Multi-class EEG classification of voluntary hand movement directions

Direction decoding of imagined hand movements using subject-specific features from parietal EEG

OBJECTIVE

Research on decoding brain signals for controlling external devices is rapidly emerging, owing to its versatile potential applications including neuro-prosthetic control and neurorehabilitation. Electroencephalogram (EEG)-based non-invasive Brain Computer Interface (BCI) systems decode brain signals to establish an augmented communication and control pathway between the brain and the computer. The development of an efficient BCI system requires accurate decoding of neural activity underlying user's intentions. This study investigates the directional tuning of Electroencephalogram (EEG) characteristics from posterior parietal region, associated with bidirectional hand movement imagination (motor imagery) in left and right directions.

APPROACH

The imagined movement directions of the chosen hand were decoded using a combination of envelope and phase features derived from parietal EEG of both hemispheres. The proposed algorithm uses wavelet for spectral decomposition, and discriminative subject-specific subband levels are identified based on Fisher analysis of envelope and phase features. The selected features from the discriminative subband levels are used for classifying left and right motor imagery directions of the hand using Support Vector Machine Classifier. Furthermore, the performance of the proposed algorithm is evaluated by incorporating a maximum variance-based EEG time bin selection algorithm.

MAIN RESULTS

With the time bin selection approach using subject-specific features, the proposed algorithm yielded an average left vs right motor imagery direction decoding accuracy of 73.33% across 15 healthy subjects. In addition, decoding accuracy offered by the phase features was higher than that of the envelope features, indicating the importance of phase features in MI kinematics decoding.

SIGNIFICANCE

The results reveal the significance of parietal EEG in decoding imagined kinematics and open new possibilities for future BCI research.

Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI

OBJECTIVE

Multi-channel EEG data containing redundant information and noise may result in low classification accuracy and high computational complexity, which limits the practicality of motor imagery-based BCI systems. Therefore, channel selection can improve BCI performance and contribute to user convenience. Additionally, cross-subject generalization is a key topic in the channel selection of motor imagery-based BCI.

APPROACH

In this study, an adaptive binary multi-objective harmony search (ABMOHS) algorithm is proposed to select the optimal set of channels. Furthermore, a new adaptive crosssubject generalization model (ACGM) is proposed. Three public motor imagery datasets were used to validate the effectiveness of the proposed method.

MAIN RESULTS

The Wilcoxon signed-rank test was performed on the test accuracies, and the results indicated that the ABMOHS method significantly outperformed all channels (p<0.001), the C3-Cz-C4 channels (p<0.001), and 20 channels (p<0.001) in the sensorimotor cortex. The ABMOHS algorithm based on Fisher's linear discriminant analysis (FLDA) and support vector machine (SVM) classifiers greatly reduces the number of selected channels, especially for larger channel sizes (Dataset 2), and obtains a comparative classification performance. Although there was no significant difference in test classification performance between ABMOHS and non-dominated sorting genetic algorithm II (NSGA-II) when FLDA and SVM were used, ABMOHS required less computational time than NSGA-II. Furthermore, the number of channels obtained by ABMOHS algorithm were significantly smaller than those obtained by CSP-Rank and correlation-based channel selection algorithm (CCS). Additionally, the generalization of ACGM to untrained subjects shows that the mean test classification accuracy of ACGM created by a small sample of trained subjects is significantly better than that of Special-16 and Special-32.

SIGNIFICANCE

The proposed method can reduce the calibration time in the training phase and improve the practicability of MI-BCI.

Feature- and classification analysis for detection and classification of tongue movements from single-trial pre-movement EEG

Individuals with severe tetraplegia can benefit from brain-computer interfaces (BCIs). While most movement-related BCI systems focus on right/left hand and/or foot movements, very few studies have considered tongue movements to construct a multiclass BCI. The aim of this study was to decode four movement directions of the tongue (left, right, up, and down) from single-trial pre-movement EEG and provide a feature and classifier investigation. In offline analyses (from ten healthy participants) detection and classification were performed using temporal, spectral, entropy, and template features classified using either a linear discriminative analysis, support vector machine, random forest or multilayer perceptron classifiers. Besides the 4-class classification scenario, all possible 3-, and 2-class scenarios were tested to find the most discriminable movement type. The linear discriminant analysis achieved on average, higher classification accuracies for both movement detection and classification. The right- and down tongue movements provided the highest and lowest detection accuracy (95.3±4.3% and 91.7±4.8%), respectively. The 4-class classification achieved an accuracy of 62.6±7.2%, while the best 3-class classification (using left, right, and up movements) and 2-class classification (using left and right movements) achieved an accuracy of 75.6±8.4% and 87.7±8.0%, respectively. Using only a combination of the temporal and template feature groups provided further classification accuracy improvements. Presumably, this is because these feature groups utilize the movement-related cortical potentials, which are noticeably different on the left- versus right brain hemisphere for the different movements. This study shows that the cortical representation of the tongue is useful for extracting control signals for multi-class movement detection BCIs.

