Hand Motor Imagery Research Articles

User State Classification Based on Functional Brain Connectivity Using a Convolutional Neural Network

The brain–computer interface (BCI) is a promising technology where a user controls a robot or computer by thinking with no movement. There are several underlying principles to implement BCI, such as sensorimotor rhythms, P300, steady-state visually evoked potentials, and directional tuning. Generally, different principles are applied to BCI depending on the application, because strengths and weaknesses vary according to each BCI method. Therefore, BCI should be able to predict a user state to apply suitable principles to the system. This study measured electroencephalography signals in four states (resting, speech imagery, leg-motor imagery, and hand-motor imagery) from 10 healthy subjects. Mutual information from 64 channels was calculated as brain connectivity. We used a convolutional neural network to predict a user state, where brain connectivity was the network input. We applied five-fold cross-validation to evaluate the proposed method. Mean accuracy for user state classification was 88.25 ± 2.34%. This implies that the system can change the BCI principle using brain connectivity. Thus, a BCI user can control various applications according to their intentions.

CNN-based classification of fNIRS signals in motor imagery BCI system

Objective. Development of a brain–computer interface (BCI) requires classification of brain neural activities to different states. Functional near-infrared spectroscopy (fNIRS) can measure the brain activities and has great potential for BCI. In recent years, a large number of classification algorithms have been proposed, in which deep learning methods, especially convolutional neural network (CNN) methods are successful. fNIRS signal has typical time series properties, we combined fNIRS data and kinds of CNN-based time series classification (TSC) methods to classify BCI task. Approach. In this study, participants were recruited for a left and right hand motor imagery experiment and the cerebral neural activities were recorded by fNIRS equipment (FOIRE-3000). TSC methods are used to distinguish the brain activities when imagining the left or right hand. We have tested the overall person, single person and overall person with single-channel classification results, and these methods achieved excellent classification results. We also compared the CNN-based TSC methods with traditional classification methods such as support vector machine. Main results. Experiments showed that the CNN-based methods have significant advantages in classification accuracy: the CNN-based methods have achieved remarkable results in the classification of left-handed and right-handed imagination tasks, reaching 98.6% accuracy on overall person, 100% accuracy on single person, and in the single-channel classification an accuracy of 80.1% has been achieved with the best-performing channel. Significance. These results suggest that using the CNN-based TSC methods can significantly improve the BCI performance and also lay the foundation for the miniaturization and portability of training rehabilitation equipment.

Reducing False Triggering Caused by Irrelevant Mental Activities in Brain-Computer Interface Based on Motor Imagery.

In recent years, the brain-computer interface (BCI) based on motor imagery (MI) has been considered as a potential post-stroke rehabilitation technology. However, the recognition of MI relies on the event-related desynchronization (ERD) feature, which has poor task specificity. Further, there is the problem of false triggering (irrelevant mental activities recognized as the MI of the target limb). In this paper, we discuss the feasibility of reducing the false triggering rate using a novel paradigm, in which the steady-state somatosensory evoked potential (SSSEP) is combined with the MI (MI-SSSEP). Data from the target (right hand MI) and nontarget task (rest) were used to establish the recognition model, and three kinds of interference tasks were used to test the false triggering performance. In the MI-SSSEP paradigm, ERD and SSSEP features modulated by MI could be used for recognition, while in the MI paradigm, only ERD features could be used. The results showed that the false triggering rate of interference tasks with SSSEP features was reduced to 29.3%, which was far lower than the 55.5% seen under the MI paradigm with ERD features. Moreover, in the MI-SSSEP paradigm, the recognition rate of the target and nontarget task was also significantly improved. Further analysis showed that the specificity of SSSEP was significantly higher than that of ERD (p < 0.05), but the sensitivity was not significantly different. These results indicated that SSSEP modulated by MI could more specifically decode the target task MI, and thereby may have potential in achieving more accurate rehabilitation training.

