Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG

Assessing the effectiveness of spatial PCA on SVM-based decoding of EEG data

Principal component analysis (PCA) has been widely employed for dimensionality reduction prior to multivariate pattern classification (decoding) in EEG research. The goal of the present study was to provide an evaluation of the effectiveness of PCA on decoding accuracy (using support vector machines) across a broad range of experimental paradigms. We evaluated several different PCA variations, including group-based and subject-based component decomposition and the application of Varimax rotation or no rotation. We also varied the numbers of PCs that were retained for the decoding analysis. We evaluated the resulting decoding accuracy for seven common event-related potential components (N170, mismatch negativity, N2pc, P3b, N400, lateralized readiness potential, and error-related negativity). We also examined more challenging decoding tasks, including decoding of face identity, facial expression, stimulus location, and stimulus orientation. The datasets also varied in the number and density of electrode sites. Our findings indicated that none of the PCA approaches consistently improved decoding performance related to no PCA, and the application of PCA frequently reduced decoding performance. Researchers should therefore be cautious about using PCA prior to decoding EEG data from similar experimental paradigms, populations, and recording setups.

Rate control deficits during pinch grip and ankle dorsiflexion in early-stage Parkinson's disease

BACKGROUND

Much of our understanding of the deficits in force control in Parkinson's disease (PD) relies on findings in the upper extremity. Currently, there is a paucity of data pertaining to the effect of PD on lower limb force control.

OBJECTIVE

The purpose of this study was to concurrently evaluate upper- and lower-limb force control in early-stage PD and a group of age- and gender-matched healthy controls.

METHODS

Twenty individuals with PD and twenty-one healthy older adults participated in this study. Participants performed two visually guided, submaximal (15% of maximum voluntary contractions) isometric force tasks: a pinch grip task and an ankle dorsiflexion task. PD were tested on their more affected side and after overnight withdrawal from antiparkinsonian medication. The tested side in controls was randomized. Differences in force control capacity were assessed by manipulating speed-based and variability-based task parameters.

RESULTS

Compared with controls, PD demonstrated slower rates of force development and force relaxation during the foot task, and a slower rate of relaxation during the hand task. Force variability was similar across groups but greater in the foot than in the hand in both PD and controls. Lower limb rate control deficits were greater in PD with more severe symptoms based on the Hoehn and Yahr stage.

CONCLUSIONS

Together, these results provide quantitative evidence of an impaired capacity in PD to produce submaximal and rapid force across multiple effectors. Moreover, results suggest that force control deficits in the lower limb may become more severe with disease progression.

Decoding continuous variables from event-related potential (ERP) data with linear support vector regression using the Decision Decoding Toolbox (DDTBOX)

Multivariate classification analysis for event-related potential (ERP) data is a powerful tool for predicting cognitive variables. However, classification is often restricted to categorical variables and under-utilises continuous data, such as response times, response force, or subjective ratings. An alternative approach is support vector regression (SVR), which uses single-trial data to predict continuous variables of interest. In this tutorial-style paper, we demonstrate how SVR is implemented in the Decision Decoding Toolbox (DDTBOX). To illustrate in more detail how results depend on specific toolbox settings and data features, we report results from two simulation studies resembling real EEG data, and one real ERP-data set, in which we predicted continuous variables across a range of analysis parameters. Across all studies, we demonstrate that SVR is effective for analysis windows ranging from 2 to 100 ms, and relatively unaffected by temporal averaging. Prediction is still successful when only a small number of channels encode true information, and the analysis is robust to temporal jittering of the relevant information in the signal. Our results show that SVR as implemented in DDTBOX can reliably predict continuous, more nuanced variables, which may not be well-captured by classification analysis. In sum, we demonstrate that linear SVR is a powerful tool for the investigation of single-trial EEG data in relation to continuous variables, and we provide practical guidance for users.

Pseudo-online detection and classification for upper-limb movements

Objective. This study analyzed detection (movement vs. non-movement) and classification (different types of movements) to decode upper-limb movement volitions in a pseudo-online fashion.Approach. Nine healthy subjects executed four self-initiated movements: left wrist extension, right wrist extension, left index finger extension, and right index finger extension. For detection, we investigated the performance of three individual classifiers (support vector machine (SVM), EEGNET, and Riemannian geometry featured SVM) on three frequency bands (0.05-5 Hz, 5-40 Hz, 0.05-40 Hz). The best frequency band and the best classifier combinations were constructed to realize an ensemble processing pipeline using majority voting. For classification, we used adaptive boosted Riemannian geometry model to differentiate contra-lateral and ipsilateral movements.Main results. The ensemble model achieved 79.6 ± 8.8% true positive rate and 3.1 ± 1.2 false positives per minute with 75.3 ± 112.6 ms latency on a pseudo-online detection task. The following classification gave around 67% accuracy to differentiate contralateral movements.Significance. The newly proposed ensemble method and pseudo-online testing procedure could provide a robust brain-computer interface design for movement decoding.

