Fully implanted brain-computer interfaces(BCIs)are preferred as they eliminate signal degradation caused by interference and absorption in external tissues,a common issue in non-fully implanted systems.To optimize the...Fully implanted brain-computer interfaces(BCIs)are preferred as they eliminate signal degradation caused by interference and absorption in external tissues,a common issue in non-fully implanted systems.To optimize the design of electroencephalography electrodes in fully implanted BCI systems,this study investigates the penetration and absorption characteristics of microwave signals in human brain tissue at different frequencies.Electromagnetic simulations are used to analyze the power density distribution and specific absorption rate(SAR)of signals at various frequen-cies.The results indicate that lower-frequency signals offer advantages in terms of power density and attenuation coeffi-cients.However,SAR-normalized analysis,which considers both power density and electromagnetic radiation hazards,shows that higher-frequency signals perform better at superficial to intermediate depths.Specifically,at a depth of 2 mm beneath the cortex,the power density of a 6.5 GHz signal is 247.83%higher than that of a 0.4 GHz signal.At a depth of 5 mm,the power density of a 3.5 GHz signal exceeds that of a 0.4 GHz signal by 224.16%.The findings suggest that 6.5 GHz is optimal for electrodes at a depth of 2 mm,3.5 GHz for 5 mm,2.45 GHz for depths of 15-20 mm,and 1.8 GHz for 25 mm.展开更多
BACKGROUND Brain-computer interface(BCI)technology is rapidly advancing in psychiatry.Informed consent competency(ICC)assessment among psychiatric patients is a pivotal concern in clinical research.AIM To analyze the ...BACKGROUND Brain-computer interface(BCI)technology is rapidly advancing in psychiatry.Informed consent competency(ICC)assessment among psychiatric patients is a pivotal concern in clinical research.AIM To analyze the assessment of ICC and form a framework with multi-dimensional elements involved in ICC of BCI clinical research among psychiatric disorders.METHODS A systematic review of studies regarding ICC assessments of BCI clinical research in patients with six kinds of psychiatric disorders was conducted.A systematic literature search was performed using PubMed,ScienceDirect,and Web of Science.Peer-reviewed articles and full-text studies were included in the analysis.There were no date restrictions,and all studies published up to February 27,2025,were included.RESULTS A total of 103 studies were selected for this review.Fifty-eight studies included ICC factors,and forty-five were classified in ICC related ethical issues of BCI research in six kinds of psychiatric disorders.Executive function impairment is widely recognized as the most significant factor impacting ICC,and processing speed deficits are observed in schizophrenia,mood disorders,and Alzheimer’s disease.Memory dysfunction,particularly episodic and working memory,contributes to compromised ICC.Five core ethical issues in BCI research should be addressed:BCI specificity,vulnerability,autonomy,dynamic ICC,comprehensiveness,and uncertainty.CONCLUSION A Five-Dimensional evaluative framework,including clinical,ethical,sociocultural,legal,and procedural dimensions,is constructed and proposed for future ICC research in BCI clinical research involving psychiatric disorders.展开更多
Traditional psychological treatment methods often require a long time and have limited effects.Researchers have begun to explore the combination of brain-computer interface(BCI)technology and mental health,providing n...Traditional psychological treatment methods often require a long time and have limited effects.Researchers have begun to explore the combination of brain-computer interface(BCI)technology and mental health,providing new possibilities for the treatment and rehabilitation of mental illnesses.This paper reviews the advantages,existing risks,and challenges of BCI technology in mental health treatment,and prospects the future development of research on BCI and mental health.展开更多
In recent years,with the continuous advancement of technolo-gies such as artificial intelligence,neurobiology,and sensors,braincomputer interface(Bcl)technology has embraced opportunitiesfor rapid development The"...In recent years,with the continuous advancement of technolo-gies such as artificial intelligence,neurobiology,and sensors,braincomputer interface(Bcl)technology has embraced opportunitiesfor rapid development The"Guidelines for the Establishment ofNeurological Medical Service Price ltems(Trial)"recently issued bythe National Healthcare Security Administration specifically sets upseparate prospective items for new BCl technologies,which will un-doubtedly strongly facilitate the clinical application of BCl technologyas soon as possible,benefiting a broad range of patients.展开更多
