A novel channel selection method for optimal classification in different motor imagery BCI paradigms

Adaptive Time-Frequency Segment Optimization for Motor Imagery Classification

Motor imagery (MI)-based brain-computer interface (BCI) has emerged as a crucial method for rehabilitating stroke patients. However, the variability in the time-frequency distribution of MI-electroencephalography (EEG) among individuals limits the generalizability of algorithms that rely on non-customized time-frequency segments. In this study, we propose a novel method for optimizing time-frequency segments of MI-EEG using the sparrow search algorithm (SSA). Additionally, we apply a correlation-based channel selection (CCS) method that considers the correlation coefficient of features between each pair of EEG channels. Subsequently, we utilize a regularized common spatial pattern method to extract effective features. Finally, a support vector machine is employed for signal classification. The results on three BCI datasets confirmed that our algorithm achieved better accuracy (99.11% vs. 94.00% for BCI Competition III Dataset IIIa, 87.70% vs. 81.10% for Chinese Academy of Medical Sciences dataset, and 87.94% vs. 81.97% for BCI Competition IV Dataset 1) compared to algorithms with non-customized time-frequency segments. Our proposed algorithm enables adaptive optimization of EEG time-frequency segments, which is crucial for the development of clinically effective motor rehabilitation.

Relevance-based channel selection in motor imagery brain-computer interface

Objective.Channel selection in the electroencephalogram (EEG)-based brain-computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep learning (DL)-based BCI models, there arises a need for fresh perspectives and novel techniques to conduct channel selection. In this regard, subject-independent channel selection is relevant, since DL models trained using cross-subject data offer superior performance, and the impact of inherent inter-subject variability of EEG characteristics on subject-independent DL training is not yet fully understood.Approach.Here, we propose a novel methodology for implementing subject-independent channel selection in DL-based motor imagery (MI)-BCI, using layer-wise relevance propagation (LRP) and neural network pruning. Experiments were conducted using Deep ConvNet and 62-channel MI data from the Korea University EEG dataset.Main Results.Using our proposed methodology, we achieved a 61% reduction in the number of channels without any significant drop (p = 0.09) in subject-independent classification accuracy, due to the selection of highly relevant channels by LRP. LRP relevance-based channel selections provide significantly better accuracies compared to conventional weight-based selections while using less than 40% of the total number of channels, with differences in accuracies ranging from 5.96% to 1.72%. The performance of the adapted sparse-LRP model using only 16% of the total number of channels is similar to that of the adapted baseline model (p = 0.13). Furthermore, the accuracy of the adapted sparse-LRP model using only 35% of the total number of channels exceeded that of the adapted baseline model by 0.53% (p = 0.81). Analyses of channels chosen by LRP confirm the neurophysiological plausibility of selection, and emphasize the influence of motor, parietal, and occipital channels in MI-EEG classification.Significance.The proposed method addresses a traditional issue in EEG-BCI decoding, while being relevant and applicable to the latest developments in the field of BCI. We believe that our work brings forth an interesting and important application of model interpretability as a problem-solving technique.

Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture

Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy.

Continuous 2D trajectory decoding from attempted movement: across-session performance in able-bodied and feasibility in a spinal cord injured participant

OBJECTIVE

In people with a cervical spinal cord injury (SCI) or degenerative diseases leading to limited motor function, restoration of upper limb movement has been a goal of the brain-computer interface (BCI) field for decades. Recently, research from our group investigated non-invasive and real-time decoding of continuous movement in able-bodied participants from low-frequency brain signals during a target-tracking task. To advance our setup towards motor-impaired end users, we consequently chose a new paradigm based on attempted movement.

APPROACH

Here, we present the results of two studies. During the first study, data of ten able-bodied participants completing a target-tracking/shape-tracing task on-screen were investigated in terms of improvements in decoding performance due to user training. In a second study, a spinal cord injured participant underwent the same tasks. To investigate the merit of employing attempted movement in end users with SCI, data of the spinal cord injured participant were recorded twice; once within an observation only condition, and once while simultaneously attempting movement.