Detection of Movement Intention in EEG-Based Brain-Computer Interfaces Using Fourier-Based Synchrosqueezing Transform

Patients with motor impairments need caregivers' help to initiate the operation of brain-computer interfaces (BCI). This study aims to identify and characterize movement intention using multichannel electroencephalography (EEG) signals as a means to initiate BCI systems without extra accessories/methodologies. We propose to discriminate the resting and motor imagery (MI) states with high accuracy using Fourier-based synchrosqueezing transform (FSST) as a feature extractor. FSST has been investigated and compared with other popular approaches in 28 healthy subjects for a total of 6657 trials. The accuracy and f-measure values were obtained as 99.8% and 0.99, respectively, when FSST was used as the feature extractor and singular value decomposition (SVD) as the feature selection method and support vector machines as the classifier. Moreover, this study investigated the use of data that contain certain amount of noise without any preprocessing in addition to the clean counterparts. Furthermore, the statistical analysis of EEG channels with the best discrimination (of resting and MI states) characteristics demonstrated that F4-Fz-C3-Cz-C4-Pz channels and several statistical features had statistical significance levels, [Formula: see text], less than 0.05. This study showed that the preparation of the movement can be detected in real-time employing FSST-SVD combination and several channels with minimal pre-processing effort.

Predicting motor behavior: an efficient EEG signal processing pipeline to detect brain states with potential therapeutic relevance for VR-based neurorehabilitation

Virtual reality (VR)-based motor therapy is an emerging approach in neurorehabilitation. The combination of VR with electroencephalography (EEG) presents further opportunities to improve therapeutic efficacy by personalizing the paradigm. Specifically, the idea is to synchronize the choice and timing of stimuli in the perceived virtual world with fluctuating brain states relevant to motor behavior. Here, we present an open source EEG single-trial based classification pipeline that is designed to identify ongoing brain states predictive of the planning and execution of movements. 9 healthy volunteers each performed 1080 trials of a repetitive reaching task with an implicit two-alternative forced choice, i.e., use of the right or left hand, in response to the appearance of a visual target. The performance of the EEG decoding pipeline was assessed with respect to classification accuracy of right vs. left arm use, based on the EEG signal at the time of the stimulus. Different features, feature extraction methods, and classifiers were compared at different time windows; the number and location of informative EEG channels and the number of calibration trials needed were also quantified, as well as any benefits from individual-level optimization of pipeline parameters. This resulted in a set of recommended parameters that achieved an average 83.3% correct prediction on never-before-seen testing data, and a state-of-the-art 77.1% in a real-time simulation. Neurophysiological plausibility of the resulting classifiers was assessed by time-frequency and event-related potential analyses, as well as by Independent Component Analysis topographies and cortical source localization. We expect that this pipeline will facilitate the identification of relevant brain states as prospective therapeutic targets in closed-loop EEG-VR motor neurorehabilitation.

Influential Factors of an Asynchronous BCI for Movement Intention Detection

In recent years, asynchronous brain computer interface (BCI) systems have been utilized in many domains such as robot controlling, assistive technology, and rehabilitation. In such BCI systems, movement intention detection algorithms are used to detect movement desires. In recent years, movement-related cortical potential (MRCP), an electroencephalogram (EEG) pattern representing voluntary movement intention, attracts wide attention in movement intention detection. Unfortunately, low MRCP detection accuracy makes the asynchronous BCI system impractical for real usage. In order to develop an effective MRCP detection algorithm, EEG data have to be properly preprocessed. In this work, we investigate the relationship and effects of three factors including frequency bands, spatial filters, and classifiers on MRCP classification performance to determine best settings. In particular, we performed a systematic performance investigation on combinations of five frequency bands, five spatial filters, and six classifiers. The EEG data were acquired from subjects performing series of self-paced ankle dorsiflexions. Analysis of variance (ANOVA) statistical test was performed on F1 scores to investigate effects of these three factors. The results show that frequency bands and spatial filters depend on each other. The combinations directly affect the F1 scores, so they have to be chosen carefully. The results can be used as guidelines for BCI researchers to effectively design a preprocessing method for an advanced asynchronous BCI system, which can assist the stroke rehabilitation.

Decoding kinetic features of hand motor preparation from single-trial EEG using convolutional neural networks

Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Predicting specific movement features, such as speed and force, before movement execution may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved classification accuracies at or slightly above chance levels, highlighting the need for more accurate prediction strategies. Thus, the aims of this study were to accurately predict hand movement speed and force from single-trial EEG signals and to decode neurophysiological information of motor preparation from the prediction strategies. To these ends, a decoding model based on convolutional neural networks (ConvNets) was implemented and compared against other state-of-the-art prediction strategies, such as support vector machines and decision trees. ConvNets outperformed the other prediction strategies, achieving an overall accuracy of 84% in the classification of two different levels of speed and force (four-class classification) from pre-movement single-trial EEG (100 ms and up to 1,600 ms prior to movement execution). Furthermore, an analysis of the ConvNet architectures suggests that the network performs a complex spatiotemporal integration of EEG data to optimize classification accuracy. These results show that movement speed and force can be accurately predicted from single-trial EEG, and that the prediction strategies may provide useful neurophysiological information about motor preparation.

EEG Headset Evaluation for Detection of Single-Trial Movement Intention for Brain-Computer Interfaces

Brain-computer interfaces (BCIs) can be used in neurorehabilitation; however, the literature about transferring the technology to rehabilitation clinics is limited. A key component of a BCI is the headset, for which several options are available. The aim of this study was to test four commercially available headsets' ability to record and classify movement intentions (movement-related cortical potentials-MRCPs). Twelve healthy participants performed 100 movements, while continuous EEG was recorded from the headsets on two different days to establish the reliability of the measures: classification accuracies of single-trials, number of rejected epochs, and signal-to-noise ratio. MRCPs could be recorded with the headsets covering the motor cortex, and they obtained the best classification accuracies (73%-77%). The reliability was moderate to good for the best headset (a gel-based headset covering the motor cortex). The results demonstrate that, among the evaluated headsets, reliable recordings of MRCPs require channels located close to the motor cortex and potentially a gel-based headset.