Brain-computer interface(BCI)technology is rapidly advancing in medical research and application.As an emerging biomedical engineering technology,it has garnered significant attention in the clinical research of brain...Brain-computer interface(BCI)technology is rapidly advancing in medical research and application.As an emerging biomedical engineering technology,it has garnered significant attention in the clinical research of brain disease diagnosis and treatment,neurological rehabilitation,and mental health.However,BCI also raises several challenges and ethical concerns in clinical research.In this article,the authors investigate and discuss three aspects of BCI in medicine and healthcare:the state of international ethical governance,multidimensional ethical challenges pertaining to BCI in clinical research,and suggestive concerns for ethical review.Despite the great potential of frontier BCI research and development in the field of medical care,the ethical challenges induced by itself and the complexities of clinical research and brain function have put forward new special fields for ethics in BCI.To ensure"responsible innovation"in BCI research in healthcare and medicine,the creation of an ethical global governance framework and system,along with special guidelines for cutting-edge BCI research in medicine,is suggested.展开更多
Visual fixation is an item in the visual function subscale of the Coma Recovery Scale-Revised （CRS-R）. Sometimes clinicians using the behavioral scales find it difficult to detect because of the motor impairment in ...Visual fixation is an item in the visual function subscale of the Coma Recovery Scale-Revised （CRS-R）. Sometimes clinicians using the behavioral scales find it difficult to detect because of the motor impairment in patients with disorders of consciousness （DOCs）. Brain- computer interface （BCI） can be used to improve clinical assessment because it directly detects the brain response to an external stimulus in the absence of behavioral expres- sion. In this study, we designed a BCI system to assist the visual fixation assessment of DOC patients. The results from 15 patients indicated that three showed visual fixation in both CRS-R and BCI assessments and one did not show such behavior in the CRS-R assessment but achieved significant online accuracy in the BCI assessment. The results revealed that electroencephalography-based BCI can detect the brain response for visual fixation. Therefore, the proposed BCI may provide a promising method for assisting behavioral assessment using the CRS-R.展开更多
A brain-computer interface(BCI)-based electric wheelchair control system was developed, which enables the users to move the wheelchair forward or backward, and turn left or right without any pre-learning. This control...A brain-computer interface(BCI)-based electric wheelchair control system was developed, which enables the users to move the wheelchair forward or backward, and turn left or right without any pre-learning. This control system makes use of the amplitude enhancement of alpha-wave blocking in electroencephalogram(EEG) when eyes close for more than 1 s to constitute a BCI for the switch control of wheelchair movements. The system was formed by BCI control panel, data acquisition, signal processing unit and interface control circuit. Eight volunteers participated in the wheelchair control experiments according to the preset routes. The experimental results show that the mean success control rate of all the subjects was 81.3%, with the highest reaching 93.7%. When one subject's triggering time was 2.8 s, i.e., the flashing time of each cycle light was 2.8 s, the average information transfer rate was 8.10 bit/min, with the highest reaching 12.54 bit/min.展开更多
The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal...The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal and the changes of the experimental environment make the feature distribution of the testing set and training set deviates,which reduces the classification accuracy of MI-BCI.In this paper,we propose a Kullback–Leibler divergence(KL)-based transfer learning algorithm to solve the problem of feature transfer,the proposed algorithm uses KL to measure the similarity between the training set and the testing set,adds support vector machine(SVM)classification probability to classify and weight the covariance,and discards the poorly performing samples.The results show that the proposed algorithm can significantly improve the classification accuracy of the testing set compared with the traditional algorithms,especially for subjects with medium classification accuracy.Moreover,the algorithm based on transfer learning has the potential to improve the consistency of feature distribution that the traditional algorithms do not have,which is significant for the application of MI-BCI.展开更多
In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in...In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects’ EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.展开更多
