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
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
Transfer learning,as a new machine learning methodology,may solve problems in related but different domains by using existing knowledge,and it is often applied to transfer training data from another domain for model t...Transfer learning,as a new machine learning methodology,may solve problems in related but different domains by using existing knowledge,and it is often applied to transfer training data from another domain for model training in the case of insuficient training data.In recent years,an increasing number of researchers who engage in brain-computer interface(BCI),have focused on using transfer learning to make most of the available electroencephalogram data from different subjects,effectively reducing the cost of expensive data acquisition and labeling as well as greatly improving the learning performance of the model.This paper surveys the development of transfer learning and reviews the transfer learning approaches in BCI.In addition,according to the"what to transfer"question in transfer learning,this review is organized into three contexts:instance-based transfer learning,parameter-based transfer learning,and feature-based transfer learning.Furthermore,the current transfer learning applications in BCI research are summarized in terms of the transfer learning methods,datasets,evaluation performance,etc.At the end of the paper,the questions to be solved in future research are put forward,laying the foundation for the popularization and in-depth research of transfer learning in BCI.展开更多
Brain-computer interface (BCI) is a communication system that can help lock-in patients to interact with the outside environment by translating brain signals into machine commands.The present work provides a design fo...Brain-computer interface (BCI) is a communication system that can help lock-in patients to interact with the outside environment by translating brain signals into machine commands.The present work provides a design for a virtual reality (VR) based BCI system that allows human participants to control a virtual hand to make gestures by P300 signals,with a positive peak of potential about 300 ms posterior to the onset of target stimulus.In this virtual environment,the participants can obtain a more immersed experience with the BCI system,such as controlling a virtual hand or walking around in the virtual world.Methods of modeling the virtual hand and analyzing the P300 signals are also described in detail.Template matching and support vector machine were used as the P300 classifier and the experiment results showed that both algorithms perform well in the system.After a short time of practice,most participants could learn to control the virtual hand during the online experiment with greater than 70% accuracy.展开更多
This paper presents a hybrid brain-computer interface (BCI) control strategy,the goal of which is to expand control functions of a conventional motor imagery or a P300 potential based BCI in a virtual environment.The ...This paper presents a hybrid brain-computer interface (BCI) control strategy,the goal of which is to expand control functions of a conventional motor imagery or a P300 potential based BCI in a virtual environment.The hybrid control strategy utilizes P300 potential to control virtual devices and motor imagery related sensorimotor rhythms to navigate in the virtual world.The two electroencephalography (EEG) patterns serve as source signals for different control functions in their corresponding system states,and state switch is achieved in a sequential manner.In the current system,imagination of left/right hand movement was translated into turning left/right in the virtual apartment continuously,while P300 potentials were mapped to discrete virtual device control commands using a five-oddball paradigm.The combination of motor imagery and P300 patterns in one BCI system for virtual environment control was tested and the results were compared with those of a single motor imagery or P300-based BCI.Subjects obtained similar performances in the hybrid and single control tasks,which indicates the hybrid control strategy works well in the virtual environment.展开更多
The advancement in neuroscience and computer science promotes the ability of the human brain to communicate and interact with the environment,making brain–computer interface(BCI)top interdisciplinary research.Further...The advancement in neuroscience and computer science promotes the ability of the human brain to communicate and interact with the environment,making brain–computer interface(BCI)top interdisciplinary research.Furthermore,with the modern technology advancement in artificial intelligence(AI),including machine learning(ML)and deep learning(DL)methods,there is vast growing interest in the electroencephalogram(EEG)-based BCIs for AI-related visual,literal,and motion applications.In this review study,the literature on mainstreams of AI for the EEG-based BCI applications is investigated to fill gaps in the interdisciplinary BCI field.Specifically,the EEG signals and their main applications in BCI are first briefly introduced.Next,the latest AI technologies,including the ML and DL models,are presented to monitor and feedback human cognitive states.Finally,some BCI-inspired AI applications,including computer vision,natural language processing,and robotic control applications,are presented.The future research directions of the EEG-based BCI are highlighted in line with the AI technologies and applications.展开更多