Prediction of gait intention from pre-movement EEG signals: a feasibility study

BACKGROUND

Prediction of Gait intention from pre-movement Electroencephalography (EEG) signals is a vital step in developing a real-time Brain-computer Interface (BCI) for a proper neuro-rehabilitation system. In that respect, this paper investigates the feasibility of a fully predictive methodology to detect the intention to start and stop a gait cycle by utilizing EEG signals obtained before the event occurrence.

METHODS

An eight-channel, custom-made, EEG system with electrodes placed around the sensorimotor cortex was used to acquire EEG data from six healthy subjects and two amputees. A discrete wavelet transform-based method was employed to capture event related information in alpha and beta bands in the time-frequency domain. The Hjorth parameters, namely activity, mobility, and complexity, were extracted as features while a two-sample unpaired Wilcoxon test was used to get rid of redundant features for better classification accuracy. The feature set thus obtained was then used to classify between 'walk vs. stop' and 'rest vs. start' classes using support vector machine (SVM) classifier with RBF kernel in a ten-fold cross-validation scheme.

RESULTS

Using a fully predictive intention detection system, 76.41±4.47% accuracy, 72.85±7.48% sensitivity, and 79.93±5.50% specificity were achieved for 'rest vs. start' classification. While for 'walk vs. stop' classification, the obtained mean accuracy, sensitivity, and specificity were 74.12±4.12%, 70.24±6.45%, and 77.78±7.01% respectively. Overall average True Positive Rate achieved by this methodology was 72.06±8.27% with 1.45 False Positives/min.

CONCLUSION

Extensive simulations and resulting classification results show that it is possible to achieve statistically similar intention detection accuracy using either only pre-movement EEG features or trans-movement EEG features. The classifier performance shows the potential of the proposed methodology to predict human movement intention exclusively from the pre-movement EEG signal to be applied in real-life prosthetic and neuro-rehabilitation systems.

Induced Beta Power Modulations during Isochronous Auditory Beats Reflect Intentional Anticipation before Gradual Tempo Changes

Induced beta-band power modulations in auditory and motor-related brain areas have been associated with automatic temporal processing of isochronous beats and explicit, temporally-oriented attention. Here, we investigated how explicit top-down anticipation before upcoming tempo changes, a sustained process commonly required during music performance, changed beta power modulations during listening to isochronous beats. Musicians’ electroencephalograms were recorded during the task of anticipating accelerating, decelerating, or steady beats after direction-specific visual cues. In separate behavioural testing for tempo-change onset detection, such cues were found to facilitate faster responses, thus effectively inducing high-level anticipation. In the electroencephalograms, periodic beta power reductions in a frontocentral topographic component with seed-based source contributions from auditory and sensorimotor cortices were apparent after isochronous beats with anticipation in all conditions, generally replicating patterns found previously during passive listening to isochronous beats. With anticipation before accelerations, the magnitude of the power reduction was significantly weaker than in the steady condition. Between the accelerating and decelerating conditions, no differences were found, suggesting that the observed beta patterns may represent an aspect of high-level anticipation common before both tempo changes, like increased attention. Overall, these results indicate that top-down anticipation influences ongoing auditory beat processing in beta-band networks.

The Decision Decoding ToolBOX (DDTBOX) - A Multivariate Pattern Analysis Toolbox for Event-Related Potentials

In recent years, neuroimaging research in cognitive neuroscience has increasingly used multivariate pattern analysis (MVPA) to investigate higher cognitive functions. Here we present DDTBOX, an open-source MVPA toolbox for electroencephalography (EEG) data. DDTBOX runs under MATLAB and is well integrated with the EEGLAB/ERPLAB and Fieldtrip toolboxes (Delorme and Makeig 2004; Lopez-Calderon and Luck 2014; Oostenveld et al. 2011). It trains support vector machines (SVMs) on patterns of event-related potential (ERP) amplitude data, following or preceding an event of interest, for classification or regression of experimental variables. These amplitude patterns can be extracted across space/electrodes (spatial decoding), time (temporal decoding), or both (spatiotemporal decoding). DDTBOX can also extract SVM feature weights, generate empirical chance distributions based on shuffled-labels decoding for group-level statistical testing, provide estimates of the prevalence of decodable information in the population, and perform a variety of corrections for multiple comparisons. It also includes plotting functions for single subject and group results. DDTBOX complements conventional analyses of ERP components, as subtle multivariate patterns can be detected that would be overlooked in standard analyses. It further allows for a more explorative search for information when no ERP component is known to be specifically linked to a cognitive process of interest. In summary, DDTBOX is an easy-to-use and open-source toolbox that allows for characterising the time-course of information related to various perceptual and cognitive processes. It can be applied to data from a large number of experimental paradigms and could therefore be a valuable tool for the neuroimaging community.