Disorders of consciousness(DoCs) are chronic conditions resulting usually from severe neurological deficits. The limitations of the existing diagnosis systems and methodologies cause a need for additional tools for re...Disorders of consciousness(DoCs) are chronic conditions resulting usually from severe neurological deficits. The limitations of the existing diagnosis systems and methodologies cause a need for additional tools for relevant patients with DoCs assessment, including brain-computer interfaces(BCIs). Recent progress in BCIs' clinical applications may offer important breakthroughs in the diagnosis and therapy of patients with DoCs. Thus the clinical significance of BCI applications in the diagnosis of patients with DoCs is hard to overestimate. One of them may be brain-computer interfaces. The aim of this study is to evaluate possibility of non-invasive EEG-based brain-computer interfaces in diagnosis of patients with DOCs in post-acute and long-term care institutions.展开更多
Brain-computer interfaces(BCI)use neural activity as a control signal to enable direct communication between the human brain and external devices.The electrical signals generated by the brain are captured through elec...Brain-computer interfaces(BCI)use neural activity as a control signal to enable direct communication between the human brain and external devices.The electrical signals generated by the brain are captured through electroencephalogram(EEG)and translated into neural intentions reflecting the user’s behavior.Correct decoding of the neural intentions then facilitates the control of external devices.Reinforcement learning-based BCIs enhance decoders to complete tasks based only on feedback signals(rewards)from the environment,building a general framework for dynamic mapping from neural intentions to actions that adapt to changing environments.However,using traditional reinforcement learning methods can have challenges such as the curse of dimensionality and poor generalization.Therefore,in this paper,we use deep reinforcement learning to construct decoders for the correct decoding of EEG signals,demonstrate its feasibility through experiments,and demonstrate its stronger generalization on motion imaging(MI)EEG data signals with high dynamic characteristics.展开更多
Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on...Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.展开更多
Abstract-Two probabilistic methods are extended to research multi-class motor imagery of brain-computer interface （BCI）： support vector machine （SVM） with posteriori probability （PSVM） and Bayesian linear discr...Abstract-Two probabilistic methods are extended to research multi-class motor imagery of brain-computer interface （BCI）： support vector machine （SVM） with posteriori probability （PSVM） and Bayesian linear discriminant analysis with probabilistic output （PBLDA）. A comparative evaluation of these two methods is conducted. The results shows that： 1） probabilistie information can improve the performance of BCI for subjects with high kappa coefficient, and 2） PSVM usually results in a stable kappa coefficient whereas PBLDA is more efficient in estimating the model parameters.展开更多
The present study utilized motor imaginary-based brain-computer interface technology combined with rehabilitation training in 20 stroke patients. Results from the Berg Balance Scale and the Holden Walking Classificati...The present study utilized motor imaginary-based brain-computer interface technology combined with rehabilitation training in 20 stroke patients. Results from the Berg Balance Scale and the Holden Walking Classification were significantly greater at 4 weeks after treatment （P 〈 0.01）, which suggested that motor imaginary-based brain-computer interface technology improved balance and walking in stroke patients.展开更多
An electroencephalogram(EEG)signal projection using kernel discriminative locality preserving canonical correlation analysis(KDLPCCA)-based correlation with steady-state visual evoked potential(SSVEP)templates for fre...An electroencephalogram(EEG)signal projection using kernel discriminative locality preserving canonical correlation analysis(KDLPCCA)-based correlation with steady-state visual evoked potential(SSVEP)templates for frequency recognition is presented in this paper.With KDLPCCA,not only a non-linear correlation but also local properties and discriminative information of each class sample are considered to extract temporal and frequency features of SSVEP signals.The new projected EEG features are classified with classical machine learning algorithms,namely,K-nearest neighbors(KNNs),naive Bayes,and random forest classifiers.To demonstrate the effectiveness of the proposed method,16-channel SSVEP data corresponding to 4 frequencies collected from 5 subjects were used to evaluate the performance.Compared with the state of the art canonical correlation analysis(CCA),experimental results show significant improvements in classification accuracy and information transfer rate(ITR),achieving 100%and 240 bits/min with 0.5 s sample block.The superior performance demonstrates that this method holds the promising potential to achieve satisfactory performance for high-accuracy SSVEP-based brain-computer interfaces.展开更多