Unraveling somatotopic organization in the human brain using machine learning and adaptive supervoxel-based parcellations

In addition to the well-established somatotopy in the pre- and post-central gyrus, there is now strong evidence that somatotopic organization is evident across other regions in the sensorimotor network. This raises several experimental questions: To what extent is activity in the sensorimotor network effector-dependent and effector-independent? How important is the sensorimotor cortex when predicting the motor effector? Is there redundancy in the distributed somatotopically organized network such that removing one region has little impact on classification accuracy? To answer these questions, we developed a novel experimental approach. fMRI data were collected while human subjects performed a precisely controlled force generation task separately with their hand, foot, and mouth. We used a simple linear iterative clustering (SLIC) algorithm to segment whole-brain beta coefficient maps to build an adaptive brain parcellation and then classified effectors using extreme gradient boosting (XGBoost) based on parcellations at various spatial resolutions. This allowed us to understand how data-driven adaptive brain parcellation granularity altered classification accuracy. Results revealed effector-dependent activity in regions of the post-central gyrus, precentral gyrus, and paracentral lobule. SMA, regions of the inferior and superior parietal lobule, and cerebellum each contained effector-dependent and effector-independent representations. Machine learning analyses showed that increasing the spatial resolution of the data-driven model increased classification accuracy, which reached 94% with 1755 supervoxels. Our SLIC-based supervoxel parcellation outperformed classification analyses using established brain templates and random simulations. Occlusion experiments further demonstrated redundancy across the sensorimotor network when classifying effectors. Our observations extend our understanding of effector-dependent and effector-independent organization within the human brain and provide new insight into the functional neuroanatomy required to predict the motor effector used in a motor control task.

Motor Imagery Hand Movement Direction Decoding Using Brain Computer Interface to Aid Stroke Recovery and Rehabilitation

Motor Imagery (MI)-based Brain Computer Interface (BCI) system is a potential technology for active neurorehabilitation of stroke patients by complementing the conventional passive rehabilitation methods. Research to date mainly focused on classifying left vs. right hand/foot MI of stroke patients. Though a very few studies have reported decoding imagined hand movement directions using electroencephalogram (EEG)-based BCI, the experiments were conducted on healthy subjects. Our work analyzes MI-based brain cortical activity from EEG signals and decodes the imagined hand movement directions in stroke patients. The decoded direction (left vs. right) of hand movement imagination is used to provide control commands to a motorized arm support on which patient's affected (paralyzed) arm is placed. This enables the patient to move his/her stroke-affected hand towards the intended (imagined) direction that aids neuroplasticity in the brain. The synchronization measure called Phase Locking Value (PLV), extracted from EEG, is the neuronal signature used to decode the directional movement of the MI task. Event-related desynchronization/synchronization (ERD/ERS) analysis on Mu and Beta frequency bands of EEG is done to select the time bin corresponding to the MI task. The dissimilarities between the two directions of MI tasks are identified by selecting the most significant channel pairs that provided maximum difference in PLV features. The training protocol has an initial calibration session followed by a feedback session with 50 trials of MI task in each session. The feedback session extracts PLV features corresponding to most significant channel pairs which are identified in the calibration session and is used to predict the direction of MI task in left/right direction. An average MI direction classification accuracy of 74.44% is obtained in performing the training protocol and 68.63% from the prediction protocol during feedback session on 16 stroke patients.

Decoding Single-Hand and Both-Hand Movement Directions From Noninvasive Neural Signals

Decoding human movement parameters from electroencephalograms (EEG) signals is of great value for human-machine collaboration. However, existing studies on hand movement direction decoding concentrate on the decoding of a single-hand movement direction from EEG signals given the opposite hand is maintained still. In practice, the cooperative movement of both hands is common. In this paper, we investigated the neural signatures and decoding of single-hand and both-hand movement directions from EEG signals. The potentials of EEG signals and power sums in the low frequency band of EEG signals from 24 channels were used as decoding features. The linear discriminant analysis (LDA) and support vector machine (SVM) classifiers were used for decoding. Experimental results showed a significant difference in the negative offset maximums of movement-related cortical potentials (MRCPs) at electrode Cz between single-hand and both-hand movements. The recognition accuracies for six-class classification, including two single-hand and four both-hand movement directions, reached 70.29%± 10.85% by using EEG potentials as features with the SVM classifier. These findings showed the feasibility of decoding single-hand and both-hand movement directions. This work can lay a foundation for the future development of an active human-machine collaboration system based on EEG signals and open a new research direction in the field of decoding hand movement parameters from EEG signals.