Background As a novel approach for people to directly communicate with an external device,the study of brain-computer interfaces(BCIs)has become well-rounded.However,similar to the real-world scenario,where individual...Background As a novel approach for people to directly communicate with an external device,the study of brain-computer interfaces(BCIs)has become well-rounded.However,similar to the real-world scenario,where individuals are expected to work in groups,the BCI systems should be able to replicate group attributes.Methods We proposed a 4-order cumulants feature extraction method(CUM4-CSP)based on the common spatial patterns(CSP)algorithm.Simulation experiments conducted using motion visual evoked potentials(mVEP)EEG data verified the robustness of the proposed algorithm.In addition,to freely choose paradigms,we adopted the mVEP and steady-state visual evoked potential(SSVEP)paradigms and designed a multimodal collaborative BCI system based on the proposed CUM4-CSP algorithm.The feasibility of the proposed multimodal collaborative system framework was demonstrated using a multiplayer game controlling system that simultaneously facilitates the coordination and competitive control of two users on external devices.To verify the robustness of the proposed scheme,we recruited 30 subjects to conduct online game control experiments,and the results were statistically analyzed.Results The simulation results prove that the proposed CUM4-CSP algorithm has good noise immunity.The online experimental results indicate that the subjects could reliably perform the game confrontation operation with the selected BCI paradigm.Conclusions The proposed CUM4-CSP algorithm can effectively extract features from EEG data in a noisy environment.Additionally,the proposed scheme may provide a new solution for EEG-based group BCI research.展开更多
The paper introduces an electroencephalography(EEG) driven online position control scheme for a robot arm by utilizing motor imagery to activate and error related potential(ErrP) to stop the movement of the individual...The paper introduces an electroencephalography(EEG) driven online position control scheme for a robot arm by utilizing motor imagery to activate and error related potential(ErrP) to stop the movement of the individual links, following a fixed(pre-defined) order of link selection. The right(left)hand motor imagery is used to turn a link clockwise(counterclockwise) and foot imagery is used to move a link forward. The occurrence of ErrP here indicates that the link under motion crosses the visually fixed target position, which usually is a plane/line/point depending on the desired transition of the link across 3D planes/around 2D lines/along 2D lines respectively. The imagined task about individual link's movement is decoded by a classifier into three possible class labels: clockwise, counterclockwise and no movement in case of rotational movements and forward, backward and no movement in case of translational movements. One additional classifier is required to detect the occurrence of the ErrP signal, elicited due to visually inspired positional link error with reference to a geometrically selected target position. Wavelet coefficients and adaptive autoregressive parameters are extracted as features for motor imagery and ErrP signals respectively. Support vector machine classifiers are used to decode motor imagination and ErrP with high classification accuracy above 80%. The average time taken by the proposed scheme to decode and execute control intentions for the complete movement of three links of a robot is approximately33 seconds. The steady-state error and peak overshoot of the proposed controller are experimentally obtained as 1.1% and4.6% respectively.展开更多
With the development of human-computer interaction technology,brain-computer interface(BCI)has been widely used in medical,entertainment,military,and other fields.Imagined speech is the latest paradigm of BCI and repr...With the development of human-computer interaction technology,brain-computer interface(BCI)has been widely used in medical,entertainment,military,and other fields.Imagined speech is the latest paradigm of BCI and represents the mental process of imagining a word without making a sound or making clear facial movements.Imagined speech allows patients with physical disabilities to communicate with the outside world and use smart devices through imagination.Imagined speech can meet the needs of more complex manipulative tasks considering its more intuitive features.This study proposes a classification method of imagined speech Electroencephalogram(EEG)signals with discrete wavelet transform(DWT)and support vector machine(SVM).An open dataset that consists of 15 subjects imagining speaking six different words,namely,up,down,left,right,backward,and forward,is used.The objective is to improve the classification accuracy of imagined speech BCI system.The features of EEG signals are first extracted by DWT,and the imagined words are clas-sified by SVM with the above features.Experimental results show that the proposed method achieves an average accuracy of 61.69%,which is better than those of existing methods for classifying imagined speech tasks.展开更多
Although notable progress has been made in the study of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI),several factors that limit the practical applications of BCIs still exist.One of ...Although notable progress has been made in the study of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI),several factors that limit the practical applications of BCIs still exist.One of these factors is the importability of the stimulator.In this study,Augmented Reality(AR)technology was introduced to present the visual stimuli of SSVEP-BCI,while the robot grasping experiment was designed to verify the applicability of the AR-BCI system.The offline experiment was designed to determine the best stimulus time,while the online experiment was used to complete the robot grasping task.The offline experiment revealed that better information transfer rate performance could be achieved when the stimulation time is 2 s.Results of the online experiment indicate that all 12 subjects could control the robot to complete the robot grasping task,which indicates the applicability of the AR-SSVEP-humanoid robot(NAO)system.This study verified the reliability of the AR-BCI system and indicated the applicability of the AR-SSVEP-NAO system in robot grasping tasks.展开更多