To Explore the Potentials of Independent Component Analysis in Brain-Computer Interface of Motor Imagery

This paper is focused on the experimental approach to explore the potential of independent component analysis (ICA) in the context of motor imagery (MI)-based brain-computer interface (BCI). We presented a simple and efficient algorithmic framework of ICA-based MI BCI (ICA-MIBCI) for the evaluation of four classical ICA algorithms (Infomax, FastICA, Jade, and Sobi) as well as a simplified Infomax (sInfomax). Two novel performance indexes, self-test accuracy and the number of invalid ICA filters, were employed to assess the performance of MIBCI based on different ICA variants. As a reference method, common spatial pattern (CSP), a commonly-used spatial filtering method, was employed for the comparative study between ICA-MIBCI and CSP-MIBCI. The experimental results showed that sInfomax-based spatial filters exhibited significantly better transferability in session to session and subject to subject transfer as compared to CSP-based spatial filters. The online experiment was also introduced to demonstrate the practicability and feasibility of sInfomax-based MIBCI. However, four classical ICA variants, especially FastICA, Jade, and Sobi, performed much worse as compared to sInfomax and CSP in terms of classification accuracy and stability. We consider that conventional ICA-based spatial filtering methods tend to be overfitting while applied to real-life electroencephalogram data. Nevertheless, the sInfomax-based experimental results indicate that ICA methods have a great space for improvement in the application of MIBCI. We believe that this paper could bring forth new ideas for the practical implementation of ICA-MIBCI.

Effective Synchronization of EEG and EMG for Mobile Brain/Body Imaging in Clinical Settings

Mobile Brain/Body Imaging (MoBI) is rapidly gaining traction as a new imaging modality to study how cognitive processes support locomotion. Electroencephalogram (EEG) and electromyogram (EMG), due to their time resolution, non-invasiveness and portability are the techniques of choice for MoBI, but synchronization requirements among others restrict its use to high-end research facilities. Here we test the effectiveness of a technique that enables us to achieve MoBI-grade synchronization of EEG and EMG, even when other strategies (such as Lab Streaming Layer (LSL)) cannot be used e.g., due to the unavailability of proprietary Application Programming Interfaces (APIs), which is often the case in clinical settings. The proposed strategy is that of aligning several spikes at the beginning and end of the session. We delivered a train of spikes to the EEG amplifier and EMG electrodes every 2 s over a 10-min time period. We selected a variable number of spikes (from 1 to 10) both at the beginning and end of the time series and linearly resampled the data so as to align them. We then compared the misalignment of the "middle" spikes over the whole recording to test for jitter and synchronization drifts, highlighting possible nonlinearities (due to hardware filters) and estimated the maximum length of the recording to achieve a [-5 to 5] ms misalignment range. We demonstrate that MoBI-grade synchronization can be achieved within 10-min recordings with a 1.7 ms jitter and [-5 5] ms misalignment range. We show that repeated spike delivery can be used to test online synchronization options and to troubleshoot synchronization issues over EEG and EMG. We also show that synchronization cannot rely only on the equipment sampling rate advertised by manufacturers. The synchronization strategy described can be used virtually in every clinical environment, and may increase the interest among a broader spectrum of clinicians and researchers in the MoBI framework, ultimately leading to a better understanding of the brain processes underlying locomotion control and the development of more effective rehabilitation approaches.

Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent

The aim of this work was to design a personalized BCI model to detect pedaling intention through EEG signals. The approach sought to select the best among many possible BCI models for each subject. The choice was between different processing windows, feature extraction algorithms and electrode configurations. Moreover, data was analyzed offline and pseudo-online (in a way suitable for real-time applications), with a preference for the latter case. A process for selecting the best BCI model was described in detail. Results for the pseudo-online processing with the best BCI model of each subject were on average 76.7% of true positive rate, 4.94 false positives per minute and 55.1% of accuracy. The personalized BCI model approach was also found to be significantly advantageous when compared to the typical approach of using a fixed feature extraction algorithm and electrode configuration. The resulting approach could be used to more robustly interface with lower limb exoskeletons in the context of the rehabilitation of stroke patients.

Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction: a review

Support vector machines (SVMs) are widely used classifiers for detecting physiological patterns in human-computer interaction (HCI). Their success is due to their versatility, robustness and large availability of free dedicated toolboxes. Frequently in the literature, insufficient details about the SVM implementation and/or parameters selection are reported, making it impossible to reproduce study analysis and results. In order to perform an optimized classification and report a proper description of the results, it is necessary to have a comprehensive critical overview of the applications of SVM. The aim of this paper is to provide a review of the usage of SVM in the determination of brain and muscle patterns for HCI, by focusing on electroencephalography (EEG) and electromyography (EMG) techniques. In particular, an overview of the basic principles of SVM theory is outlined, together with a description of several relevant literature implementations. Furthermore, details concerning reviewed papers are listed in tables and statistics of SVM use in the literature are presented. Suitability of SVM for HCI is discussed and critical comparisons with other classifiers are reported.

A Fully Automated Trial Selection Method for Optimization of Motor Imagery Based Brain-Computer Interface

Independent component analysis (ICA) as a promising spatial filtering method can separate motor-related independent components (MRICs) from the multichannel electroencephalogram (EEG) signals. However, the unpredictable burst interferences may significantly degrade the performance of ICA-based brain-computer interface (BCI) system. In this study, we proposed a new algorithm frame to address this issue by combining the single-trial-based ICA filter with zero-training classifier. We developed a two-round data selection method to identify automatically the badly corrupted EEG trials in the training set. The "high quality" training trials were utilized to optimize the ICA filter. In addition, we proposed an accuracy-matrix method to locate the artifact data segments within a single trial and investigated which types of artifacts can influence the performance of the ICA-based MIBCIs. Twenty-six EEG datasets of three-class motor imagery were used to validate the proposed methods, and the classification accuracies were compared with that obtained by frequently used common spatial pattern (CSP) spatial filtering algorithm. The experimental results demonstrated that the proposed optimizing strategy could effectively improve the stability, practicality and classification performance of ICA-based MIBCI. The study revealed that rational use of ICA method may be crucial in building a practical ICA-based MIBCI system.