EEG Feature Extraction Based on Brain Function Network and Sample Entropy

For the low recognition rate of motor imagery ElectroEncephaloGram (EEG) signals using single feature in Brain-Computer Interface (BCI) research, a feature extraction method combining brain function network and sample entropy is proposed. According to the neural mechanism appearing in Event Related Synchronization/Event Related Desynchronization (ERS/ERD) phenomenon and the contralateral mapping mechanism between cortex and limb motor imagery, the μ rhythm is denoised by wavelet packet transform. The brain function network is constructed for left hemispherical brain region and right hemispherical brain region by μ rhythm of 27 left channels and 27 right channels respectively. The mean node degree and the mean clustering coefficient are calculated as the brain function network characteristics, and the feature vectors combining the distribution and directivity are constructed by the sample entropy of C3 and C4 channels with the μ rhythm. The Support Vector Machine (SVM) is used to classify the left hand and right hand motor imagery EEG signals. The results show that the feature extraction method based on brain function network and sample entropy achieves better classification result, and the highest classification rate reached 90.27%.

Visual‐Electrotactile Stimulation Feedback to Improve Immersive Brain‐Computer Interface Based on Hand Motor Imagery

In the aging society, the number of people suffering from vascular disorders is rapidly increasing and has become a social problem. The death rate due to stroke, which is the second leading cause of global mortality, has increased by 40% in the last two decades. Stroke can also cause paralysis. Of late, brain‐computer interfaces (BCIs) have been garnering attention in the rehabilitation field as assistive technology. A BCI for the motor rehabilitation of patients with paralysis promotes neural plasticity, when subjects perform motor imagery (MI). Feedback, such as visual and proprioceptive, influences brain rhythm modulation to contribute to MI learning and motor function restoration. Also, virtual reality (VR) can provide powerful graphical options to enhance feedback visualization. This work aimed to improve immersive VR‐BCI based on hand MI, using visual‐electrotactile stimulation feedback instead of visual feedback. The MI tasks include grasping, flexion/extension, and their random combination. Moreover, the subjects answered a system perception questionnaire after the experiments. The proposed system was evaluated with twenty able‐bodied subjects. Visual‐electrotactile feedback improved the mean classification accuracy for the grasping (93.00% ± 3.50%) and flexion/extension (95.00% ± 5.27%) MI tasks. Additionally, the subjects achieved an acceptable mean classification accuracy (maximum of 86.5% ± 5.80%) for the random MI task, which required more concentration. The proprioceptive feedback maintained lower mean power spectral density in all channels and higher attention levels than those of visual feedback during the test trials for the grasping and flexion/extension MI tasks. Also, this feedback generated greater relative power in the μ‐band for the premotor cortex, which indicated better MI preparation. Thus, electrotactile stimulation along with visual feedback enhanced the immersive VR‐BCI classification accuracy by 5.5% and 4.5% for the grasping and flexion/extension MI tasks, respectively, retained the subject’s attention, and eased MI better than visual feedback alone.

A BCI-Based Vibrotactile Neurofeedback Training Improves Motor Cortical Excitability During Motor Imagery.

In this study, we address the issue of whether vibrotactile feedback can enhance the motor cortex excitability translated into the plastic changes in local cortical areas during motor imagery (MI) BCI-based training. For this purpose, we focused on two of the most notable neurophysiological effects of MI - the event-related desynchronization (ERD) level and the increase in cortical excitability assessed with navigated transcranial magnetic stimulation (nTMS). For TMS navigation, we used individual high-resolution 3D brain MRIs. Ten BCI-naive and healthy adults participated in this study. The MI (rest or left/right hand imagery using Graz-BCI paradigm) tasks were performed separately in the presence and absence of feedback. To investigate how much the presence/absence of vibrotactile feedback in MI BCI-based training could contribute to the sensorimotor cortical activations, we compared the MEPs amplitude during MI after training with and without feedback. In addition, the ERD levels during MI BCI-based training were investigated. Our findings provide evidence that applying vibrotactile feedback during MI training leads to (i) an enhancement of the desynchronization level of mu-rhythm EEG patterns over the contralateral motor cortex area corresponding to the MI of the non-dominant hand; (ii) an increase in motor cortical excitability in hand muscle representation corresponding to a muscle engaged by the MI.