The Brain-Computer Interfaces(BCIs)had been proposed and used in therapeutics for decades.However,the need of time-consuming calibration phase and the lack of robustness,which are caused by little-labeled data,are res...The Brain-Computer Interfaces(BCIs)had been proposed and used in therapeutics for decades.However,the need of time-consuming calibration phase and the lack of robustness,which are caused by little-labeled data,are restricting the advance and application of BCI,especially for the BCI based on motor imagery(MI).In this paper,we reviewed the recent development in the machine learning algorithm used in the MI-based BCI,which may provide potential solutions for addressing the issue.We classified these algorithms into two categories,namely,and enhancing the representation and expanding the training set.Specifically,these methods of enhancing the representation of features collected from few EEG trials are based on extracting features of multiple bands,regularization,and so on.The methods of expanding the training dataset include approaches of transfer learning(session to session transfer,subject to subject transfer)and generating artificial EEG data.The result of these techniques showed the resolution of the challenges to some extent.As a developing research area,the study of BCI algorithms in little-labeled data is increasingly requiring the advancement of human brain physiological structure research and more transfer learning algorithms research.展开更多
As a non-invasive neurophysiologieal index for brain-computer interface （BCI）, electroencephalogram （EEG） attracts much attention at present. In order to have a portable BCI, a simple and efficient pre-amplifier i...As a non-invasive neurophysiologieal index for brain-computer interface （BCI）, electroencephalogram （EEG） attracts much attention at present. In order to have a portable BCI, a simple and efficient pre-amplifier is crucial in practice. In this work, a preamplifier based on the characteristics of EEG signals is designed, which consists of a highly symmetrical input stage, low-pass filter, 50 Hz notch filter and a post amplifier. A prototype of this EEG module is fabricated and EEG data are obtained through an actual experiment. The results demonstrate that the EEG preamplifier will be a promising unit for BCI in the future.展开更多
Accurate classification of EEG left and right hand motor imagery is an important issue in brain-computer interface. Firstly, discrete wavelet transform method was used to decompose the average power of C3 electrode an...Accurate classification of EEG left and right hand motor imagery is an important issue in brain-computer interface. Firstly, discrete wavelet transform method was used to decompose the average power of C3 electrode and C4 electrode in left-right hands imagery movement during some periods of time. The reconstructed signal of approximation coefficient A6 on the 6al level was selected to build up a feature signal. Secondly, the performances by Fisher Linear Discriminant Analysis with two different threshold calculation ways and Support Vector Machine methods were compared. The final classification results showed that false classification rate by Support Vector Machine was lower and gained an ideal classification results.展开更多
Brain-Computer interfacing(BCI)has currently added a new dimension in assistive robotics.Existing braincomputer interfaces designed for position control applications suffer from two fundamental limitations.First,most ...Brain-Computer interfacing(BCI)has currently added a new dimension in assistive robotics.Existing braincomputer interfaces designed for position control applications suffer from two fundamental limitations.First,most of the existing schemes employ open-loop control,and thus are unable to track positional errors,resulting in failures in taking necessary online corrective actions.There are examples of a few works dealing with closed-loop electroencephalography(EEG)-based position control.These existing closed-loop brain-induced position control schemes employ a fixed order link selection rule,which often creates a bottleneck preventing time-efficient control.Second,the existing brain-induced position controllers are designed to generate a position response like a traditional firstorder system,resulting in a large steady-state error.This paper overcomes the above two limitations by keeping provisions for steady-state visual evoked potential(SSVEP)induced linkselection in an arbitrary order as required for efficient control and generating a second-order response of the position-control system with gradually diminishing overshoots/undershoots to reduce steady-state errors.Other than the above,the third innovation is to utilize motor imagery and P300 signals to design the hybrid brain-computer interfacing system for the said application with gradually diminishing error-margin using speed reversal at the zero-crossings of positional errors.Experiments undertaken reveal that the steady-state error is reduced to 0.2%.The paper also provides a thorough analysis of the stability of the closed-loop system performance using the Root Locus technique.展开更多
基金The Open Project of State Key Laboratory of Smart Grid Protection and Operation Control in 2022(No.SGNR0000KJJS2302150).
