A two-stage four-class BCI based on imaginary movements of the left and the right wrist

TSPNet: a time-spatial parallel network for classification of EEG-based multiclass upper limb motor imagery BCI

The classification of electroencephalogram (EEG) motor imagery signals has emerged as a prominent research focus within the realm of brain-computer interfaces. Nevertheless, the conventional, limited categories (typically just two or four) offered by brain-computer interfaces fail to provide an extensive array of control modes. To address this challenge, we propose the Time-Spatial Parallel Network (TSPNet) for recognizing six distinct categories of upper limb motor imagery. Within TSPNet, temporal and spatial features are extracted separately, with the time dimension feature extractor and spatial dimension feature extractor performing their respective functions. Following this, the Time-Spatial Parallel Feature Extractor is employed to decouple the connection between temporal and spatial features, thus diminishing feature redundancy. The Time-Spatial Parallel Feature Extractor deploys a gating mechanism to optimize weight distribution and parallelize time-spatial features. Additionally, we introduce a feature visualization algorithm based on signal occlusion frequency to facilitate a qualitative analysis of TSPNet. In a six-category scenario, TSPNet achieved an accuracy of 49.1% ± 0.043 on our dataset and 49.7% ± 0.029 on a public dataset. Experimental results conclusively establish that TSPNet outperforms other deep learning methods in classifying data from these two datasets. Moreover, visualization results vividly illustrate that our proposed framework can generate distinctive classifier patterns for multiple categories of upper limb motor imagery, discerned through signals of varying frequencies. These findings underscore that, in comparison to other deep learning methods, TSPNet excels in intention recognition, which bears immense significance for non-invasive brain-computer interfaces.

Discriminating three motor imagery states of the same joint for brain-computer interface

The classification of electroencephalography (EEG) induced by the same joint is one of the major challenges for brain-computer interface (BCI) systems. In this paper, we propose a new framework, which includes two parts, feature extraction and classification. Based on local mean decomposition (LMD), cloud model, and common spatial pattern (CSP), a feature extraction method called LMD-CSP is proposed to extract distinguishable features. In order to improve the classification results multi-objective grey wolf optimization twin support vector machine (MOGWO-TWSVM) is applied to discriminate the extracted features. We evaluated the performance of the proposed framework on our laboratory data sets with three motor imagery (MI) tasks of the same joint (shoulder abduction, extension, and flexion), and the average classification accuracy was 91.27%. Further comparison with several widely used methods showed that the proposed method had better performance in feature extraction and pattern classification. Overall, this study can be used for developing high-performance BCI systems, enabling individuals to control external devices intuitively and naturally.

Time-resolved estimation of strength of motor imagery representation by multivariate EEG decoding

Objective. Multivariate decoding enables access to information encoded in multiple brain activity features with high temporal resolution. However, whether the strength, of which this information is represented in the brain, can be extracted across time within single trials remains largely unexplored.Approach.In this study, we addressed this question by applying a support vector machine (SVM) to extract motor imagery (MI) representations, from electroencephalogram (EEG) data, and by performing time-resolved single-trial analyses of the multivariate decoding. EEG was recorded from a group of healthy participants during MI of opening and closing of the same hand.Main results.Cross-temporal decoding revealed both dynamic and stationary MI-relevant features during the task. Specifically, features representing MI evolved dynamically early in the trial and later stabilized into a stationary network of MI features. Using a hierarchical genetic algorithm for selection of MI-relevant features, we identified primarily contralateral alpha and beta frequency features over the sensorimotor and parieto-occipital cortices as stationary which extended into a bilateral pattern in the later part of the trial. During the stationary encoding of MI, by extracting the SVM prediction scores, we analyzed MI-relevant EEG activity patterns with respect to the temporal dynamics within single trials. We show that the SVM prediction score correlates to the amplitude of univariate MI-relevant features (as documented from an extensive repertoire of previous MI studies) within single trials, strongly suggesting that these are functional variations of MI strength hidden in trial averages.Significance.Our work demonstrates a powerful approach for estimating MI strength continually within single trials, having far-reaching impact for single-trial analyses. In terms of MI neurofeedback for motor rehabilitation, these results set the ground for more refined neurofeedback reflecting the strength of MI that can be provided to patients continually in time.

Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression

OBJECTIVE

Due to low spatial resolution and poor signal-to-noise ratio of electroencephalogram (EEG), high accuracy classifications still suffer from lots of obstacles in the context of motor imagery (MI)-based brain-machine interface (BMI) systems. Particularly, it is extremely challenging to decode multiclass MI EEG from the same upper limb. This research proposes a novel feature learning approach to address the classification problem of 6-class MI tasks, including imaginary elbow flexion/extension, wrist supination/pronation, and hand close/open within the unilateral upper limb.

APPROACH

Instead of the traditional common spatial pattern (CSP) or filter-bank CSP (FBCSP) manner, the Riemannian geometry (RG) framework involving Riemannian distance and Riemannian mean was directly adopted to extract tangent space (TS) features from spatial covariance matrices of the MI EEG trials. Subsequently, to reduce the dimensionality of the TS features, the algorithm of partial least squares regression was applied to obtain more separable and compact feature representations.

MAIN RESULTS

The performance of the learned RG feature representations was validated by a linear discriminative analysis and support vector machine classifier, with an average accuracy of 80.50% and 79.70% on EEG dataset collected from 12 participants, respectively.

SIGNIFICANCE

These results demonstrate that compared with CSP and FBCSP features, the proposed approach can significantly increase the decoding accuracy for multiclass MI tasks from the same upper limb. This approach is promising and could potentially be applied in the context of MI-based BMI control of a robotic arm or a neural prosthesis for motor disabled patients with highly impaired upper limb.

Using machine learning to reveal the population vector from EEG signals

OBJECTIVE

Since the discovery of the population vector that directly relates neural spiking activity with arm movement direction, it has become feasible to control robotic arms and neuroprostheses using invasively recorded brain signals. For non-invasive approaches, a direct relation between human brain signals and arm movement direction is yet to be established.

APPROACH

Here, we investigated electroencephalographic (EEG) signals in temporal and spectral domains in a continuous, circular arm movement task. Using machine learning methods that respect the linear mixture of brain activity within EEG signals, we show that directional information is represented in the temporal domain in amplitude modulations of the same frequency as the arm movement, and in the spectral domain in power modulations of the 20-24 Hz frequency band.

MAIN RESULTS

In the temporal domain, the directional information was mainly expressed in primary sensorimotor cortex (SM1) and posterior parietal cortex (PPC) contralateral to the moving arm, while in the spectral domain SM1 and PPC of both hemispheres predicted arm movement direction. The different cortical representations suggest distinct neural representations in both domains.

SIGNIFICANCE

This direct relation between neural activity and arm movement direction in both domains demonstrates the potential of machine learning to reveal neuroscientific insights about the dynamics of human arm movements.

Advances in Hybrid Brain-Computer Interfaces: Principles, Design, and Applications

Conventional brain-computer interface (BCI) systems have been facing two fundamental challenges: the lack of high detection performance and the control command problem. To this end, the researchers have proposed a hybrid brain-computer interface (hBCI) to address these challenges. This paper mainly discusses the research progress of hBCI and reviews three types of hBCI, namely, hBCI based on multiple brain models, multisensory hBCI, and hBCI based on multimodal signals. By analyzing the general principles, paradigm designs, experimental results, advantages, and applications of the latest hBCI system, we found that using hBCI technology can improve the detection performance of BCI and achieve multidegree/multifunctional control, which is significantly superior to single-mode BCIs.

The contribution of different frequency bands in class separability of covert speech tasks for BCIs

Several recent studies demonstrate the possibility of using user initiated covert speech mental tasks in brain computer interfaces with varying degrees of success, but details of the best frequency features had not been investigated. In this work, ten volunteers in the age range of 22-70 years participated in the experiment. Eight of them were neurologically healthy, one user was dyslexic, and another was autistic. The four words "back", "forward", "left", and "right" were shortened into "BA", "FO", "LE", and "RY", which are phonetically dissimilar and cognitively relevant directional commands. Participants were asked to covertly speak each as soon as the letters appeared on a screen. Volunteers completed five recording runs. During each run the four words were presented in random succession to avoid sequence bias. The recorded EEG data from the ten users were analysed to discover the best features within a Gabor Transform of the signals, i.e., those yielding the highest word-pair classification accuracy for this specific type of linguistic mental activity. Using this BCI, suitable class separability of covert speech tasks is confirmed for all, including disabled users, with consistently high classification accuracy from 72% to 88% in all cases. Like motor imagery tasks, Alpha and Beta band activity were found to contain 12% and 31% of the most important features respectively. Gamma band activity, which indicates high mental functions, contains 57% of the most important features in this study.