Analysis and Classification for Single-Trial EEG Induced by Sequential Finger Movements

In recent years, motor imagery-based BCIs (MI-BCIs) controlled various external devices successfully, which have great potential in neurological rehabilitation. In this paper, we designed a paradigm of sequential finger movements and utilized spatial filters for feature extraction to classify single-trial electroencephalography (EEG) induced by finger movements of left and right hand. Ten healthy subjects participated the experiment. The analysis of EEG patterns showed significant contralateral dominance. We investigated how data length affected the classification accuracy. The classification accuracy was improved with the increase of the keystrokes in one trial, and the results were 87.42%, 91.21%, 93.08% and 93.59% corresponding to single keystroke, two keystrokes, three keystrokes and four keystrokes. This study would be helpful to improve the decoding efficiency and optimize the encoding method of motor-related EEG information.

Upper limb complex movements decoding from pre-movement EEG signals using wavelet common spatial patterns

BACKGROUND AND OBJECTIVE

Decoding functional movements from electroencephalographic (EEG) activity for motor disability rehabilitation is essential to develop home-use brain-computer interface systems. In this paper, the classification of five complex functional upper limb movements is studied by using only the pre-movement planning and preparation recordings of EEG data.

METHODS

Nine healthy volunteers performed five different upper limb movements. Different frequency bands of the EEG signal are extracted by the stationary wavelet transform. Common spatial patterns are used as spatial filters to enhance separation of the five movements in each frequency band. In order to increase the efficiency of the system, a mutual information-based feature selection algorithm is applied. The selected features are classified using the k-nearest neighbor, support vector machine, and linear discriminant analysis methods.

RESULTS

K-nearest neighbor method outperformed the other classifiers and resulted in an average classification accuracy of 94.0 ± 2.7% for five classes of movements across subjects. Further analysis of each frequency band's contribution in the optimal feature set, showed that the gamma and beta frequency bands had the most contribution in the classification. To reduce the complexity of the EEG recording system setup, we selected a subset of the 10 most effective EEG channels from 64 channels, by which we could reach an accuracy of 70%. Those EEG channels were mostly distributed over the prefrontal and frontal areas.

CONCLUSIONS

Overall, the results indicate that it is possible to classify complex movements before the movement onset by using spatially selected EEG data.

Selection of Features and Classifiers for EMG-EEG-Based Upper Limb Assistive Devices-A Review

Bio-signals are distinctive factors in the design of human-machine interface, essentially useful for prosthesis, orthosis, and exoskeletons. Despite the progress in the analysis of pattern recognition based devices; the acceptance of these devices is still questionable. One reason is the lack of information to identify the possible combinations of features and classifiers. Besides; there is also a need for optimal selection of various sensors for sensations such as touch, force, texture, along with EMGs/EEGs. This article reviews the two bio-signal techniques, named as electromyography and electroencephalography. The details of the features and the classifiers used in the data processing for upper limb assist devices are summarised here. Various features and their sets are surveyed and different classifiers for feature sets are discussed on the basis of the classification rate. The review was carried out on the basis of the last 10-12 years of published research in this area. This article also outlines the influence of modality of EMGs and EEGs with other sensors on classifications. Also, other bio-signals used in upper limb devices and future aspects are considered.

Connectivity steered graph Fourier transform for motor imagery BCI decoding

OBJECTIVE

Graph signal processing (GSP) concepts are exploited for brain activity decoding and particularly the detection and recognition of a motor imagery (MI) movement. A novel signal analytic technique that combines graph Fourier transform (GFT) with estimates of cross-frequency coupling (CFC) and discriminative learning is introduced as a means to recover the subject's intention from the multichannel signal.

APPROACH

Adopting a multi-view perspective, based on the popular concept of co-existing and interacting brain rhythms, a multilayer network model is first built from empirical data and its connectivity graph is used to derive the GFT-basis. A personalized decoding scheme supporting a binary decision, either 'left versus right' or 'rest versus MI', is crafted from a small set of training trials. Electroencephalographic (EEG) activity from 12 volunteers recorded during two randomly alternating, externally cued, MI tasks (clenching either left or right fist) and a rest condition is used to introduce and validate our methodology. In addition, the introduced methodology was further validated based on dataset IVa of BCI III competition.

MAIN RESULTS

Our GFT-domain decoding scheme achieves nearly optimal performance and proves superior to alternative techniques that are very popular in the field.

SIGNIFICANCE

At a conceptual level, our work suggests a fruitful way to introduce network neuroscience in BCI research. At a more practical level, it is characterized by efficiency. Training is realized using a small number of exemplar trials and decoding requires very simple operations that leaves room for real-time implementation.