Mental task classification is one of the most important problems in Brain-computer interface.This paper studies the classification of five-class mental tasks.The nonlinear parameter of mean period obtained from freque...Mental task classification is one of the most important problems in Brain-computer interface.This paper studies the classification of five-class mental tasks.The nonlinear parameter of mean period obtained from frequency domain information was used as features for classification implemented by using the method of SVM(support vector machines).The averaged classification accuracy of 85.6% over 7 subjects was achieved for 2-second EEG segments.And the results for EEG segments of 0.5s and 5.0s compared favorably to those of Garrett’s.The results indicate that the parameter of mean period represents mental tasks well for classification.Furthermore,the method of mean period is less computationally demanding,which indicates its potential use for online BCI systems.展开更多
The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with co...The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with continuous physiotherapy as these diseases can be eased within the initial stages of the symptoms.So far,the popular control system for robot-assisted rehabilitation devices is only of two types which consist of passive and active devices.However,if there is a control system that can directly detect the motor functions,it will induce neuroplasticity to facilitate early motor recovery.In this paper,the control system,which is a motor recovery system with the intent of rehabilitation,focuses on the hand organs and utilizes a brain-computer interface(BCI)technology.The final results depict that the brainwave detection for controlling pneumatic glove in real-time has an accuracy up to 82%.Moreover,the motor recovery system enables the feasibility of brainwave classification from the motor cortex with Artificial Neural Networks(ANN).The overall model performance reveals an accuracy up to 96.56%with sensitivity of 94.22%and specificity of 98.8%.Therefore,the proposed system increases the efficiency of the traditional device control system and tends to provide a better rehabilitation than the traditional physiotherapy alone.展开更多
In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prol...In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover,this study designed a transfer-extended Canonical Correlation Analysis(t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies,t-eCCA obtained an average accuracy of 86.96%˙12.87% across 12 subjects using only half of the calibration time,which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis(88.32%±13.97%) and task-related component analysis(88.92%±14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis(CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.展开更多
With the development of deep learning, many motor imagerybrain-computer interfaces based on convolutional neural networks(CNNs) show outstanding performances. However, the trial number ofEEG in the training set is usu...With the development of deep learning, many motor imagerybrain-computer interfaces based on convolutional neural networks(CNNs) show outstanding performances. However, the trial number ofEEG in the training set is usually limited, and redundancy extensivelyexists in multiple channel EEG. Thus, overfitting often appears in CNNbased motor imagery recognition model and greatly affects the performancesof model. In this paper, channel drop out is proposed to addressthis problem by data augmentation and ensemble learning. Specifically,one of all EEG channels will be dropped and replaced by the mean signalof all EEG channels. In this way, the trial number in the training setwas enlarged by channel drop out. And at the testing stage, all the EEGtrials processed by channel drop out were fed to the CNN model and theaverage output probabilities of them were applied to determine the prediction.The experiments were conducted on two popular CNN modelsapplied in motor imagery BCI and BCI Competition IV datasets 2a toverify the performances of the proposed channel drop out approach. Theresults show that average improvements provided by channel drop outin two-category or four-category motor imagery classification are 2.83%and 2.65% compared with the original CNN model. So the channel dropout approach significantly improves the performances of motor imagerybased BCI.展开更多
A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their...A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.展开更多
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.
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.
基金the National Natural Science Foundation of China(Nos.11832003 and 81471770)the Natural Science Foundation of Beijing(No.4182009)。
文摘Transfer learning,as a new machine learning methodology,may solve problems in related but different domains by using existing knowledge,and it is often applied to transfer training data from another domain for model training in the case of insuficient training data.In recent years,an increasing number of researchers who engage in brain-computer interface(BCI),have focused on using transfer learning to make most of the available electroencephalogram data from different subjects,effectively reducing the cost of expensive data acquisition and labeling as well as greatly improving the learning performance of the model.This paper surveys the development of transfer learning and reviews the transfer learning approaches in BCI.In addition,according to the"what to transfer"question in transfer learning,this review is organized into three contexts:instance-based transfer learning,parameter-based transfer learning,and feature-based transfer learning.Furthermore,the current transfer learning applications in BCI research are summarized in terms of the transfer learning methods,datasets,evaluation performance,etc.At the end of the paper,the questions to be solved in future research are put forward,laying the foundation for the popularization and in-depth research of transfer learning in BCI.