Comparison of EEG measurement of upper limb movement in motor imagery training system

BACKGROUND

One of the most promising applications for electroencephalogram (EEG)-based brain computer interface is for stroke rehabilitation. Implemented as a standalone motor imagery (MI) training system or as part of a rehabilitation robotic system, many studies have shown benefits of using them to restore motor control in stroke patients. Hand movements have widely been chosen as MI tasks. Although potentially more challenging to analyze, wrist and forearm movement such as wrist flexion/extension and forearm pronation/supination should also be considered for MI tasks, because these movements are part of the main exercises given to patients in conventional stroke rehabilitation. This paper will evaluate the effectiveness of such movements for MI tasks.

METHODS

Three hand and wrist movement tasks which were hand opening/closing, wrist flexion/extension and forearm pronation/supination were chosen as motor imagery tasks for both hands. Eleven subjects participated in the experiment. All of them completed hand opening/closing task session. Ten subjects completed two MI task sessions which were hand opening/closing and wrist flexion/extension. Five subjects completed all three MI tasks sessions. Each MI task comprised 8 sessions spanning a 4 weeks period. For classification, feature extraction based on common spatial pattern (CSP) algorithm was used. Two types were implemented, one with conventional CSP (termed WB) and one with an increase number of features achieved by filtering EEG data into five bands (termed FB). Classification was done by linear discriminant analysis (LDA) and support vector machine (SVM).

RESULTS

Eight-fold cross validation was applied on EEG data. LDA and SVM gave comparable classification accuracy. FB achieved significantly higher classification accuracy compared to WB. The accuracy of classifying wrist flexion/extension task were higher than that of classifying hand opening/closing task in all subjects. Classifying forearm pronation/supination task achieved higher accuracy than classifying hand opening/closing task in most subjects but achieved lower accuracy than classifying wrist flexion/extension task in all subjects. Significant improvements of classification accuracy were found in nine subjects when considering individual sessions of experiments of all MI tasks. The results of classifying hand opening/closing task and wrist flexion/extension task were comparable to the results of classifying hand opening/closing task and forearm pronation/supination task. Classification accuracy of wrist flexion/extension task and forearm pronation/supination task was lower than those of hand movement tasks and wrist movement tasks.

CONCLUSION

High classification accuracy of the three MI tasks support the possibility of using EEG-based stroke rehabilitation system with these movements. Either LDA or SVM can equally be chosen as a classifier since the difference of their accuracies is not statistically significant. Significantly higher classification accuracy made FB more suitable for classifying MI task compared to WB. More training sessions could potentially lead to better accuracy as evident in most subjects in this experiment.

Design of Embedded System for Multivariate Classification of Finger and Thumb Movements Using EEG Signals for Control of Upper Limb Prosthesis

Brain Computer Interface (BCI) determines the intent of the user from a variety of electrophysiological signals. These signals, Slow Cortical Potentials, are recorded from scalp, and cortical neuronal activity is recorded by implanted electrodes. This paper is focused on design of an embedded system that is used to control the finger movements of an upper limb prosthesis using Electroencephalogram (EEG) signals. This is a follow-up of our previous research which explored the best method to classify three movements of fingers (thumb movement, index finger movement, and first movement). Two-stage logistic regression classifier exhibited the highest classification accuracy while Power Spectral Density (PSD) was used as a feature of the filtered signal. The EEG signal data set was recorded using a 14-channel electrode headset (a noninvasive BCI system) from right-handed, neurologically intact volunteers. Mu (commonly known as alpha waves) and Beta Rhythms (8-30 Hz) containing most of the movement data were retained through filtering using "Arduino Uno" microcontroller followed by 2-stage logistic regression to obtain a mean classification accuracy of 70%.