Detection of reaching intention using EEG signals and nonlinear dynamic system identification

BACKGROUND AND OBJECTIVES

Low frequency electroencephalography (EEG) signals are associated with preparation of movement and thus provide valuable information for brain-machine interface applications. The purpose of this study was to detect movement intention from EEG signals before execution of self-paced arm reaching movements.

METHODS

Ten healthy individuals were recruited. Movement onset was determined from surface electromyography recordings time-locked with EEG signals. Unlike previous studies, which employed feature extraction and classification for decoding, a nonlinear dynamic multiple-input/single output (MISO) model was developed. The MISO model consisted of a cascade of Volterra structures and a threshold block, generating the binary output corresponding to intention/no-intention. The modeling process included input selection from a pool of different EEG channels. The predictive performance of the model was evaluated using the receiver operating characteristics curve, from which the optimum threshold was also selected. The Mann-Whitney statistics was employed to select the significant EEG channels for the output by examining the statistical significance of improvement in the predictive capability of the model when the respective channels were included.

RESULTS

With the proposed approach, movement intention was detected approximately 500 ms before the movement onset and on average, with an accuracy of 96.37 ± 0.94%, a sensitivity of 77.93 ± 4.40% and a specificity of 98.52 ± 1.19%.

CONCLUSIONS

The model output can be converted to motion commands for neuroprosthetic devices and exoskeletons in future applications.

Classification of Movement Intention Using Independent Components of Premovement EEG

Many previous studies on brain-machine interfaces (BMIs) have focused on electroencephalography (EEG) signals elicited during motor-command execution to generate device commands. However, exploiting pre-execution brain activity related to movement intention could improve the practical applicability of BMIs. Therefore, in this study we investigated whether EEG signals occurring before movement execution could be used to classify movement intention. Six subjects performed reaching tasks that required them to move a cursor to one of four targets distributed horizontally and vertically from the center. Using independent components of EEG acquired during a premovement phase, two-class classifications were performed for left vs. right trials and top vs. bottom trials using a support vector machine. Instructions were presented visually (test) and aurally (condition). In the test condition, accuracy for a single window was about 75%, and it increased to 85% in classification using two windows. In the control condition, accuracy for a single window was about 73%, and it increased to 80% in classification using two windows. Classification results showed that a combination of two windows from different time intervals during the premovement phase improved classification performance in the both conditions compared to a single window classification. By categorizing the independent components according to spatial pattern, we found that information depending on the modality can improve classification performance. We confirmed that EEG signals occurring during movement preparation can be used to control a BMI.

Analysis and Classification for EEG Patterns of Force Motor Imagery Using Movement Related Cortical Potentials

Motor imagery-based BCIs are the most natural human-computer interaction paradigms. In recent years, researchers have tried to decode the kinetic information of motor imagery. In this paper, we analyzed and discriminated the EEG patterns of different force levels motor imagery using MRCPs. In the experiment, nine healthy subjects were required to perform the hand force motor imagery tasks (30% MVC and 10% MVC). From the view of MRCPs, the most significant discrimination between the two levels of mental tasks was the manifestation of motor planning. The average classification accuracy for features involving both MRCP and CSP was 78.3%, which was 8.5% higher than the CSP-based features (p¡0.001) and 2% higher than the MRCP-based features. The results demonstrated the feasibility of using MRCPs for hand force motor imagery classification.

Exploiting the heightened phase synchrony in patients with neuromuscular disease for the establishment of efficient motor imagery BCIs

Background

Phase synchrony has extensively been studied for understanding neural coordination in health and disease. There are a few studies concerning the implications in the context of BCIs, but its potential for establishing a communication channel in patients suffering from neuromuscular disorders remains totally unexplored. We investigate, here, this possibility by estimating the time-resolved phase connectivity patterns induced during a motor imagery (MI) task and adopting a supervised learning scheme to recover the subject’s intention from the streaming data.

Methods

Electroencephalographic activity from six patients suffering from neuromuscular disease (NMD) and six healthy individuals was recorded during two randomly alternating, externally cued, MI tasks (clenching either left or right fist) and a rest condition. The metric of Phase locking value (PLV) was used to describe the functional coupling between all recording sites. The functional connectivity patterns and the associate network organization was first compared between the two cohorts. Next, working at the level of individual patients, we trained support vector machines (SVMs) to discriminate between “left” and “right” based on different instantiations of connectivity patterns (depending on the encountered brain rhythm and the temporal interval). Finally, we designed and realized a novel brain decoding scheme that could interpret the intention from streaming connectivity patterns, based on an ensemble of SVMs.

Results

The group-level analysis revealed increased phase synchrony and richer network organization in patients. This trend was also seen in the performance of the employed classifiers. Time-resolved connectivity led to superior performance, with distinct SVMs acting as local experts, specialized in the patterning emerged within specific temporal windows (defined with respect to the external trigger). This empirical finding was further exploited in implementing a decoding scheme that can be activated without the need of the precise timing of a trigger.