Phase/Amplitude Synchronization of Brain Signals During Motor Imagery BCI Tasks.

In the last decade, functional connectivity (FC) has been increasingly adopted based on its ability to capture statistical dependencies between multivariate brain signals. However, the role of FC in the context of brain-computer interface applications is still poorly understood. To address this gap in knowledge, we considered a group of 20 healthy subjects during an EEG-based hand motor imagery (MI) task. We studied two well-established FC estimators, i.e. spectral- and imaginary-coherence, and we investigated how they were modulated by the MI task. We characterized the resulting FC networks by extracting the strength of connectivity of each EEG sensor and we compared the discriminant power with respect to standard power spectrum features. At the group level, results showed that while spectral-coherence based network features were increasing in the sensorimotor areas, those based on imaginary-coherence were significantly decreasing. We demonstrated that this opposite, but complementary, behavior was respectively determined by the increase in amplitude and phase synchronization between the brain signals. At the individual level, we eventually assessed the potential of these network connectivity features in a simple off-line classification scenario. Taken together, our results provide fresh insights into the oscillatory mechanisms subserving brain network changes during MI and offer new perspectives to improve BCI performance.

Efficacy evaluation of neurofeedback applied for treatment of central neuropathic pain using machine learning

Brain-computer interface (BCI) is believed to be the translator of brain signals into actions based on the model, built on the machine learning (ML) algorithms, incorporated in it. This study reports on the performance of various ML algorithms in evaluating efficacy of neurofeedback applied for treatment of central neuropathic pain (CNP). In the first phase of this study, we applied different ML algorithms for classification of electroencephalography (EEG) patterns, associated with CNP, obtained from three groups of participants, during imagined movement of their limbs, named as able-bodied (AB), paraplegic patients with (PWP) and without (PNP) neuropathic pain. In the second phase, we tested the accuracy of BCI-classifier by applying new EEG data obtained from PWP participants who have completed neurofeedback training provided for the management of pain. Support vector Machine (SVM) algorithm gained higher accuracy, with all groups, than the other classifiers. However, the highest classification accuracy of 99 ± 0.49% was obtained with the right hand motor imagery of (AB vs PWP) group and 61 electrodes. In Conclusion, SVM based BCI-classifier achieved high accuracy in evaluating efficacy of neurofeedback applied for treatment of CNP. Results of this study show that the accuracy of BCI changes with ML algorithm, electrodes combinations, and training data set.

Adaptive transfer learning for EEG motor imagery classification with deep Convolutional Neural Network

In recent years, deep learning has emerged as a powerful tool for developing Brain–Computer Interface (BCI) systems. However, for deep learning models trained entirely on the data from a specific individual, the performance increase has only been marginal owing to the limited availability of subject-specific data. To overcome this, many transfer-based approaches have been proposed, in which deep networks are trained using pre-existing data from other subjects and evaluated on new target subjects. This mode of transfer learning however faces the challenge of substantial inter-subject variability in brain data. Addressing this, in this paper, we propose 5 schemes for adaptation of a deep convolutional neural network (CNN) based electroencephalography (EEG)-BCI system for decoding hand motor imagery (MI). Each scheme fine-tunes an extensively trained, pre-trained model and adapt it to enhance the evaluation performance on a target subject. We report the highest subject-independent performance with an average (N=54) accuracy of 84.19% (±9.98%) for two-class motor imagery, while the best accuracy on this dataset is 74.15% (±15.83%) in the literature. Further, we obtain a statistically significant improvement (p=0.005) in classification using the proposed adaptation schemes compared to the baseline subject-independent model.