Evaluating the versatility of EEG models generated from motor imagery tasks: An exploratory investigation on upper-limb elbow-centered motor imagery tasks

Electroencephalography (EEG) has recently been considered for use in rehabilitation of people with motor deficits. EEG data from the motor imagery of different body movements have been used, for instance, as an EEG-based control method to send commands to rehabilitation devices that assist people to perform a variety of different motor tasks. However, it is both time and effort consuming to go through data collection and model training for every rehabilitation task. In this paper, we investigate the possibility of using an EEG model from one type of motor imagery (e.g.: elbow extension and flexion) to classify EEG from other types of motor imagery activities (e.g.: open a drawer). In order to study the problem, we focused on the elbow joint. Specifically, nine kinesthetic motor imagery tasks involving the elbow were investigated in twelve healthy individuals who participated in the study. While results reported that models from goal-oriented motor imagery tasks had higher accuracy than models from the simple joint tasks in intra-task testing (e.g., model from elbow extension and flexion task was tested on EEG data collected from elbow extension and flexion task), models from simple joint tasks had higher accuracies than the others in inter-task testing (e.g., model from elbow extension and flexion task tested on EEG data collected from drawer opening task). Simple single joint motor imagery tasks could, therefore, be considered for training models to potentially reduce the number of repetitive data acquisitions and model training in rehabilitation applications.

Decoding complex imagery hand gestures

Brain computer interfaces (BCIs) offer individuals suffering from major disabilities an alternative method to interact with their environment. Sensorimotor rhythm (SMRs) based BCIs can successfully perform control tasks; however, the traditional SMR paradigms intuitively disconnect the control and real task, making them non-ideal for complex control scenarios. In this study we design a new, intuitively connected motor imagery (MI) paradigm using hierarchical common spatial patterns (HCSP) and context information to effectively predict intended hand grasps from electroencephalogram (EEG) data. Experiments with 5 participants yielded an aggregate classification accuracy-intended grasp prediction probability-of 64.5% for 8 different hand gestures, more than 5 times the chance level.

Upper limb movements can be decoded from the time-domain of low-frequency EEG

How neural correlates of movements are represented in the human brain is of ongoing interest and has been researched with invasive and non-invasive methods. In this study, we analyzed the encoding of single upper limb movements in the time-domain of low-frequency electroencephalography (EEG) signals. Fifteen healthy subjects executed and imagined six different sustained upper limb movements. We classified these six movements and a rest class and obtained significant average classification accuracies of 55% (movement vs movement) and 87% (movement vs rest) for executed movements, and 27% and 73%, respectively, for imagined movements. Furthermore, we analyzed the classifier patterns in the source space and located the brain areas conveying discriminative movement information. The classifier patterns indicate that mainly premotor areas, primary motor cortex, somatosensory cortex and posterior parietal cortex convey discriminative movement information. The decoding of single upper limb movements is specially interesting in the context of a more natural non-invasive control of e.g., a motor neuroprosthesis or a robotic arm in highly motor disabled persons.

Hybrid Brain-Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

In this article, non-invasive hybrid brain-computer interface (hBCI) technologies for improving classification accuracy and increasing the number of commands are reviewed. Hybridization combining more than two modalities is a new trend in brain imaging and prosthesis control. Electroencephalography (EEG), due to its easy use and fast temporal resolution, is most widely utilized in combination with other brain/non-brain signal acquisition modalities, for instance, functional near infrared spectroscopy (fNIRS), electromyography (EMG), electrooculography (EOG), and eye tracker. Three main purposes of hybridization are to increase the number of control commands, improve classification accuracy and reduce the signal detection time. Currently, such combinations of EEG + fNIRS and EEG + EOG are most commonly employed. Four principal components (i.e., hardware, paradigm, classifiers, and features) relevant to accuracy improvement are discussed. In the case of brain signals, motor imagination/movement tasks are combined with cognitive tasks to increase active brain-computer interface (BCI) accuracy. Active and reactive tasks sometimes are combined: motor imagination with steady-state evoked visual potentials (SSVEP) and motor imagination with P300. In the case of reactive tasks, SSVEP is most widely combined with P300 to increase the number of commands. Passive BCIs, however, are rare. After discussing the hardware and strategies involved in the development of hBCI, the second part examines the approaches used to increase the number of control commands and to enhance classification accuracy. The future prospects and the extension of hBCI in real-time applications for daily life scenarios are provided.

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.

