collapse
|