Conclusion

The increased phase synchrony in NMD patients can turn to a valuable tool for MI decoding. Considering the fast implementation for the PLV pattern computation in multichannel signals, we can envision the development of efficient personalized BCI systems in assistance of these patients.

Electronic supplementary material

The online version of this article (10.1186/s12984-018-0431-6) contains supplementary material, which is available to authorized users.

Wavlet phase-locking based binary classification of hand movement directions from EEG

OBJECTIVE

Brain signals can be used to extract relevant features to decode various limb movement parameters such as the direction of upper limb movements. Amplitude based feature extraction techniques have been used to study such motor activity of upper limbs whereas phase synchrony, used to estimate functional relationship between signals, has rarely been used to study single hand movements in different directions.

APPROACH

In this paper, a novel phase-locking-based feature extraction method, called wavelet phase-locking value (W-PLV) is proposed to analyse synchronous EEG channel-pairs and classify hand movement directions. EEG data collected from seven subjects performing right hand movements in four orthogonal directions in the horizontal plane is used for this analysis.

MAIN RESULTS

Our proposed W-PLV based method achieves a mean binary classification accuracy of 76.85% over seven subjects using wavelet levels corresponding to ⩽12 Hz EEG. The results also show direction-dependent information in various wavelet levels and indicate the presence of relevant information in slow cortical potentials (<1 Hz) as well as higher wavelet levels (⩽12 Hz).

SIGNIFICANCE

This study presents a thorough analysis of the phase-locking patterns extracted from EEG corresponding to hand movements in different directions using W-PLV across various wavelet levels and verifies their discriminative ability in the single trial binary classification of hand movement directions.

Classification of different reaching movements from the same limb using EEG

OBJECTIVE

Brain-computer-interfaces (BCIs) have been proposed not only as assistive technologies but also as rehabilitation tools for lost functions. However, due to the stochastic nature, poor spatial resolution and signal to noise ratio from electroencephalography (EEG), multidimensional decoding has been the main obstacle to implement non-invasive BCIs in real-live rehabilitation scenarios. This study explores the classification of several functional reaching movements from the same limb using EEG oscillations in order to create a more versatile BCI for rehabilitation.

APPROACH

Nine healthy participants performed four 3D center-out reaching tasks in four different sessions while wearing a passive robotic exoskeleton at their right upper limb. Kinematics data were acquired from the robotic exoskeleton. Multiclass extensions of Filter Bank Common Spatial Patterns (FBCSP) and a linear discriminant analysis (LDA) classifier were used to classify the EEG activity into four forward reaching movements (from a starting position towards four target positions), a backward movement (from any of the targets to the starting position and rest). Recalibrating the classifier using data from previous or the same session was also investigated and compared.

MAIN RESULTS

Average EEG decoding accuracy were significantly above chance with 67%, 62.75%, and 50.3% when decoding three, four and six tasks from the same limb, respectively. Furthermore, classification accuracy could be increased when using data from the beginning of each session as training data to recalibrate the classifier.

SIGNIFICANCE

Our results demonstrate that classification from several functional movements performed by the same limb is possible with acceptable accuracy using EEG oscillations, especially if data from the same session are used to recalibrate the classifier. Therefore, an ecologically valid decoding could be used to control assistive or rehabilitation mutli-degrees of freedom (DoF) robotic devices using EEG data. These results have important implications towards assistive and rehabilitative neuroprostheses control in paralyzed patients.

EEG source space analysis of the supervised factor analytic approach for the classification of multi-directional arm movement

OBJECTIVE

In electroencephalography (EEG)-based brain-computer interface (BCI) systems for motor control tasks the conventional practice is to decode motor intentions by using scalp EEG. However, scalp EEG only reveals certain limited information about the complex tasks of movement with a higher degree of freedom. Therefore, our objective is to investigate the effectiveness of source-space EEG in extracting relevant features that discriminate arm movement in multiple directions.

APPROACH

We have proposed a novel feature extraction algorithm based on supervised factor analysis that models the data from source-space EEG. To this end, we computed the features from the source dipoles confined to Brodmann areas of interest (BA4a, BA4p and BA6). Further, we embedded class-wise labels of multi-direction (multi-class) source-space EEG to an unsupervised factor analysis to make it into a supervised learning method.

MAIN RESULTS

Our approach provided an average decoding accuracy of 71% for the classification of hand movement in four orthogonal directions, that is significantly higher (>10%) than the classification accuracy obtained using state-of-the-art spatial pattern features in sensor space. Also, the group analysis on the spectral characteristics of source-space EEG indicates that the slow cortical potentials from a set of cortical source dipoles reveal discriminative information regarding the movement parameter, direction.