文摘Fully implanted brain-computer interfaces(BCIs)are preferred as they eliminate signal degradation caused by interference and absorption in external tissues,a common issue in non-fully implanted systems.To optimize the design of electroencephalography electrodes in fully implanted BCI systems,this study investigates the penetration and absorption characteristics of microwave signals in human brain tissue at different frequencies.Electromagnetic simulations are used to analyze the power density distribution and specific absorption rate(SAR)of signals at various frequen-cies.The results indicate that lower-frequency signals offer advantages in terms of power density and attenuation coeffi-cients.However,SAR-normalized analysis,which considers both power density and electromagnetic radiation hazards,shows that higher-frequency signals perform better at superficial to intermediate depths.Specifically,at a depth of 2 mm beneath the cortex,the power density of a 6.5 GHz signal is 247.83%higher than that of a 0.4 GHz signal.At a depth of 5 mm,the power density of a 3.5 GHz signal exceeds that of a 0.4 GHz signal by 224.16%.The findings suggest that 6.5 GHz is optimal for electrodes at a depth of 2 mm,3.5 GHz for 5 mm,2.45 GHz for depths of 15-20 mm,and 1.8 GHz for 25 mm.
基金Supported by the Ministry of Science and Technology of the People's Republic of China(2021ZD0201900)Project 5,No.2021ZD0201905Capital’s Funds for Health Improvement and Research,No.CFH 2022-2-4115.
文摘BACKGROUND Brain-computer interface(BCI)technology is rapidly advancing in psychiatry.Informed consent competency(ICC)assessment among psychiatric patients is a pivotal concern in clinical research.AIM To analyze the assessment of ICC and form a framework with multi-dimensional elements involved in ICC of BCI clinical research among psychiatric disorders.METHODS A systematic review of studies regarding ICC assessments of BCI clinical research in patients with six kinds of psychiatric disorders was conducted.A systematic literature search was performed using PubMed,ScienceDirect,and Web of Science.Peer-reviewed articles and full-text studies were included in the analysis.There were no date restrictions,and all studies published up to February 27,2025,were included.RESULTS A total of 103 studies were selected for this review.Fifty-eight studies included ICC factors,and forty-five were classified in ICC related ethical issues of BCI research in six kinds of psychiatric disorders.Executive function impairment is widely recognized as the most significant factor impacting ICC,and processing speed deficits are observed in schizophrenia,mood disorders,and Alzheimer’s disease.Memory dysfunction,particularly episodic and working memory,contributes to compromised ICC.Five core ethical issues in BCI research should be addressed:BCI specificity,vulnerability,autonomy,dynamic ICC,comprehensiveness,and uncertainty.CONCLUSION A Five-Dimensional evaluative framework,including clinical,ethical,sociocultural,legal,and procedural dimensions,is constructed and proposed for future ICC research in BCI clinical research involving psychiatric disorders.
文摘Traditional psychological treatment methods often require a long time and have limited effects.Researchers have begun to explore the combination of brain-computer interface(BCI)technology and mental health,providing new possibilities for the treatment and rehabilitation of mental illnesses.This paper reviews the advantages,existing risks,and challenges of BCI technology in mental health treatment,and prospects the future development of research on BCI and mental health.
文摘In recent years,with the continuous advancement of technolo-gies such as artificial intelligence,neurobiology,and sensors,braincomputer interface(Bcl)technology has embraced opportunitiesfor rapid development The"Guidelines for the Establishment ofNeurological Medical Service Price ltems(Trial)"recently issued bythe National Healthcare Security Administration specifically sets upseparate prospective items for new BCl technologies,which will un-doubtedly strongly facilitate the clinical application of BCl technologyas soon as possible,benefiting a broad range of patients.