基金Project supported by the National Natural Science Foundation of China (No.60873125)the National Institute of Biomedical Imaging and Bioengineering (No.1R03EB008235-01A1)+1 种基金the Shanghai Commission of Science and Technology (No.10440710200)the Fundamental Research Funds for the Central Universities
文摘Brain-computer interface (BCI) is a communication system that can help lock-in patients to interact with the outside environment by translating brain signals into machine commands.The present work provides a design for a virtual reality (VR) based BCI system that allows human participants to control a virtual hand to make gestures by P300 signals,with a positive peak of potential about 300 ms posterior to the onset of target stimulus.In this virtual environment,the participants can obtain a more immersed experience with the BCI system,such as controlling a virtual hand or walking around in the virtual world.Methods of modeling the virtual hand and analyzing the P300 signals are also described in detail.Template matching and support vector machine were used as the P300 classifier and the experiment results showed that both algorithms perform well in the system.After a short time of practice,most participants could learn to control the virtual hand during the online experiment with greater than 70% accuracy.
基金supported by the National Natural Science Foundation of China (Nos.30800287,60703038,60873125,61001172,and 61031002)the Zhejiang Provincial Natural Science Foundation of China (No.Y2090707)the Fundamental Research Funds for the Central Universities of China
文摘This paper presents a hybrid brain-computer interface (BCI) control strategy,the goal of which is to expand control functions of a conventional motor imagery or a P300 potential based BCI in a virtual environment.The hybrid control strategy utilizes P300 potential to control virtual devices and motor imagery related sensorimotor rhythms to navigate in the virtual world.The two electroencephalography (EEG) patterns serve as source signals for different control functions in their corresponding system states,and state switch is achieved in a sequential manner.In the current system,imagination of left/right hand movement was translated into turning left/right in the virtual apartment continuously,while P300 potentials were mapped to discrete virtual device control commands using a five-oddball paradigm.The combination of motor imagery and P300 patterns in one BCI system for virtual environment control was tested and the results were compared with those of a single motor imagery or P300-based BCI.Subjects obtained similar performances in the hybrid and single control tasks,which indicates the hybrid control strategy works well in the virtual environment.
文摘The advancement in neuroscience and computer science promotes the ability of the human brain to communicate and interact with the environment,making brain–computer interface(BCI)top interdisciplinary research.Furthermore,with the modern technology advancement in artificial intelligence(AI),including machine learning(ML)and deep learning(DL)methods,there is vast growing interest in the electroencephalogram(EEG)-based BCIs for AI-related visual,literal,and motion applications.In this review study,the literature on mainstreams of AI for the EEG-based BCI applications is investigated to fill gaps in the interdisciplinary BCI field.Specifically,the EEG signals and their main applications in BCI are first briefly introduced.Next,the latest AI technologies,including the ML and DL models,are presented to monitor and feedback human cognitive states.Finally,some BCI-inspired AI applications,including computer vision,natural language processing,and robotic control applications,are presented.The future research directions of the EEG-based BCI are highlighted in line with the AI technologies and applications.
基金Supported by the National Natural Science Foundation of China(U19A2082,61961160705,61901077)the National Key Research and Development Plan of China(2017YFB1002501)the Key R&D Program of Guangdong Province,China(2018B030339001).
文摘Background As a novel approach for people to directly communicate with an external device,the study of brain-computer interfaces(BCIs)has become well-rounded.However,similar to the real-world scenario,where individuals are expected to work in groups,the BCI systems should be able to replicate group attributes.Methods We proposed a 4-order cumulants feature extraction method(CUM4-CSP)based on the common spatial patterns(CSP)algorithm.Simulation experiments conducted using motion visual evoked potentials(mVEP)EEG data verified the robustness of the proposed algorithm.In addition,to freely choose paradigms,we adopted the mVEP and steady-state visual evoked potential(SSVEP)paradigms and designed a multimodal collaborative BCI system based on the proposed CUM4-CSP algorithm.The feasibility of the proposed multimodal collaborative system framework was demonstrated using a multiplayer game controlling system that simultaneously facilitates the coordination and competitive control of two users on external devices.To verify the robustness of the proposed scheme,we recruited 30 subjects to conduct online game control experiments,and the results were statistically analyzed.Results The simulation results prove that the proposed CUM4-CSP algorithm has good noise immunity.The online experimental results indicate that the subjects could reliably perform the game confrontation operation with the selected BCI paradigm.Conclusions The proposed CUM4-CSP algorithm can effectively extract features from EEG data in a noisy environment.Additionally,the proposed scheme may provide a new solution for EEG-based group BCI research.