SIGNIFICANCE

This study presents evidence that low-frequency components in the source space play an important role in movement kinematics, and thus it may lead to new strategies for BCI-based neurorehabilitation.

From classic motor imagery to complex movement intention decoding: The noninvasive Graz-BCI approach

In this chapter, we give an overview of the Graz-BCI research, from the classic motor imagery detection to complex movement intentions decoding. We start by describing the classic motor imagery approach, its application in tetraplegic end users, and the significant improvements achieved using coadaptive brain-computer interfaces (BCIs). These strategies have the drawback of not mirroring the way one plans a movement. To achieve a more natural control-and to reduce the training time-the movements decoded by the BCI need to be closely related to the user's intention. Within this natural control, we focus on the kinematic level, where movement direction and hand position or velocity can be decoded from noninvasive recordings. First, we review movement execution decoding studies, where we describe the decoding algorithms, their performance, and associated features. Second, we describe the major findings in movement imagination decoding, where we emphasize the importance of estimating the sources of the discriminative features. Third, we introduce movement target decoding, which could allow the determination of the target without knowing the exact movement-by-movement details. Aside from the kinematic level, we also address the goal level, which contains relevant information on the upcoming action. Focusing on hand-object interaction and action context dependency, we discuss the possible impact of some recent neurophysiological findings in the future of BCI control. Ideally, the goal and the kinematic decoding would allow an appropriate matching of the BCI to the end users' needs, overcoming the limitations of the classic motor imagery approach.

Evolutionary Algorithm Based Feature Optimization for Multi-Channel EEG Classification

The most BCI systems that rely on EEG signals employ Fourier based methods for time-frequency decomposition for feature extraction. The band-limited multiple Fourier linear combiner is well-suited for such band-limited signals due to its real-time applicability. Despite the improved performance of these techniques in two channel settings, its application in multiple-channel EEG is not straightforward and challenging. As more channels are available, a spatial filter will be required to eliminate the noise and preserve the required useful information. Moreover, multiple-channel EEG also adds the high dimensionality to the frequency feature space. Feature selection will be required to stabilize the performance of the classifier. In this paper, we develop a new method based on Evolutionary Algorithm (EA) to solve these two problems simultaneously. The real-valued EA encodes both the spatial filter estimates and the feature selection into its solution and optimizes it with respect to the classification error. Three Fourier based designs are tested in this paper. Our results show that the combination of Fourier based method with covariance matrix adaptation evolution strategy (CMA-ES) has the best overall performance.

Classification of upper limb center-out reaching tasks by means of EEG-based continuous decoding techniques

Background

One of the current challenges in brain-machine interfacing is to characterize and decode upper limb kinematics from brain signals, e.g. to control a prosthetic device. Recent research work states that it is possible to do so based on low frequency EEG components. However, the validity of these results is still a matter of discussion. In this paper, we assess the feasibility of decoding upper limb kinematics from EEG signals in center-out reaching tasks during passive and active movements.

Methods

The decoding of arm movement was performed using a multidimensional linear regression. Passive movements were analyzed using the same methodology to study the influence of proprioceptive sensory feedback in the decoding. Finally, we evaluated the possible advantages of classifying reaching targets, instead of continuous trajectories.

Results

The results showed that arm movement decoding was significantly above chance levels. The results also indicated that EEG slow cortical potentials carry significant information to decode active center-out movements. The classification of reached targets allowed obtaining the same conclusions with a very high accuracy. Additionally, the low decoding performance obtained from passive movements suggests that discriminant modulations of low-frequency neural activity are mainly related to the execution of movement while proprioceptive feedback is not sufficient to decode upper limb kinematics.

Conclusions

This paper contributes to the assessment of feasibility of using linear regression methods to decode upper limb kinematics from EEG signals. From our findings, it can be concluded that low frequency bands concentrate most of the information extracted from upper limb kinematics decoding and that decoding performance of active movements is above chance levels and mainly related to the activation of cortical motor areas. We also show that the classification of reached targets from decoding approaches may be a more suitable real-time methodology than a direct decoding of hand position.

Towards decoding of functional movements from the same limb using EEG

In recent years, there has been an increasing interest in using electroencephalographic (EEG) activity to close the loop between brain oscillations and movement to induce functional motor rehabilitation. Rehabilitation robots or exoskeletons have been controlled using EEG activity. However, all studies have used a 2-class or one-dimensional decoding scheme. In this study we investigated EEG decoding of 5 functional movements of the same limb towards an online scenario. Six healthy participants performed a three-dimensional center-out reaching task based on direction movements (four directions and rest) wearing a 32-channel EEG cap. A BCI design based on multiclass extensions of Spectrally Weighted Common Spatial Patterns (Spec-CSP) and a linear discriminant analysis (LDA) classifier was developed and tested offline. The decoding accuracy was 5-fold cross-validated. A decoding accuracy of 39.5% on average for all the six subjects was obtained (chance level being 20%). The results of the current study demonstrate multiple functional movements decoding (significantly higher than chance level) from the same limb using EEG data. This study represents first steps towards a same limb multi degree of freedom (DOF) online EEG based BCI for motor restoration.