A Review of Techniques for Detection of Movement Intention Using Movement-Related Cortical Potentials

The movement-related cortical potential (MRCP) is a low-frequency negative shift in the electroencephalography (EEG) recording that takes place about 2 seconds prior to voluntary movement production. MRCP replicates the cortical processes employed in planning and preparation of movement. In this study, we recapitulate the features such as signal's acquisition, processing, and enhancement and different electrode montages used for EEG data recoding from different studies that used MRCPs to predict the upcoming real or imaginary movement. An authentic identification of human movement intention, accompanying the knowledge of the limb engaged in the performance and its direction of movement, has a potential implication in the control of external devices. This information could be helpful in development of a proficient patient-driven rehabilitation tool based on brain-computer interfaces (BCIs). Such a BCI paradigm with shorter response time appears more natural to the amputees and can also induce plasticity in brain. Along with different training schedules, this can lead to restoration of motor control in stroke patients.

A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery

This work describes a generalized method for classifying motor-related neural signals for a brain-computer interface (BCI), based on a stochastic machine learning method. The method differs from the various feature extraction and selection techniques employed in many other BCI systems. The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge. Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure. The results showed that the average performance of the new algorithm outperformed other published methods using the Berlin BCI IV (2008) competition dataset and was comparable to the best results in the Berlin BCI II (2002–3) competition dataset. The new method was also applied to electroencephalography (EEG) data recorded from five subjects undertaking a hand squeeze task and demonstrated high levels of accuracy with a mean classification accuracy of 78.9% after five-fold cross-validation. Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

Comparison of Features for Movement Prediction from Single-Trial Movement-Related Cortical Potentials in Healthy Subjects and Stroke Patients

Detection of movement intention from the movement-related cortical potential (MRCP) derived from the electroencephalogram (EEG) signals has shown to be important in combination with assistive devices for effective neurofeedback in rehabilitation. In this study, we compare time and frequency domain features to detect movement intention from EEG signals prior to movement execution. Data were recoded from 24 able-bodied subjects, 12 performing real movements, and 12 performing imaginary movements. Furthermore, six stroke patients with lower limb paresis were included. Temporal and spectral features were investigated in combination with linear discriminant analysis and compared with template matching. The results showed that spectral features were best suited for differentiating between movement intention and noise across different tasks. The ensemble average across tasks when using spectral features was (error = 3.4 ± 0.8%, sensitivity = 97.2 ± 0.9%, and specificity = 97 ± 1%) significantly better (P < 0.01) than temporal features (error = 15 ± 1.4%, sensitivity: 85 ± 1.3%, and specificity: 84 ± 2%). The proposed approach also (error = 3.4 ± 0.8%) outperformed template matching (error = 26.9 ± 2.3%) significantly (P > 0.001). Results imply that frequency information is important for detecting movement intention, which is promising for the application of this approach to provide patient-driven real-time neurofeedback.

Predictive classification of self-paced upper-limb analytical movements with EEG

The extent to which the electroencephalographic activity allows the characterization of movements with the upper limb is an open question. This paper describes the design and validation of a classifier of upper-limb analytical movements based on electroencephalographic activity extracted from intervals preceding self-initiated movement tasks. Features selected for the classification are subject specific and associated with the movement tasks. Further tests are performed to reject the hypothesis that other information different from the task-related cortical activity is being used by the classifiers. Six healthy subjects were measured performing self-initiated upper-limb analytical movements. A Bayesian classifier was used to classify among seven different kinds of movements. Features considered covered the alpha and beta bands. A genetic algorithm was used to optimally select a subset of features for the classification. An average accuracy of 62.9 ± 7.5% was reached, which was above the baseline level observed with the proposed methodology (30.2 ± 4.3%). The study shows how the electroencephalography carries information about the type of analytical movement performed with the upper limb and how it can be decoded before the movement begins. In neurorehabilitation environments, this information could be used for monitoring and assisting purposes.

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.

Distributed patterns of event-related potentials predict subsequent ratings of abstract stimulus attributes

Exposure to pleasant and rewarding visual stimuli can bias people's choices towards either immediate or delayed gratification. We hypothesised that this phenomenon might be based on carry-over effects from a fast, unconscious assessment of the abstract 'time reference' of a stimuli, i.e. how the stimulus relates to one's personal understanding and connotation of time. Here we investigated whether participants' post-experiment ratings of task-irrelevant, positive background visual stimuli for the dimensions 'arousal' (used as a control condition) and 'time reference' were related to differences in single-channel event-related potentials (ERPs) and whether they could be predicted from spatio-temporal patterns of ERPs. Participants performed a demanding foreground choice-reaction task while on each trial one task-irrelevant image (depicting objects, people and scenes) was presented in the background. Conventional ERP analyses as well as multivariate support vector regression (SVR) analyses were conducted to predict participants' subsequent ratings. We found that only SVR allowed both 'arousal' and 'time reference' ratings to be predicted during the first 200 ms post-stimulus. This demonstrates an early, automatic semantic stimulus analysis, which might be related to the high relevance of 'time reference' to everyday decision-making and preference formation.