基金supported by UGC Sponsored UPE-ⅡProject in Cognitive Science of Jadavpur University,Kolkata
文摘The paper introduces an electroencephalography(EEG) driven online position control scheme for a robot arm by utilizing motor imagery to activate and error related potential(ErrP) to stop the movement of the individual links, following a fixed(pre-defined) order of link selection. The right(left)hand motor imagery is used to turn a link clockwise(counterclockwise) and foot imagery is used to move a link forward. The occurrence of ErrP here indicates that the link under motion crosses the visually fixed target position, which usually is a plane/line/point depending on the desired transition of the link across 3D planes/around 2D lines/along 2D lines respectively. The imagined task about individual link's movement is decoded by a classifier into three possible class labels: clockwise, counterclockwise and no movement in case of rotational movements and forward, backward and no movement in case of translational movements. One additional classifier is required to detect the occurrence of the ErrP signal, elicited due to visually inspired positional link error with reference to a geometrically selected target position. Wavelet coefficients and adaptive autoregressive parameters are extracted as features for motor imagery and ErrP signals respectively. Support vector machine classifiers are used to decode motor imagination and ErrP with high classification accuracy above 80%. The average time taken by the proposed scheme to decode and execute control intentions for the complete movement of three links of a robot is approximately33 seconds. The steady-state error and peak overshoot of the proposed controller are experimentally obtained as 1.1% and4.6% respectively.
基金supported in part by the Fundamental Research Funds for the Central Universities(xcxjh20210104).
文摘With the development of human-computer interaction technology,brain-computer interface(BCI)has been widely used in medical,entertainment,military,and other fields.Imagined speech is the latest paradigm of BCI and represents the mental process of imagining a word without making a sound or making clear facial movements.Imagined speech allows patients with physical disabilities to communicate with the outside world and use smart devices through imagination.Imagined speech can meet the needs of more complex manipulative tasks considering its more intuitive features.This study proposes a classification method of imagined speech Electroencephalogram(EEG)signals with discrete wavelet transform(DWT)and support vector machine(SVM).An open dataset that consists of 15 subjects imagining speaking six different words,namely,up,down,left,right,backward,and forward,is used.The objective is to improve the classification accuracy of imagined speech BCI system.The features of EEG signals are first extracted by DWT,and the imagined words are clas-sified by SVM with the above features.Experimental results show that the proposed method achieves an average accuracy of 61.69%,which is better than those of existing methods for classifying imagined speech tasks.
基金Research was supported in part by the National Natural Science Foundation of China(No.62171473)Beijing Science and Technology Program(No.Z201100004420015)Fundamental Research Funds for the Central Universities of China(No.FRF-TP-20-017A1).
文摘Although notable progress has been made in the study of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI),several factors that limit the practical applications of BCIs still exist.One of these factors is the importability of the stimulator.In this study,Augmented Reality(AR)technology was introduced to present the visual stimuli of SSVEP-BCI,while the robot grasping experiment was designed to verify the applicability of the AR-BCI system.The offline experiment was designed to determine the best stimulus time,while the online experiment was used to complete the robot grasping task.The offline experiment revealed that better information transfer rate performance could be achieved when the stimulation time is 2 s.Results of the online experiment indicate that all 12 subjects could control the robot to complete the robot grasping task,which indicates the applicability of the AR-SSVEP-humanoid robot(NAO)system.This study verified the reliability of the AR-BCI system and indicated the applicability of the AR-SSVEP-NAO system in robot grasping tasks.
基金This work was supportedin part by the National Natural Science Foundation of China(No.60271025,No.30370395)in part by the Science and Technology Depart ment of Shaanxi Province(No.2003K10-G24).