User Adaptation to Closed-Loop Decoding of Motor Imagery Termination.

Here, we provide insights in the decoding of motor imagery termination and investigate the use of such decoder in closed-loop BMI. Participants (N = 9) were asked to perform kinesthetic motor imagery of both hands simultaneously cued with a clock indicating the initiation and termination of the action. Using electroencephalogram (EEG) signals, we built a decoder to detect the transition between event-related desynchronization and event-related synchronization. Features for this decoder were correlates of motor termination in the upper μ and β bands. The decoder reached an accuracy of 76.2% (N = 9), revealing the high robustness of our approach. More importantly, this paper shows that the decoding of motor termination has an intrinsic latency mainly due to the delayed appearance of its correlates. Because the latency was consistent and thus predictable, users were able to compensate it after training. Using our decoding system, BMI users were able to adapt their behavior and modulate their sensorimotor rhythm to stop the device (clock) accurately on time. These results show the importance of closed-loop evaluations of BMI decoders and open new possibilities for BMI control using decoding of movement termination.

Intralobular and Interlobular Parietal Functional Network Correlated to MI-BCI Performance.

Brain-computer interface (BCI) brings hope to patients suffering from neuromuscular diseases, by allowing the control of external devices using neural signals from the central nervous system. However, a portion of individuals was unable to operate BCI with high efficacy. This research aimed to study the brain-wide functional connectivity differences that contributed to BCI performance, and investigate the relationship between task-related connectivity strength and BCI performance. Functional connectivity was estimated using pairwise Pearson's correlation from the EEG of 48 subjects performing left or right hand motor imagery (MI) tasks. The classification accuracy of linear support vector machine (SVM) to distinguish both tasks were used to represent MI-BCI performance. The significant differences in connectivity strengths were examined using Welch's T-test. The association between accuracy and connection strength was studied using correlation model. Three intralobular and fourteen interlobular connections from the parietal lobe showed a correlation of 0.31 and -0.34 respectively. Results indicate that alpha wave connectivity from 8 Hz to 13 Hz was more related to classification performance compared to high-frequency waves. Subject-independent trial-based analysis shows that MI trials executed with stronger intralobular and interlobular parietal connections performed significantly better than trials with weaker connections. Further investigation from an independent MI dataset reveals several similar connections that were correlated with MI-BCI performance. The functional connectivity of the parietal lobe could potentially allow prediction of MI-BCI performance and enable implementation of neurofeedback training for users to improve the usability of MI-BCI.

Spatial-temporal aspects of continuous EEG-based neurorobotic control

Objective. The goal of this work is to identify the spatio-temporal facets of state-of-the-art electroencephalography (EEG)-based continuous neurorobotics that need to be addressed, prior to deployment in practical applications at home and in the clinic. Approach. Nine healthy human subjects participated in five sessions of one-dimensional (1D) horizontal (LR), 1D vertical (UD) and two-dimensional (2D) neural tracking from EEG. Users controlled a robotic arm and virtual cursor to continuously track a Gaussian random motion target using EEG sensorimotor rhythm modulation via motor imagery (MI) commands. Continuous control quality was analyzed in the temporal and spatial domains separately. Main results. Axis-specific errors during 2D tasks were significantly larger than during 1D counterparts. Fatigue rates were larger for control tasks with higher cognitive demand (LR, left- and right-hand MI) compared to those with lower cognitive demand (UD, both hands MI and rest). Additionally robotic arm and virtual cursor control exhibited equal tracking error during all tasks. However, further spatial error analysis of 2D control revealed a significant reduction in tracking quality that was dependent on the visual interference of the physical device. In fact, robotic arm performance was significantly greater than that of virtual cursor control when the users’ sightlines were not obstructed. Significance. This work emphasizes the need for practical interfaces to be designed around real-world tasks of increased complexity. Here, the dependence of control quality on cognitive task demand emphasizes the need for decoders that facilitate the translation of 1D task mastery to 2D control. When device footprint was accounted for, the introduction of a physical robotic arm improved control quality, likely due to increased user engagement. In general, this work demonstrates the need to consider both the physical footprint of devices, the complexity of training tasks, and the synergy of control strategies during the development of neurorobotic control.