MAIN RESULTS

We observed mean correlation well above chance level for continuous motor decoding based on attempted movement in able-bodied participants. No global improvement over three sessions, both in sensor and source space, could be observed across all participants and movement parameters. In the participant with SCI, decoding performance well above chance was found.

SIGNIFICANCE

No presence of a learning effect in continuous attempted movement decoding in able-bodied participants could be observed. In contrast, non-significantly varying decoding patterns may promote the use of source space decoding in terms of generalized decoders utilizing transfer learning. Furthermore, above-chance correlations for attempted movement decoding ranging between those of observation only and executed movement were seen in one spinal cord injured participant, suggesting attempted movement decoding as a possible link between feasibility studies in able-bodied and actual applications in motor impaired end users.

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Motor imagery (MI) brain–computer interface (BCI) systems have broad application prospects in rehabilitation and other fields. However, to achieve accurate and practical MI-BCI applications, there are still several critical issues, such as channel selection, electroencephalogram (EEG) feature extraction and EEG classification, needed to be better resolved. In this paper, these issues are studied for lower limb MI which is more difficult and less studied than upper limb MI. First, a novel iterative EEG source localization method is proposed for channel selection. Channels FC1, FC2, C1, C2 and Cz, instead of the commonly used traditional channel set (TCS) C3, C4 and Cz, are selected as the optimal channel set (OCS). Then, a multi-domain feature (MDF) extraction algorithm is presented to fuse single-domain features into multi-domain features. Finally, a particle swarm optimization based support vector machine (SVM) method is utilized to classify the EEG data collected by the lower limb MI experiment designed by us. The results show that the classification accuracy is 88.43%, 3.35–5.41% higher than those of using traditional SVM to classify single-domain features on the TCS, which proves that the combination of OCS and MDF can not only reduce the amount of data processing, but also retain more feature information to improve the accuracy of EEG classification.

Participant-specific classifier tuning increases the performance of hand movement detection from EEG in patients with amyotrophic lateral sclerosis

Objective.Brain-computer interface (BCI) systems can be employed to provide motor and communication assistance to patients suffering from neuromuscular diseases, such as amyotrophic lateral sclerosis (ALS). Movement related cortical potentials (MRCPs), which are naturally generated during movement execution, can be used to implement a BCI triggered by motor attempts. Such BCI could assist impaired motor functions of ALS patients during disease progression, and facilitate the training for the generation of reliable MRCPs. The training aspect is relevant to establish a communication channel in the late stage of the disease. Therefore, the aim of this study was to investigate the possibility of detecting MRCPs associated to movement intention in ALS patients with different levels of disease progression from slight to complete paralysis.Approach.Electroencephalography signals were recorded from nine channels in 30 ALS patients at various stages of the disease while they performed or attempted to perform hand movements timed to a visual cue. The movement detection was implemented using offline classification between movement and rest phase. Temporal and spectral features were extracted using 500 ms sliding windows with 50% overlap. The detection was tested for each individual channel and two surrogate channels by performing feature selection followed by classification using linear and non-linear support vector machine and linear discriminant analysis.Main results.The results demonstrated that the detection performance was high in all patients (accuracy 80.5 ± 5.6%) but that the classification parameters (channel, features and classifier) leading to the best performance varied greatly across patients. When the same channel and classifier were used for all patients (participant-generic analysis), the performance significantly decreased (accuracy 74 ± 8.3%).Significance.The present study demonstrates that to maximize the detection of brain waves across ALS patients at different stages of the disease, the classification pipeline should be tuned to each patient individually.

Inter-stimulus phase coherence in steady-state somatosensory evoked potentials and its application in improving the performance of single-channel MI-BCI