Block design enhances classification of 3D reach targets from electroencephalographic signals

To date, decoding accuracy of actual or imagined pointing movements to targets in 3D space from electroencephalographic (EEG) signals has remained modest. The reason may pertain to the fact that these movements activate essentially the same neural networks. In this study, we aimed at testing whether repetitive pointing movements to each of the targets promotes the development of segregated neural patterns, resulting in enhanced decoding accuracy. Six human subjects generated slow or fast repetitive pointing movements with their right dominant arm to one of five targets distributed in 3D space, followed by repetitive imagery of movements to the same target or to a different target. Nine naive subjects generated both repetitive and non-repetitive slow actual movements to each of the five targets to test the effect of block design on decoding accuracy. In order to assure that base line drift and low frequency motion artifacts do not contaminate the data, the data were high-pass filtered in 4-30Hz, leaving out the delta and gamma band. For the repetitive trials, the model decoded target location with 81% accuracy, which is significantly higher than chance level. The average decoding rate of target location was only 30% for the non-repetitive trials, which is not significantly different than chance level. A subset of electrodes, mainly over the contralateral sensorimotor areas, was found to provide most of the discriminative features for all tested conditions. Time proximity between trained and tested blocks was found to enhance decoding accuracy of target location both by target non-specific and specific mechanisms. Our findings suggest that movement repetition promotes the development of distinct neural patterns, presumably by the formation of target-specific kinesthetic memory.

Multi-direction hand movement classification using EEG-based source space analysis

Recent advances in the brain-computer interfaces (BCIs) have demonstrated the inference of movement related activity using non-invasive EEG. However, most of the sensorspace approaches that study sensorimotor rhythms using EEG do not reveal the underlying neurophysiological phenomenon while executing or imagining the movement with finer control. Therefore, there is a need to examine feature extraction techniques in the cortical source space which can provide more information about the task compared to sensor-space. In this study, we extend the traditional sensor-space feature extraction method, Common Spatial Pattern (CSP), to the source space, using various regularization approaches. We use Weighted Minimum Norm Estimate (wMNE) as a source localization technique. We show that for a multi-direction hand movement classification problem, the source space features can result in an increase of over 10% accuracy compared to sensor space features. Fisher's Linear Discriminant (FLD) classifier with the One-versus-rest approach is used for the classification.

Adaptive estimation of hand movement trajectory in an EEG based brain-computer interface system

OBJECTIVE

The various parameters that define a hand movement such as its trajectory, speed, etc, are encoded in distinct brain activities. Decoding this information from neurophysiological recordings is a less explored area of brain-computer interface (BCI) research. Applying non-invasive recordings such as electroencephalography (EEG) for decoding makes the problem more challenging, as the encoding is assumed to be deep within the brain and not easily accessible by scalp recordings.

APPROACH

EEG based BCI systems can be developed to identify the neural features underlying movement parameters that can be further utilized to provide a detailed and well defined control command set to a BCI output device. A real-time continuous control is better suited for practical BCI systems, and can be achieved by continuous adaptive reconstruction of movement trajectory than discrete brain activity classifications. In this work, we adaptively reconstruct/estimate the parameters of two-dimensional hand movement trajectory, namely movement speed and position, from multi-channel EEG recordings. The data for analysis is collected by performing an experiment that involved center-out right-hand movement tasks in four different directions at two different speeds in random order. We estimate movement trajectory using a Kalman filter that models the relation between brain activity and recorded parameters based on a set of defined predictors. We propose a method to define these predictor variables that includes spatial, spectral and temporally localized neural information and to select optimally informative variables.

MAIN RESULTS

The proposed method yielded correlation of (0.60 ± 0.07) between recorded and estimated data. Further, incorporating the proposed predictor subset selection, the correlation achieved is (0.57 ± 0.07, p < 0.004) with significant gain in stability of the system, as well as dramatic reduction in number of predictors (76%) for the savings of computational time.

SIGNIFICANCE

The proposed system provides a real time movement control system using EEG-BCI with control over movement speed and position. These results are higher and statistically significant compared to existing techniques in EEG based systems and thus promise the applicability of the proposed method for efficient estimation of movement parameters and for continuous motor control.