基金supported by the Ministry of Science and Tech-nology of the People's Republic of China(2021ZD0201900),Project 5(2021ZD0201905).
文摘Brain-computer interface(BCI)technology is rapidly advancing in medical research and application.As an emerging biomedical engineering technology,it has garnered significant attention in the clinical research of brain disease diagnosis and treatment,neurological rehabilitation,and mental health.However,BCI also raises several challenges and ethical concerns in clinical research.In this article,the authors investigate and discuss three aspects of BCI in medicine and healthcare:the state of international ethical governance,multidimensional ethical challenges pertaining to BCI in clinical research,and suggestive concerns for ethical review.Despite the great potential of frontier BCI research and development in the field of medical care,the ethical challenges induced by itself and the complexities of clinical research and brain function have put forward new special fields for ethics in BCI.To ensure"responsible innovation"in BCI research in healthcare and medicine,the creation of an ethical global governance framework and system,along with special guidelines for cutting-edge BCI research in medicine,is suggested.
基金supported by the National Key Research and Development Program of China (2017YFB1002505)the National Natural Science Foundation of China (61633010, 91420302, and 61503143)+1 种基金the Natural Science Foundation of Guangdong Province, China (2014A030312005 and 2014A030310244)the Pearl River S&T Nova Program of Guangzhou Municipality, China (201710010038)
文摘Visual fixation is an item in the visual function subscale of the Coma Recovery Scale-Revised （CRS-R）. Sometimes clinicians using the behavioral scales find it difficult to detect because of the motor impairment in patients with disorders of consciousness （DOCs）. Brain- computer interface （BCI） can be used to improve clinical assessment because it directly detects the brain response to an external stimulus in the absence of behavioral expres- sion. In this study, we designed a BCI system to assist the visual fixation assessment of DOC patients. The results from 15 patients indicated that three showed visual fixation in both CRS-R and BCI assessments and one did not show such behavior in the CRS-R assessment but achieved significant online accuracy in the BCI assessment. The results revealed that electroencephalography-based BCI can detect the brain response for visual fixation. Therefore, the proposed BCI may provide a promising method for assisting behavioral assessment using the CRS-R.
基金Supported by the National Natural Science Foundation of China(No.81222021,No.30970875,No.90920015,No.61172008 and No.81171423)National Key Technology Research and Development Program of the Ministry of Science and Technology of China(No.2012BAI34B02)Program for New Century Excellent Talents in University of the Ministry of Education of China(No.NCET-10-0618)
文摘A brain-computer interface(BCI)-based electric wheelchair control system was developed, which enables the users to move the wheelchair forward or backward, and turn left or right without any pre-learning. This control system makes use of the amplitude enhancement of alpha-wave blocking in electroencephalogram(EEG) when eyes close for more than 1 s to constitute a BCI for the switch control of wheelchair movements. The system was formed by BCI control panel, data acquisition, signal processing unit and interface control circuit. Eight volunteers participated in the wheelchair control experiments according to the preset routes. The experimental results show that the mean success control rate of all the subjects was 81.3%, with the highest reaching 93.7%. When one subject's triggering time was 2.8 s, i.e., the flashing time of each cycle light was 2.8 s, the average information transfer rate was 8.10 bit/min, with the highest reaching 12.54 bit/min.
文摘The non-stationary of the motor imagery electroencephalography(MI-EEG)signal is one of the main limitations for the development of motor imagery brain-computer interfaces(MI-BCI).The nonstationary of the MI-EEG signal and the changes of the experimental environment make the feature distribution of the testing set and training set deviates,which reduces the classification accuracy of MI-BCI.In this paper,we propose a Kullback–Leibler divergence(KL)-based transfer learning algorithm to solve the problem of feature transfer,the proposed algorithm uses KL to measure the similarity between the training set and the testing set,adds support vector machine(SVM)classification probability to classify and weight the covariance,and discards the poorly performing samples.The results show that the proposed algorithm can significantly improve the classification accuracy of the testing set compared with the traditional algorithms,especially for subjects with medium classification accuracy.Moreover,the algorithm based on transfer learning has the potential to improve the consistency of feature distribution that the traditional algorithms do not have,which is significant for the application of MI-BCI.