Assessment of cognitive engagement in stroke patients from single-trial EEG during motor rehabilitation

We propose a novel method for monitoring cognitive engagement in stroke patients during motor rehabilitation. Active engagement reflects implicit motivation and can enhance motor recovery. In this study, we used electroencephalography (EEG) to assess cognitive engagement in 11 chronic stroke patients while they executed active and passive motor tasks involving grasping and supination hand movements. We observed that the active motor task induced larger event-related desynchronization (ERD) than the passive task in the bilateral motor cortex and supplementary motor area (SMA). ERD differences between tasks were observed during both initial and post-movement periods . Additionally, differences in beta band activity were larger than differences in mu band activity . EEG data was used to help classify each trial as involving the active or passive motor task. Average classification accuracy was 80.7 ±0.1% for grasping movement and 82.8 ±0.1% for supination movement. Classification accuracy using a combination of movement and post-movement periods was higher than in other cases . Our results support using EEG to assess cognitive engagement in stroke patients during motor rehabilitation.

Enhanced low-latency detection of motor intention from EEG for closed-loop brain-computer interface applications

In recent years, the detection of voluntary motor intentions from electroencephalogram (EEG) has been used for triggering external devices in closed-loop brain-computer interface (BCI) research. Movement-related cortical potentials (MRCP), a type of slow cortical potentials, have been recently used for detection. In order to enhance the efficacy of closed-loop BCI systems based on MRCPs, a manifold method called Locality Preserving Projection, followed by a linear discriminant analysis (LDA) classifier (LPP-LDA) is proposed in this paper to detect MRCPs from scalp EEG in real time. In an online experiment on nine healthy subjects, LPP-LDA statistically outperformed the classic matched filter approach with greater true positive rate (79 ± 11% versus 68 ± 10%; p = 0.007) and less false positives (1.4 ± 0.8/min versus 2.3 ± 1.1/min; p = 0.016 ). Moreover, the proposed system performed detections with significantly shorter latency (315 ± 165 ms versus 460 ± 123 ms; p = 0.013), which is a fundamental characteristics to induce neuroplastic changes in closed-loop BCIs, following the Hebbian principle. In conclusion, the proposed system works as a generic brain switch, with high accuracy, low latency, and easy online implementation. It can thus be used as a fundamental element of BCI systems for neuromodulation and motor function rehabilitation.

Detection of the onset of upper-limb movements based on the combined analysis of changes in the sensorimotor rhythms and slow cortical potentials

OBJECTIVE

Characterizing the intention to move by means of electroencephalographic activity can be used in rehabilitation protocols with patients' cortical activity taking an active role during the intervention. In such applications, the reliability of the intention estimation is critical both in terms of specificity 'number of misclassifications' and temporal accuracy. Here, a detector of the onset of voluntary upper-limb reaching movements based on the cortical rhythms and the slow cortical potentials is proposed. The improvement in detections due to the combination of these two cortical patterns is also studied.

APPROACH

Upper-limb movements and cortical activity were recorded in healthy subjects and stroke patients performing self-paced reaching movements. A logistic regression combined the output of two classifiers: (i) a naïve Bayes classifier trained to detect the event-related desynchronization preceding the movement onset and (ii) a matched filter detecting the bereitschaftspotential. The proposed detector was compared with the detectors by using each one of these cortical patterns separately. In addition, differences between the patients and healthy subjects were analysed.

MAIN RESULTS

On average, 74.5 ± 13.8% and 82.2 ± 10.4% of the movements were detected with 1.32 ± 0.87 and 1.50 ± 1.09 false detections generated per minute in the healthy subjects and the patients, respectively. A significantly better performance was achieved by the combined detector (as compared to the detectors of the two cortical patterns separately) in terms of true detections (p = 0.099) and false positives (p = 0.0083).

SIGNIFICANCE

A rationale is provided for combining information from cortical rhythms and slow cortical potentials to detect the onsets of voluntary upper-limb movements. It is demonstrated that the two cortical processes supply complementary information that can be summed up to boost the performance of the detector. Successful results have been also obtained with stroke patients, which supports the use of the proposed system in brain-computer interface applications with this group of patients.

Movement type prediction before its onset using signals from prefrontal area: an electrocorticography study

Power changes in specific frequency bands are typical brain responses during motor planning or preparation. Many studies have demonstrated that, in addition to the premotor, supplementary motor, and primary sensorimotor areas, the prefrontal area contributes to generating such responses. However, most brain-computer interface (BCI) studies have focused on the primary sensorimotor area and have estimated movements using postonset period brain signals. Our aim was to determine whether the prefrontal area could contribute to the prediction of voluntary movement types before movement onset. In our study, electrocorticography (ECoG) was recorded from six epilepsy patients while performing two self-paced tasks: hand grasping and elbow flexion. The prefrontal area was sufficient to allow classification of different movements through the area's premovement signals (−2.0 s to 0 s) in four subjects. The most pronounced power difference frequency band was the beta band (13–30 Hz). The movement prediction rate during single trial estimation averaged 74% across the six subjects. Our results suggest that premovement signals in the prefrontal area are useful in distinguishing different movement tasks and that the beta band is the most informative for prediction of movement type before movement onset.