Adaptive Stacked Generalization for Multiclass Motor Imagery-Based Brain Computer Interfaces

Practical motor imagery-based brain computer interface (MI-BCI) applications are limited by the difficult to decode brain signals in a reliable way. In this paper, we propose a processing framework to address non-stationarity, as well as handle spectral, temporal, and spatial characteristics associated with execution of motor tasks. Stacked generalization is used to exploit the power of classifier ensembles for combining information coming from multiple sources and reducing the existing uncertainty in EEG signals. The outputs of several regularized linear discriminant analysis (RLDA) models are combined to account for temporal, spatial, and spectral information. The resultant algorithm is called stacked RLDA (SRLDA). Additionally, an adaptive processing stage is introduced before classification to reduce the harmful effect of intersession non-stationarity. The benefits of the proposed method are evaluated on the BCI Competition IV dataset 2a. We demonstrate its effectiveness in binary and multiclass settings with four different motor imagery tasks: left-hand, right-hand, both feet, and tongue movements. The results show that adaptive SRLDA outperforms the winner of the competition and other approaches tested on this multiclass dataset.

Addressing low frequency movement artifacts in EEG signal recorded during center-out reaching tasks

The successful application of noninvasive brain-computer interfaces (BCI) to neurological rehabilitation requires examination of low frequency movement artifacts and development of accurate new methods for their correction. To this end, this study applies an adaptive trend extraction method to electroencephalogram (EEG) signals recorded during active and passive center-out reaching tasks. Distinct patterns are discovered, which correlate to arm kinematics, but are shown to be largely artifactual in nature. Notably, these patterns are found to be similar to features currently used for discrimination of movement direction, indicating a necessity for caution and precise signal processing methods when utilizing low frequency content of EEG signals in such applications.

Sitting and standing intention can be decoded from scalp EEG recorded prior to movement execution

Low frequency signals recorded from non-invasive electroencephalography (EEG), in particular movement-related cortical potentials (MRPs), are associated with preparation and execution of movement and thus present a target for use in brain-machine interfaces. We investigated the ability to decode movement intent from delta-band (0.1-4 Hz) EEG recorded immediately before movement execution in healthy volunteers. We used data from epochs starting 1.5 s before movement onset to classify future movements into one of three classes: stand-up, sit-down, or quiet. We assessed classification accuracy in both externally triggered and self-paced paradigms. Movement onset was determined from electromyography (EMG) recordings synchronized with EEG signals. We employed an artifact subspace reconstruction (ASR) algorithm to eliminate high amplitude noise before building our time-embedded EEG features. We applied local Fisher's discriminant analysis to reduce the dimensionality of our spatio-temporal features and subsequently used a Gaussian mixture model classifier for our three class problem. Our results demonstrate significantly better than chance classification accuracy (chance level = 33.3%) for the self-initiated (78.0 ± 2.6%) and triggered (74.7 ± 5.7%) paradigms. Surprisingly, we found no significant difference in classification accuracy between the self-paced and cued paradigms when using the full set of non-peripheral electrodes. However, accuracy was significantly increased for self-paced movements when only electrodes over the primary motor area were used. Overall, this study demonstrates that delta-band EEG recorded immediately before movement carries discriminative information regarding movement type. Our results suggest that EEG-based classifiers could improve lower-limb neuroprostheses and neurorehabilitation techniques by providing earlier detection of movement intent, which could be used in robot-assisted strategies for motor training and recovery of function.

Single trial prediction of self-paced reaching directions from EEG signals

Early detection of movement intention could possibly minimize the delays in the activation of neuroprosthetic devices. As yet, single trial analysis using non-invasive approaches for understanding such movement preparation remains a challenging task. We studied the feasibility of predicting movement directions in self-paced upper limb center-out reaching tasks, i.e., spontaneous movements executed without an external cue that can better reflect natural motor behavior in humans. We reported results of non-invasive electroencephalography (EEG) recorded from mild stroke patients and able-bodied participants. Previous studies have shown that low frequency EEG oscillations are modulated by the intent to move and therefore, can be decoded prior to the movement execution. Motivated by these results, we investigated whether slow cortical potentials (SCPs) preceding movement onset can be used to classify reaching directions and evaluated the performance using 5-fold cross-validation. For able-bodied subjects, we obtained an average decoding accuracy of 76% (chance level of 25%) at 62.5 ms before onset using the amplitude of on-going SCPs with above chance level performances between 875 to 437.5 ms prior to onset. The decoding accuracy for the stroke patients was on average 47% with their paretic arms. Comparison of the decoding accuracy across different frequency ranges (i.e., SCPs, delta, theta, alpha, and gamma) yielded the best accuracy using SCPs filtered between 0.1 to 1 Hz. Across all the subjects, including stroke subjects, the best selected features were obtained mostly from the fronto-parietal regions, hence consistent with previous neurophysiological studies on arm reaching tasks. In summary, we concluded that SCPs allow the possibility of single trial decoding of reaching directions at least 312.5 ms before onset of reach.