文摘In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects’ EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.
文摘Disorders of consciousness(DoCs) are chronic conditions resulting usually from severe neurological deficits. The limitations of the existing diagnosis systems and methodologies cause a need for additional tools for relevant patients with DoCs assessment, including brain-computer interfaces(BCIs). Recent progress in BCIs' clinical applications may offer important breakthroughs in the diagnosis and therapy of patients with DoCs. Thus the clinical significance of BCI applications in the diagnosis of patients with DoCs is hard to overestimate. One of them may be brain-computer interfaces. The aim of this study is to evaluate possibility of non-invasive EEG-based brain-computer interfaces in diagnosis of patients with DOCs in post-acute and long-term care institutions.
文摘Brain-computer interfaces(BCI)use neural activity as a control signal to enable direct communication between the human brain and external devices.The electrical signals generated by the brain are captured through electroencephalogram(EEG)and translated into neural intentions reflecting the user’s behavior.Correct decoding of the neural intentions then facilitates the control of external devices.Reinforcement learning-based BCIs enhance decoders to complete tasks based only on feedback signals(rewards)from the environment,building a general framework for dynamic mapping from neural intentions to actions that adapt to changing environments.However,using traditional reinforcement learning methods can have challenges such as the curse of dimensionality and poor generalization.Therefore,in this paper,we use deep reinforcement learning to construct decoders for the correct decoding of EEG signals,demonstrate its feasibility through experiments,and demonstrate its stronger generalization on motion imaging(MI)EEG data signals with high dynamic characteristics.
基金supported by the National Natural Science Foundation of China under Grant No. 30525030, 60701015, and 60736029.
文摘Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.
基金supported by the National Natural Science Foundation of China under Grant No. 30525030, 60701015, and 60736029.
文摘Abstract-Two probabilistic methods are extended to research multi-class motor imagery of brain-computer interface （BCI）： support vector machine （SVM） with posteriori probability （PSVM） and Bayesian linear discriminant analysis with probabilistic output （PBLDA）. A comparative evaluation of these two methods is conducted. The results shows that： 1） probabilistie information can improve the performance of BCI for subjects with high kappa coefficient, and 2） PSVM usually results in a stable kappa coefficient whereas PBLDA is more efficient in estimating the model parameters.
基金the National Natural Science Foundation of China,No.60970062the Shanghai Pujiang Program,No.09PJ1410200
文摘The present study utilized motor imaginary-based brain-computer interface technology combined with rehabilitation training in 20 stroke patients. Results from the Berg Balance Scale and the Holden Walking Classification were significantly greater at 4 weeks after treatment （P 〈 0.01）, which suggested that motor imaginary-based brain-computer interface technology improved balance and walking in stroke patients.
基金the National Natural Science Foundation of China(Nos.61702395 and 61972302)the Science and Technology Projects of Xi’an,China(No.201809170CX11JC12)。
文摘An electroencephalogram(EEG)signal projection using kernel discriminative locality preserving canonical correlation analysis(KDLPCCA)-based correlation with steady-state visual evoked potential(SSVEP)templates for frequency recognition is presented in this paper.With KDLPCCA,not only a non-linear correlation but also local properties and discriminative information of each class sample are considered to extract temporal and frequency features of SSVEP signals.The new projected EEG features are classified with classical machine learning algorithms,namely,K-nearest neighbors(KNNs),naive Bayes,and random forest classifiers.To demonstrate the effectiveness of the proposed method,16-channel SSVEP data corresponding to 4 frequencies collected from 5 subjects were used to evaluate the performance.Compared with the state of the art canonical correlation analysis(CCA),experimental results show significant improvements in classification accuracy and information transfer rate(ITR),achieving 100%and 240 bits/min with 0.5 s sample block.The superior performance demonstrates that this method holds the promising potential to achieve satisfactory performance for high-accuracy SSVEP-based brain-computer interfaces.