文摘Mental task classification is one of the most important problems in Brain-computer interface.This paper studies the classification of five-class mental tasks.The nonlinear parameter of mean period obtained from frequency domain information was used as features for classification implemented by using the method of SVM(support vector machines).The averaged classification accuracy of 85.6% over 7 subjects was achieved for 2-second EEG segments.And the results for EEG segments of 0.5s and 5.0s compared favorably to those of Garrett’s.The results indicate that the parameter of mean period represents mental tasks well for classification.Furthermore,the method of mean period is less computationally demanding,which indicates its potential use for online BCI systems.
基金the Declaration of Helsinki,and the protocol was approved by the Ethics Committee of Suranaree University of Technology(License EC-61-14 COA No.16/2561)the Thailand Research Fund through the RoyalGolden Jubilee Ph.D.Program(Grant No.PHD/0148/2557).
文摘The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with continuous physiotherapy as these diseases can be eased within the initial stages of the symptoms.So far,the popular control system for robot-assisted rehabilitation devices is only of two types which consist of passive and active devices.However,if there is a control system that can directly detect the motor functions,it will induce neuroplasticity to facilitate early motor recovery.In this paper,the control system,which is a motor recovery system with the intent of rehabilitation,focuses on the hand organs and utilizes a brain-computer interface(BCI)technology.The final results depict that the brainwave detection for controlling pneumatic glove in real-time has an accuracy up to 82%.Moreover,the motor recovery system enables the feasibility of brainwave classification from the motor cortex with Artificial Neural Networks(ANN).The overall model performance reveals an accuracy up to 96.56%with sensitivity of 94.22%and specificity of 98.8%.Therefore,the proposed system increases the efficiency of the traditional device control system and tends to provide a better rehabilitation than the traditional physiotherapy alone.
基金supported by the National Key Basic Research and Development Program of China (No.2017YFB1002505)Key Research and Development Program of Guangdong Province (No. 2018B030339001)the National Natural Science Foundation of China (No.61431007)。
文摘In general, a large amount of training data can effectively improve the classification performance of the Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer Interface(BCI) system. However, it will prolong the training time and considerably restrict the practicality of the system. This study proposed a SSVEP nonlinear signal model based on the Volterra filter, which could reconstruct stable reference signals using relatively small number of training targets by transfer learning, thereby reducing the training cost of SSVEP-BCI. Moreover,this study designed a transfer-extended Canonical Correlation Analysis(t-eCCA) method based on the model to achieve cross-target transfer. As a result, in a single-target SSVEP experiment with 16 stimulus frequencies,t-eCCA obtained an average accuracy of 86.96%˙12.87% across 12 subjects using only half of the calibration time,which exhibited no significant difference from the representative training classification algorithms, namely, extended canonical correlation analysis(88.32%±13.97%) and task-related component analysis(88.92%±14.44%), and was significantly higher than that of the classic non-training algorithms, namely, Canonical Correlation Analysis(CCA) as well as filter-bank CCA. Results showed that the proposed cross-target transfer algorithm t-eCCA could fully utilize the information about the targets and its stimulus frequencies and effectively reduce the training time of SSVEP-BCI.
基金Supported by the National Natural Science Foundation of China,grants 61906152 and 61976177Key Research and Development Program of Shaanxi(Program No.2021GY-080).
文摘With the development of deep learning, many motor imagerybrain-computer interfaces based on convolutional neural networks(CNNs) show outstanding performances. However, the trial number ofEEG in the training set is usually limited, and redundancy extensivelyexists in multiple channel EEG. Thus, overfitting often appears in CNNbased motor imagery recognition model and greatly affects the performancesof model. In this paper, channel drop out is proposed to addressthis problem by data augmentation and ensemble learning. Specifically,one of all EEG channels will be dropped and replaced by the mean signalof all EEG channels. In this way, the trial number in the training setwas enlarged by channel drop out. And at the testing stage, all the EEGtrials processed by channel drop out were fed to the CNN model and theaverage output probabilities of them were applied to determine the prediction.The experiments were conducted on two popular CNN modelsapplied in motor imagery BCI and BCI Competition IV datasets 2a toverify the performances of the proposed channel drop out approach. Theresults show that average improvements provided by channel drop outin two-category or four-category motor imagery classification are 2.83%and 2.65% compared with the original CNN model. So the channel dropout approach significantly improves the performances of motor imagerybased BCI.
文摘A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.