Classifying three imaginary states of the same upper extremity using time-domain features

Brain-computer interface (BCI) allows collaboration between humans and machines. It translates the electrical activity of the brain to understandable commands to operate a machine or a device. In this study, we propose a method to improve the accuracy of a 3-class BCI using electroencephalographic (EEG) signals. This BCI discriminates rest against imaginary grasps and elbow movements of the same limb. This classification task is challenging because imaginary movements within the same limb have close spatial representations on the motor cortex area. The proposed method extracts time-domain features and classifies them using a support vector machine (SVM) with a radial basis kernel function (RBF). An average accuracy of 74.2% was obtained when using the proposed method on a dataset collected, prior to this study, from 12 healthy individuals. This accuracy was higher than that obtained when other widely used methods, such as common spatial patterns (CSP), filter bank CSP (FBCSP), and band power methods, were used on the same dataset. These results are encouraging and the proposed method could potentially be used in future applications including BCI-driven robotic devices, such as a portable exoskeleton for the arm, to assist individuals with impaired upper extremity functions in performing daily tasks.

Hybrid EEG-fNIRS-Based Eight-Command Decoding for BCI: Application to Quadcopter Control

In this paper, a hybrid electroencephalography–functional near-infrared spectroscopy (EEG–fNIRS) scheme to decode eight active brain commands from the frontal brain region for brain–computer interface is presented. A total of eight commands are decoded by fNIRS, as positioned on the prefrontal cortex, and by EEG, around the frontal, parietal, and visual cortices. Mental arithmetic, mental counting, mental rotation, and word formation tasks are decoded with fNIRS, in which the selected features for classification and command generation are the peak, minimum, and mean ΔHbO values within a 2-s moving window. In the case of EEG, two eyeblinks, three eyeblinks, and eye movement in the up/down and left/right directions are used for four-command generation. The features in this case are the number of peaks and the mean of the EEG signal during 1 s window. We tested the generated commands on a quadcopter in an open space. An average accuracy of 75.6% was achieved with fNIRS for four-command decoding and 86% with EEG for another four-command decoding. The testing results show the possibility of controlling a quadcopter online and in real-time using eight commands from the prefrontal and frontal cortices via the proposed hybrid EEG–fNIRS interface.

Discriminating hand gesture motor imagery tasks using cortical current density estimation

Current EEG based brain computer interface (BCI) systems have achieved successful control in up to 3 dimensions; however the current paradigm may be unnatural for many rehabilitative and recreational applications. Therefore there is a great need to find motor imagination (MI) tasks that are realistic for output device control. In this paper we present our results on classifying hand gesture MI tasks, including right hand flexion, extension, supination and pronation using a novel EEG inverse imaging approach. By using both temporal and spatial specificity in the source domain we were able to separate MI tasks with up to 95% accuracy for binary classification of any two tasks compared to a maximum of only 79% in the sensor domain.

EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks

GOAL

Sensorimotor-based brain-computer interfaces (BCIs) have achieved successful control of real and virtual devices in up to three dimensions; however, the traditional sensor-based paradigm limits the intuitive use of these systems. Many control signals for state-of-the-art BCIs involve imagining the movement of body parts that have little to do with the output command, revealing a cognitive disconnection between the user's intent and the action of the end effector. Therefore, there is a need to develop techniques that can identify with high spatial resolution the self-modulated neural activity reflective of the actions of a helpful output device.

METHODS

We extend previous EEG source imaging (ESI) work to decoding natural hand/wrist manipulations by applying a novel technique to classifying four complex motor imaginations of the right hand: flexion, extension, supination, and pronation.

RESULTS

We report an increase of up to 18.6% for individual task classification and 12.7% for overall classification using the proposed ESI approach over the traditional sensor-based method.

CONCLUSION

ESI is able to enhance BCI performance of decoding complex right-hand motor imagery tasks.

SIGNIFICANCE

This study may lead to the development of BCI systems with naturalistic and intuitive motor imaginations, thus facilitating broad use of noninvasive BCIs.

Simultaneous channel and feature selection of fused EEG features based on Sparse Group Lasso

Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs). Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

Using a noninvasive decoding method to classify rhythmic movement imaginations of the arm in two planes