文摘The Brain-Computer Interfaces(BCIs)had been proposed and used in therapeutics for decades.However,the need of time-consuming calibration phase and the lack of robustness,which are caused by little-labeled data,are restricting the advance and application of BCI,especially for the BCI based on motor imagery(MI).In this paper,we reviewed the recent development in the machine learning algorithm used in the MI-based BCI,which may provide potential solutions for addressing the issue.We classified these algorithms into two categories,namely,and enhancing the representation and expanding the training set.Specifically,these methods of enhancing the representation of features collected from few EEG trials are based on extracting features of multiple bands,regularization,and so on.The methods of expanding the training dataset include approaches of transfer learning(session to session transfer,subject to subject transfer)and generating artificial EEG data.The result of these techniques showed the resolution of the challenges to some extent.As a developing research area,the study of BCI algorithms in little-labeled data is increasingly requiring the advancement of human brain physiological structure research and more transfer learning algorithms research.
基金supported by the National Natural Science Foundation of China under Grant No. 60571019the University of Electronic Science and Technology of China Youth Foundation under Grant No. L08010901JX0772.
文摘As a non-invasive neurophysiologieal index for brain-computer interface （BCI）, electroencephalogram （EEG） attracts much attention at present. In order to have a portable BCI, a simple and efficient pre-amplifier is crucial in practice. In this work, a preamplifier based on the characteristics of EEG signals is designed, which consists of a highly symmetrical input stage, low-pass filter, 50 Hz notch filter and a post amplifier. A prototype of this EEG module is fabricated and EEG data are obtained through an actual experiment. The results demonstrate that the EEG preamplifier will be a promising unit for BCI in the future.
基金The Open Project of the State Key Laboratory of Robotics and System (HIT)the State Key Laboratory of Cognitive Neuroscience and Learning+3 种基金Natural Science Fund for Colleges and Universities in Jiangsu Provincegrant number:105TB51003Natural Science Fund in Changzhougrant number:CJ20110023
文摘Accurate classification of EEG left and right hand motor imagery is an important issue in brain-computer interface. Firstly, discrete wavelet transform method was used to decompose the average power of C3 electrode and C4 electrode in left-right hands imagery movement during some periods of time. The reconstructed signal of approximation coefficient A6 on the 6al level was selected to build up a feature signal. Secondly, the performances by Fisher Linear Discriminant Analysis with two different threshold calculation ways and Support Vector Machine methods were compared. The final classification results showed that false classification rate by Support Vector Machine was lower and gained an ideal classification results.
文摘Brain-Computer interfacing(BCI)has currently added a new dimension in assistive robotics.Existing braincomputer interfaces designed for position control applications suffer from two fundamental limitations.First,most of the existing schemes employ open-loop control,and thus are unable to track positional errors,resulting in failures in taking necessary online corrective actions.There are examples of a few works dealing with closed-loop electroencephalography(EEG)-based position control.These existing closed-loop brain-induced position control schemes employ a fixed order link selection rule,which often creates a bottleneck preventing time-efficient control.Second,the existing brain-induced position controllers are designed to generate a position response like a traditional firstorder system,resulting in a large steady-state error.This paper overcomes the above two limitations by keeping provisions for steady-state visual evoked potential(SSVEP)induced linkselection in an arbitrary order as required for efficient control and generating a second-order response of the position-control system with gradually diminishing overshoots/undershoots to reduce steady-state errors.Other than the above,the third innovation is to utilize motor imagery and P300 signals to design the hybrid brain-computer interfacing system for the said application with gradually diminishing error-margin using speed reversal at the zero-crossings of positional errors.Experiments undertaken reveal that the steady-state error is reduced to 0.2%.The paper also provides a thorough analysis of the stability of the closed-loop system performance using the Root Locus technique.