An EEG channel selection method for motor imagery based brain–computer interface and neurofeedback using Granger causality

Motor imagery (MI) brain–computer interface (BCI) and neurofeedback (NF) with electroencephalogram (EEG) signals are commonly used for motor function improvement in healthy subjects and to restore neurological functions in stroke patients. Generally, in order to decrease noisy and redundant information in unrelated EEG channels, channel selection methods are used which provide feasible BCI and NF implementations with better performances. Our assumption is that there are causal interactions between the channels of EEG signal in MI tasks that are repeated in different trials of a BCI and NF experiment. Therefore, a novel method for EEG channel selection is proposed which is based on Granger causality (GC) analysis. Additionally, the machine-learning approach is used to cluster independent component analysis (ICA) components of the EEG signal into artifact and normal EEG clusters. After channel selection, using the common spatial pattern (CSP) and regularized CSP (RCSP), features are extracted and with the k-nearest neighbor (k-NN), support vector machine (SVM) and linear discriminant analysis (LDA) classifiers, MI tasks are classified into left and right hand MI. The goal of this study is to achieve a method resulting in lower EEG channels with higher classification performance in MI-based BCI and NF by causal constraint. The proposed method based on GC, with only eight selected channels, results in 93.03% accuracy, 92.93% sensitivity, and 93.12% specificity, with RCSP feature extractor and best classifier for each subject, after being applied on Physionet MI dataset, which is increased by 3.95%, 3.73%, and 4.13%, in comparison with correlation-based channel selection method.

Evidence for an effector-independent action system from people born without hands

Many parts of the visuomotor system guide daily hand actions, like reaching for and grasping objects. Do these regions depend exclusively on the hand as a specific body part whose movement they guide, or are they organized for the reaching task per se, for any body part used as an effector? To address this question, we conducted a neuroimaging study with people born without upper limbs-individuals with dysplasia-who use the feet to act, as they and typically developed controls performed reaching and grasping actions with their dominant effector. Individuals with dysplasia have no prior experience acting with hands, allowing us to control for hand motor imagery when acting with another effector (i.e., foot). Primary sensorimotor cortices showed selectivity for the hand in controls and foot in individuals with dysplasia. Importantly, we found a preference based on action type (reaching/grasping) regardless of the effector used in the association sensorimotor cortex, in the left intraparietal sulcus and dorsal premotor cortex, as well as in the basal ganglia and anterior cerebellum. These areas also showed differential response patterns between action types for both groups. Intermediate areas along a posterior-anterior gradient in the left dorsal premotor cortex gradually transitioned from selectivity based on the body part to selectivity based on the action type. These findings indicate that some visuomotor association areas are organized based on abstract action functions independent of specific sensorimotor parameters, paralleling sensory feature-independence in visual and auditory cortices in people born blind and deaf. Together, they suggest association cortices across action and perception may support specific computations, abstracted from low-level sensorimotor elements.