Decoding individual finger movements from one hand using human EEG signals

Brain computer interface (BCI) is an assistive technology, which decodes neurophysiological signals generated by the human brain and translates them into control signals to control external devices, e.g., wheelchairs. One problem challenging noninvasive BCI technologies is the limited control dimensions from decoding movements of, mainly, large body parts, e.g., upper and lower limbs. It has been reported that complicated dexterous functions, i.e., finger movements, can be decoded in electrocorticography (ECoG) signals, while it remains unclear whether noninvasive electroencephalography (EEG) signals also have sufficient information to decode the same type of movements. Phenomena of broadband power increase and low-frequency-band power decrease were observed in EEG in the present study, when EEG power spectra were decomposed by a principal component analysis (PCA). These movement-related spectral structures and their changes caused by finger movements in EEG are consistent with observations in previous ECoG study, as well as the results from ECoG data in the present study. The average decoding accuracy of 77.11% over all subjects was obtained in classifying each pair of fingers from one hand using movement-related spectral changes as features to be decoded using a support vector machine (SVM) classifier. The average decoding accuracy in three epilepsy patients using ECoG data was 91.28% with the similarly obtained features and same classifier. Both decoding accuracies of EEG and ECoG are significantly higher than the empirical guessing level (51.26%) in all subjects (p<0.05). The present study suggests the similar movement-related spectral changes in EEG as in ECoG, and demonstrates the feasibility of discriminating finger movements from one hand using EEG. These findings are promising to facilitate the development of BCIs with rich control signals using noninvasive technologies.

Individual EEG differences in affective valence processing in women with low and high neuroticism

OBJECTIVE

In this study, individual differences in brain electrophysiology during positive and negative affective valence processing in women with different neuroticism scores are quantified.

METHODS

Twenty-six women scoring high and low on neuroticism participated on this experiment. A support vector machine (SVM)-based classifier was applied on the EEG single trials elicited by high arousal pictures with negative and positive valence scores. Based on the accuracy values obtained from subject identification tasks, the most distinguishing EEG channels among participants were detected, pointing which scalp regions show more distinct patterns.

RESULTS

Significant differences were obtained, in the EEG heterogeneity between positive and negative valence stimuli, yielding higher accuracy in subject identification using negative pictures. Regarding the topographical analysis, significantly higher accuracy values were reached in occipital areas and in the right hemisphere (p < 0.001).

CONCLUSIONS

Mainly, individual differences in EEG can be located in parietooccipital regions. These differences are likely to be due to the different reactivity and coping strategies to unpleasant stimuli in individuals with high neuroticism. In addition, the right hemisphere shows a greater individual specificity.

SIGNIFICANCE

An SVM-based classifier asserts the individual specificity and its topographical differences in electrophysiological activity for women with high neuroticism compared to low neuroticism.

What we think before a voluntary movement

A central feature of voluntary movement is the sense of volition, but when this sense arises in the course of movement formulation and execution is not clear. Many studies have explored how the brain might be actively preparing movement before the sense of volition; however, because the timing of the sense of volition has depended on subjective and retrospective judgments, these findings are still regarded with a degree of scepticism. EEG events such as beta event-related desynchronization and movement-related cortical potentials are associated with the brain's programming of movement. Using an optimized EEG signal derived from multiple variables, we were able to make real-time predictions of movements in advance of their occurrence with a low false-positive rate. We asked participants what they were thinking at the time of prediction: Sometimes they were thinking about movement, and other times they were not. Our results indicate that the brain can be preparing to make voluntary movements while participants are thinking about something else.

Predicting perceptual decision biases from early brain activity

Perceptual decision making is believed to be driven by the accumulation of sensory evidence following stimulus encoding. More controversially, some studies report that neural activity preceding the stimulus also affects the decision process. We used a multivariate pattern classification approach for the analysis of the human electroencephalogram (EEG) to decode choice outcomes in a perceptual decision task from spatially and temporally distributed patterns of brain signals. When stimuli provided discriminative information, choice outcomes were predicted by neural activity following stimulus encoding; when stimuli provided no discriminative information, choice outcomes were predicted by neural activity preceding the stimulus. Moreover, in the absence of discriminative information, the recent choice history primed the choices on subsequent trials. A diffusion model fitted to the choice probabilities and response time distributions showed that the starting point of the evidence accumulation process was shifted toward the previous choice, consistent with the hypothesis that choice priming biases the accumulation process toward a decision boundary. This bias is reflected in prestimulus brain activity, which, in turn, becomes predictive of future decisions. Our results provide a model of how non-stimulus-driven decision making in humans could be accomplished on a neural level.

Detection of self-paced reaching movement intention from EEG signals

Future neuroprosthetic devices, in particular upper limb, will require decoding and executing not only the user's intended movement type, but also when the user intends to execute the movement. This work investigates the potential use of brain signals recorded non-invasively for detecting the time before a self-paced reaching movement is initiated which could contribute to the design of practical upper limb neuroprosthetics. In particular, we show the detection of self-paced reaching movement intention in single trials using the readiness potential, an electroencephalography (EEG) slow cortical potential (SCP) computed in a narrow frequency range (0.1–1 Hz). Our experiments with 12 human volunteers, two of them stroke subjects, yield high detection rates prior to the movement onset and low detection rates during the non-movement intention period. With the proposed approach, movement intention was detected around 500 ms before actual onset, which clearly matches previous literature on readiness potentials. Interestingly, the result obtained with one of the stroke subjects is coherent with those achieved in healthy subjects, with single-trial performance of up to 92% for the paretic arm. These results suggest that, apart from contributing to our understanding of voluntary motor control for designing more advanced neuroprostheses, our work could also have a direct impact on advancing robot-assisted neurorehabilitation.