A brain-computer interface (BCI) can help to overcome movement deficits in persons with spinal-cord injury. Ideally, such a BCI detects detailed movement imaginations, i.e., trajectories, and transforms them into a control signal for a neuroprosthesis or a robotic arm restoring movement. Robotic arms have already been controlled successfully by means of invasive recording techniques, and executed movements have been reconstructed using noninvasive decoding techniques. However, it is unclear if detailed imagined movements can be decoded noninvasively using electroencephalography (EEG). We made progress toward imagined movement decoding and successfully classified horizontal and vertical imagined rhythmic movements of the right arm in healthy subjects using EEG. Notably, we used an experimental design which avoided muscle and eye movements to prevent classification results being affected. To classify imagined movements of the same limb, we decoded the movement trajectories and correlated them with assumed movement trajectories (horizontal and vertical). We then assigned the decoded movements to the assumed movements with the higher correlation. To train the decoder, we applied partial least squares, which allowed us to interpret the classifier weights although channels were highly correlated. To conclude, we showed the classification of imagined movements of one limb in two different movement planes in seven out of nine subjects. Furthermore, we found a strong involvement of the supplementary motor area. Finally, as our classifier was based on the decoding approach, we indirectly showed the decoding of imagined movements.

Decoding of four movement directions using hybrid NIRS-EEG brain-computer interface

The hybrid brain-computer interface (BCI)'s multimodal technology enables precision brain-signal classification that can be used in the formulation of control commands. In the present study, an experimental hybrid near-infrared spectroscopy-electroencephalography (NIRS-EEG) technique was used to extract and decode four different types of brain signals. The NIRS setup was positioned over the prefrontal brain region, and the EEG over the left and right motor cortex regions. Twelve subjects participating in the experiment were shown four direction symbols, namely, “forward,” “backward,” “left,” and “right.” The control commands for forward and backward movement were estimated by performing arithmetic mental tasks related to oxy-hemoglobin (HbO) changes. The left and right directions commands were associated with right and left hand tapping, respectively. The high classification accuracies achieved showed that the four different control signals can be accurately estimated using the hybrid NIRS-EEG technology.

EFFICIENT AUTOMATIC SELECTION AND COMBINATION OF EEG FEATURES IN LEAST SQUARES CLASSIFIERS FOR MOTOR IMAGERY BRAIN–COMPUTER INTERFACES

Discriminative features have to be properly extracted and selected from the electroencephalographic (EEG) signals of each specific subject in order to achieve an adaptive brain–computer interface (BCI) system. This work presents an efficient wrapper-based methodology for feature selection and least squares discrimination of high-dimensional EEG data with low computational complexity. Features are computed in different time segments using three widely used methods for motor imagery tasks and, then, they are concatenated or averaged in order to take into account the time course variability of the EEG signals. Once EEG features have been extracted, proposed framework comprises two stages. The first stage entails feature ranking and, in this work, two different procedures have been considered, the least angle regression (LARS) and the Wilcoxon rank sum test, to compare the performance of each one. The second stage selects the most relevant features using an efficient leave-one-out (LOO) estimation based on the Allen's PRESS statistic. Experimental comparisons with the state-of-the-art BCI methods shows that this approach gives better results than current state-of-the-art approaches in terms of recognition rates and computational requirements and, also with respect to the first ranking stage, it is confirmed that the LARS algorithm provides better results than the Wilcoxon rank sum test for these experiments.

Using a motor imagery questionnaire to estimate the performance of a Brain-Computer Interface based on object oriented motor imagery

OBJECTIVES

The primary objective was to test whether motor imagery (MI) questionnaires can be used to detect BCI 'illiterate'. The second objective was to test how different MI paradigms, with and without the physical presence of the goal of an action, influence a BCI classifier.

METHODS

Kinaesthetic (KI) and visual (VI) motor imagery questionnaires were administered to 30 healthy volunteers. Their EEG was recorded during a cue-based, simple imagery (SI) and goal oriented imagery (GOI).

RESULTS

The strongest correlation (Pearson r(2)=0.53, p=1.6e-5) was found between KI and SI, followed by a moderate correlation between KI and GOI (r(2)=0.33, p=0.001) and a weak correlation between VI and SI (r(2)=0.21, p=0.022) and VI and GOI (r(2)=0.17, p=0.05). Classification accuracy was similar for SI (71.1 ± 7.8%) and GOI (70.5 ± 5.9%) though corresponding classification features differed in 70% participants. Compared to SI, GOI improved the classification accuracy in 'poor' imagers while reducing the classification accuracy in 'very good' imagers.

CONCLUSION

The KI score could potentially be a useful tool to predict the performance of a MI based BCI. The physical presence of the object of an action facilitates motor imagination in 'poor' able-bodied imagers.

SIGNIFICANCE

Although this study shows results on able-bodied people, its general conclusions should be transferable to BCI based on MI for assisted rehabilitation of the upper extremities in patients.