Objective. With the development of clinical applications of motor imagery-based brain-computer interfaces (MI-BCIs), a single-channel MI-BCI system that can be easily assembled is an attractive goal. However, due to the low quality of the spectral power features in the traditional MI-BCI paradigm, the recognition performance of current single-channel systems is far lower than that of multi-channel systems, impeding their use in clinical applications.Approach.In this study, the subjects' right and left hands were stimulated simultaneously at different frequencies to induce steady-state somatosensory evoked potentials (SSSEP). Subjects then performed motor imagery (MI) tasks. A new electroencephalography (EEG) index, inter-stimulus phase coherence (ISPC), was built to measure phase desynchronization of SSSEP caused by MI. Then, ISPC is introduced as a feature into left-hand and right-hand MI recognition.Main results.ISPC analysis found that left-handed MI can cause a significant decrease in phase synchronization in contralateral sensorimotor SSSEP, while right-handed MI has little effect on it, and vice versa. Combining ISPC features with traditional spectral power features, the single-channel left-hand versus right-hand MI recognition accuracy reaches 81.0%, which is much higher than that observed with traditional MI paradigms (about 60%).Significance.This work shows that the hybrid MI-SSSEP paradigm can provide more sensitive EEG features to decode motor intentions, demonstrating its potential for clinical applications.

Formulation of the Challenges in Brain-Computer Interfaces as Optimization Problems-A Review

Electroencephalogram (EEG) is one of the common modalities of monitoring the mental activities. Owing to the non-invasive availability of this system, its applicability has seen remarkable developments beyond medical use-cases. One such use case is brain-computer interfaces (BCI). Such systems require the usage of high resolution-based multi-channel EEG devices so that the data collection spans multiple locations of the brain like the occipital, frontal, temporal, and so on. This results in huge data (with high sampling rates) and with multiple EEG channels with inherent artifacts. Several challenges exist in analyzing data of this nature, for instance, selecting the optimal number of EEG channels or deciding what best features to rely on for achieving better performance. The selection of these variables is complicated and requires a lot of domain knowledge and non-invasive EEG monitoring, which is not feasible always. Hence, optimization serves to be an easy to access tool in deriving such parameters. Considerable efforts in formulating these issues as an optimization problem have been laid. As a result, various multi-objective and constrained optimization functions have been developed in BCI that has achieved reliable outcomes in device control like neuro-prosthetic arms, application control, gaming, and so on. This paper makes an attempt to study the usage of optimization techniques in formulating the issues in BCI. The outcomes, challenges, and major observations of these approaches are discussed in detail.

Channel Selection for Optimal EEG Measurement in Motor Imagery-Based Brain-Computer Interfaces

A method for selecting electroencephalographic (EEG) signals in motor imagery-based brain-computer interfaces (MI-BCI) is proposed for enhancing the online interoperability and portability of BCI systems, as well as user comfort. The attempt is also to reduce variability and noise of MI-BCI, which could be affected by a large number of EEG channels. The relation between selected channels and MI-BCI performance is therefore analyzed. The proposed method is able to select acquisition channels common to all subjects, while achieving a performance compatible with the use of all the channels. Results are reported with reference to a standard benchmark dataset, the BCI competition IV dataset 2a. They prove that a performance compatible with the best state-of-the-art approaches can be achieved, while adopting a significantly smaller number of channels, both in two and in four tasks classification. In particular, classification accuracy is about 77-83% in binary classification with down to 6 EEG channels, and above 60% for the four-classes case when 10 channels are employed. This gives a contribution in optimizing the EEG measurement while developing non-invasive and wearable MI-based brain-computer interfaces.

Enhancing Classification Performance of fNIRS-BCI by Identifying Cortically Active Channels Using the z-Score Method

A state-of-the-art brain–computer interface (BCI) system includes brain signal acquisition, noise removal, channel selection, feature extraction, classification, and an application interface. In functional near-infrared spectroscopy-based BCI (fNIRS-BCI) channel selection may enhance classification performance by identifying suitable brain regions that contain brain activity. In this study, the z-score method for channel selection is proposed to improve fNIRS-BCI performance. The proposed method uses cross-correlation to match the similarity between desired and recorded brain activity signals, followed by forming a vector of each channel’s correlation coefficients’ maximum values. After that, the z-score is calculated for each value of that vector. A channel is selected based on a positive z-score value. The proposed method is applied to an open-access dataset containing mental arithmetic (MA) and motor imagery (MI) tasks for twenty-nine subjects. The proposed method is compared with the conventional t-value method and with no channel selected, i.e., using all channels. The z-score method yielded significantly improved (p < 0.0167) classification accuracies of 87.2 ± 7.0%, 88.4 ± 6.2%, and 88.1 ± 6.9% for left motor imagery (LMI) vs. rest, right motor imagery (RMI) vs. rest, and mental arithmetic (MA) vs. rest, respectively. The proposed method is also validated on an open-access database of 17 subjects, containing right-hand finger tapping (RFT), left-hand finger tapping (LFT), and dominant side foot tapping (FT) tasks.The study shows an enhanced performance of the z-score method over the t-value method as an advancement in efforts to improve state-of-the-art fNIRS-BCI systems’ performance.