Classification of right and left hand motor imagery using deep learning in electroencephalography and near-infrared spectroscopy

Classification of right and left hand motor imagery using deep learning in electroencephalography and near-infrared spectroscopy

Decoding Hand Motor Imagery Tasks Within the Same Limb From EEG Signals Using Deep Learning

Motor imagery (MI) tasks of different body parts have been successfully decoded by conventional classifiers, such as LDA and SVM. On the other hand, decoding MI tasks within the same limb is a challenging problem with these classifiers; however, it would provide more options to control robotic devices. This work proposes to improve the hand MI tasks decoding within the same limb in a brain-computer interface using convolutional neural networks (CNNs); the CNN EEGNet, LDA, and SVM classifiers were evaluated for two (flexion/extension) and three (flexion/extension/grasping) MI tasks. Our approach is the first attempt to apply CNNs for solving this problem to our best knowledge. In addition, visual and electrotactile stimulation were included as BCI training reinforcement after the MI task similar to feedback sessions; then, they were compared. The EEGNet achieved maximum mean accuracies of 78.46% (±12.50%) and 76.72% (±11.67%) for two and three classes, respectively. Outperforming conventional classifiers with results around 60% and 48%, and similar works with results lower than 67% and 75%, respectively. Moreover, the electrical stimulation over the visual stimulus was not significant during the calibration session. The deep learning scheme enhanced the decoding of MI tasks within the same limb against the conventional framework.

A Multi-view CNN with Novel Variance Layer for Motor Imagery Brain Computer Interface.

Accurate and robust classification of Motor Imagery (MI) from Electroencephalography (EEG) signals is among the most challenging tasks in Brain-Computer Interface (BCI) field. To address this challenge, this paper proposes a novel, neuro-physiologically inspired convolutional neural network (CNN) named Filter-Bank Convolutional Network (FBCNet) for MI classification. Capturing neurophysiological signatures of MI, FBCNet first creates a multi-view representation of the data by bandpass-filtering the EEG into multiple frequency bands. Next, spatially discriminative patterns for each view are learned using a CNN layer. Finally, the temporal information is aggregated using a new variance layer and a fully connected layer classifies the resultant features into MI classes. We evaluate the performance of FBCNet on a publicly available dataset from Korea University for classification of left vs right hand MI in a subject-specific 10-fold cross-validation setting. Results show that FBCNet achieves more than 6.7% higher accuracy compared to other state-of-the-art deep learning architectures while requiring less than 1% of the learning parameters. We explain the higher classification accuracy achieved by FBCNet using feature visualization where we show the superiority of FBCNet in learning interpretable and highly generalizable discriminative features. We provide the source code of FBCNet for reproducibility of results.

The Promotoer, a brain-computer interface-assisted intervention to promote upper limb functional motor recovery after stroke: a study protocol for a randomized controlled trial to test early and long-term efficacy and to identify determinants of response

BackgroundStroke is a leading cause of long-term disability. Cost-effective post-stroke rehabilitation programs for upper limb are critically needed. Brain-Computer Interfaces (BCIs) which enable the modulation of Electroencephalography (EEG) sensorimotor rhythms are promising tools to promote post-stroke recovery of upper limb motor function. The “Promotoer” study intends to boost the application of the EEG-based BCIs in clinical practice providing evidence for a short/long-term efficacy in enhancing post-stroke hand functional motor recovery and quantifiable indices of the participants response to a BCI-based intervention. To these aims, a longitudinal study will be performed in which subacute stroke participants will undergo a hand motor imagery (MI) training assisted by the Promotoer system, an EEG-based BCI system fully compliant with rehabilitation requirements.MethodsThis longitudinal 2-arm randomized controlled superiority trial will include 48 first ever, unilateral, subacute stroke participants, randomly assigned to 2 intervention groups: the BCI-assisted hand MI training and a hand MI training not supported by BCI. Both interventions are delivered (3 weekly session; 6 weeks) as add-on regimen to standard intensive rehabilitation. A multidimensional assessment will be performed at: randomization/pre-intervention, 48 h post-intervention, and at 1, 3 and 6 month/s after end of intervention. Primary outcome measure is the Fugl-Meyer Assessment (FMA, upper extremity) at 48 h post-intervention. Secondary outcome measures include: the upper extremity FMA at follow-up, the Modified Ashworth Scale, the Numeric Rating Scale for pain, the Action Research Arm Test, the National Institute of Health Stroke Scale, the Manual Muscle Test, all collected at the different timepoints as well as neurophysiological and neuroimaging measures.DiscussionWe expect the BCI-based rewarding of hand MI practice to promote long-lasting retention of the early induced improvement in hand motor outcome and also, this clinical improvement to be sustained by a long-lasting neuroplasticity changes harnessed by the BCI-based intervention. Furthermore, the longitudinal multidimensional assessment will address the selection of those stroke participants who best benefit of a BCI-assisted therapy, consistently advancing the transfer of BCIs to a best clinical practice.Trial registrationName of registry: BCI-assisted MI Intervention in Subacute Stroke (Promotoer).Trial registration number: NCT04353297; registration date on the ClinicalTrial.gov platform: April, 15/2020.