A PC-based system for predicting movement from deep brain signals in Parkinson's disease

There is much current interest in deep brain stimulation (DBS) of the subthalamic nucleus (STN) for the treatment of Parkinson's disease (PD). This type of surgery has enabled unprecedented access to deep brain signals in the awake human. In this paper we present an easy-to-use computer based system for recording, displaying, archiving, and processing electrophysiological signals from the STN. The system was developed for predicting self-paced hand-movements in real-time via the online processing of the electrophysiological activity of the STN. It is hoped that such a computerised system might have clinical and experimental applications. For example, those sites within the STN most relevant to the processing of voluntary movement could be identified through the predictive value of their activities with respect to the timing of future movement.

Electroencephalography (EEG)-based brain-computer interface (BCI): a 2-D virtual wheelchair control based on event-related desynchronization/synchronization and state control

This study aims to propose an effective and practical paradigm for a brain-computer interface (BCI)-based 2-D virtual wheelchair control. The paradigm was based on the multi-class discrimination of spatiotemporally distinguishable phenomenon of event-related desynchronization/synchronization (ERD/ERS) in electroencephalogram signals associated with motor execution/imagery of right/left hand movement. Comparing with traditional method using ERD only, where bilateral ERDs appear during left/right hand mental tasks, the 2-D control exhibited high accuracy within a short time, as incorporating ERS into the paradigm hypothetically enhanced the spatiotemoral feature contrast of ERS versus ERD. We also expected users to experience ease of control by including a noncontrol state. In this study, the control command was sent discretely whereas the virtual wheelchair was moving continuously. We tested five healthy subjects in a single visit with two sessions, i.e., motor execution and motor imagery. Each session included a 20 min calibration and two sets of games that were less than 30 min. Average target hit rate was as high as 98.4% with motor imagery. Every subject achieved 100% hit rate in the second set of wheelchair control games. The average time to hit a target 10 m away was about 59 s, with 39 s for the best set. The superior control performance in subjects without intensive BCI training suggested a practical wheelchair control paradigm for BCI users.

Determination of awareness in patients with severe brain injury using EEG power spectral analysis

OBJECTIVE

To determine whether EEG spectral analysis could be used to demonstrate awareness in patients with severe brain injury.

METHODS

We recorded EEG from healthy controls and three patients with severe brain injury, ranging from minimally conscious state (MCS) to locked-in-state (LIS), while they were asked to imagine motor and spatial navigation tasks. We assessed EEG spectral differences from 4 to 24 Hz with univariate comparisons (individual frequencies) and multivariate comparisons (patterns across the frequency range).

RESULTS

In controls, EEG spectral power differed at multiple frequency bands and channels during performance of both tasks compared to a resting baseline. As patterns of signal change were inconsistent between controls, we defined a positive response in patient subjects as consistent spectral changes across task performances. One patient in MCS and one in LIS showed evidence of motor imagery task performance, though with patterns of spectral change different from the controls.

CONCLUSIONS

EEG power spectral analysis demonstrates evidence for performance of mental imagery tasks in healthy controls and patients with severe brain injury.

SIGNIFICANCE

EEG power spectral analysis can be used as a flexible bedside tool to demonstrate awareness in brain-injured patients who are otherwise unable to communicate.

Towards a brain controlled assistive technology for powered mobility

For individuals with mobility limitations, powered wheelchair systems provide improved functionality, increased access to healthcare, education and social activities. Input devices such as joystick and switches can provide the necessary input required for efficient control of the powered wheelchair. For persons with limited dexterity, or fine control of the fingers, access to mechanical hardware such as buttons and joysticks can be quite difficult and sometimes painful. For individuals with conditions such as Traumatic Brain Injury (TBI), Multiple Sclerosis (MS) or Amyotrophic lateral sclerosis (ALS) voluntary control of limb movement maybe substantially limited or completely absent. Brain Computer Interfaces (BCI) are emerging as a possible method to replace the brains normal output pathways of peripheral nerves and muscles, allowing individuals with paralysis a method of communication and computer control. This study involves the analysis of non-invasive electroencephalograms (EEG) arising from the use of a newly developed Human Machine Interface (HMI) for powered wheelchair control. Using a delayed response task, binary classification of left and right movement intentions were classified with a best classification rate of 81.63% from single trial EEG. Results suggest that this method may be used to enhance control of HMI's for individuals with severe mobility limitations.

Prediction of human voluntary movement before it occurs

OBJECTIVE

Human voluntary movement is associated with two changes in electroencephalography (EEG) that can be observed as early as 1.5 s prior to movement: slow DC potentials and frequency power shifts in the alpha and beta bands. Our goal was to determine whether and when we can reliably predict human natural movement BEFORE it occurs from EEG signals ONLINE IN REAL-TIME.

METHODS

We developed a computational algorithm to support online prediction. Seven healthy volunteers participated in this study and performed wrist extensions at their own pace.

RESULTS

The average online prediction time was 0.62±0.25 s before actual movement monitored by EMG signals. There were also predictions that occurred without subsequent actual movements, where subjects often reported that they were thinking about making a movement.

CONCLUSION

Human voluntary movement can be predicted before movement occurs.

SIGNIFICANCE

The successful prediction of human movement intention will provide further insight into how the brain prepares for movement, as well as the potential for direct cortical control of a device which may be faster than normal physical control.