On the (in)efficacy of motor imagery training without feedback and event-related desynchronizations considerations

Motor imagery (MI) constitutes a recurrent strategy for signals generation in brain-computer interfaces (BCIs) - systems that aim to control external devices by directly associating brain responses to distinct commands. Although great improvement has been achieved in MI-BCIs performance over recent years, they still suffer from inter- and intra-subject variability issues. As an attempt to cope with this, some studies have suggested that MI training should aid users to appropriately modulate their response for BCI usage: generally, this training is performed based on the sensorimotor rhythms’ modulation over the primary sensorimotor cortex (PMC), with the signal being feedbacked to the user. Nonetheless, recent studies have revisited the actual involvement of the PMC into MI, and little to no attention has been devoted to understanding the participation of other cortical areas into training protocols. Therefore, in this work, our aim was to analyze the response induced by hands MI of 10 healthy subjects in the form of event-related desynchronizations (ERDs) and to assess whether features from beyond the PMC might be useful for hands MI classification. We investigated how this response occurs for distinct frequency intervals between 7–30 Hz, and ex0plored changes in their evocation pattern across 12 MI training sessions without feedback. Overall, we found that ERD patterns occur differently for the frequencies encompassed by the μ and β bands, with its evocation being favored for the first band. Over time, the no-feedback approach was inefficient to aid in enhancing ERD evocation (EO). Moreover, to some extent, EO tends to decrease over blocks within a given run, and runs within an MI session, but remains stable within an MI block. We also found that the C3/C4 pair is not necessarily optimal for data classification, and both spectral and spatial subjects’ specificities should be considered when designing training protocols.

Brain Computer Interface Classifiers for Semi-Autonomous Wheelchair Using Fuzzy Logic Optimization

Abstract A brain–computer interface (BCI)-based controller bridges the gap between smart wheelchairs and physically impaired persons with severe conditions. This paper presents the design of a hybrid BCI controller with six classifiers using an electroencephalogram (EEG) headset to detect hand motor imagery (MI) and jaw electromyography (EMG) signals. A BCI controller and semi-autonomous system is developed to control a smart wheelchair in conjunction with its semi-autonomous capabilities. For data acquisition, an openvibe system and a commercial grade EEG headset are used. A multiple common spatial pattern (CSP) filter and Linear discriminant analysis (LDA) classifier system is used to process and classify the user's brain activity. To convert the classifier data into a signal that is compatible with the semi-autonomous wheelchair system, a fuzzy logic controller (FLC) is integrated in LabVIEW. Subjects are trained to use the BCI system and the classifier profiles are optimized for each user and the results are analyzed for this study. The openvibe “Replay” script and recorded training data are used to evaluate the performance of the controller scheme. For each subject, positive, negative, and false-positive executions are recorded. During the initial testing phase, the positive rates for subjects were strong, but false-positive rates were too high to be used. Therefore, the design is iterated by changing the rules of the FLC and configuration of the LabVIEW script. The configuration with the best positive rates for turn executions is chosen where the average positive rate for turning is 0.68 for subject 1 and 0.64 for subject 2.