Early classification of motor tasks using dynamic functional connectivity graphs from EEG

OBJECTIVE

Classification of electroencephalography (EEG) signals with high accuracy using short recording intervals has been a challenging problem in developing brain computer interfaces (BCIs). This paper presents a novel feature extraction method for EEG recordings to tackle this problem.

APPROACH

The proposed approach is based on the concept that the brain functions in a dynamic manner, and utilizes dynamic functional connectivity graphs. The EEG data is first segmented into intervals during which functional networks sustain their connectivity. Functional connectivity networks for each identified segment are then localized, and graphs are constructed, which will be used as features. To take advantage of the dynamic nature of the generated graphs, a Long Short Term Memory (LSTM) classifier is employed for classification.

MAIN RESULTS

Features extracted from various durations of post-stimulus EEG data associated with motor execution and imagery tasks are used to test the performance of the classifier. Results show an average accuracy of 85.32% using features extracted from only 500 ms of the post-stimulus data.

SIGNIFICANCE

Our results demonstrate, for the first time, that using the proposed feature extraction method, it is possible to classify motor tasks from EEG recordings using a short interval of the data in the order of hundreds of milliseconds (e.g. 500 ms). This duration is considerably shorter than what has been reported before. These results will have significant implications for improving the effectiveness and the speed of BCIs, particularly for those used in assistive technologies.

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

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

Motor Imagery Classification via Temporal Attention Cues of Graph Embedded EEG Signals

Motor imagery classification from EEG signals is essential for motor rehabilitation with a Brain-Computer Interface (BCI). Most current works on this issue require a subject-specific adaptation step before applied to a new user. Thus the research of directly extending a pre-trained model to new users is particularly desired and indispensable. As brain dynamics fluctuate considerably across different subjects, it is challenging to design practical hand-crafted features based on prior knowledge. Regarding this gap, this paper proposes a Graph-based Convolutional Recurrent Attention Model (G-CRAM) to explore EEG features across different subjects for motor imagery classification. A graph structure is first developed to represent the positioning information of EEG nodes. Then a convolutional recurrent attention model learns EEG features from both spatial and temporal dimensions and emphasizes on the most distinguishable temporal periods. We evaluate the proposed approach on two benchmark EEG datasets of motor imagery classification on the subject-independent testing. The results show that the G-CRAM achieves superior performance to state-of-the-art methods regarding recognition accuracy and ROC-AUC. Furthermore, model interpretation studies reveal the learning process of different neural network components and demonstrate that the proposed model can extract detailed features efficiently.

An Optimized Channel Selection Method Based on Multifrequency CSP-Rank for Motor Imagery-Based BCI System

Background

Due to the redundant information contained in multichannel electroencephalogram (EEG) signals, the classification accuracy of brain-computer interface (BCI) systems may deteriorate to a large extent. Channel selection methods can help to remove task-independent electroencephalogram (EEG) signals and hence improve the performance of BCI systems. However, in different frequency bands, brain areas associated with motor imagery are not exactly the same, which will result in the inability of traditional channel selection methods to extract effective EEG features.

New Method

To address the above problem, this paper proposes a novel method based on common spatial pattern- (CSP-) rank channel selection for multifrequency band EEG (CSP-R-MF). It combines the multiband signal decomposition filtering and the CSP-rank channel selection methods to select significant channels, and then linear discriminant analysis (LDA) was used to calculate the classification accuracy.

Results

The results showed that our proposed CSP-R-MF method could significantly improve the average classification accuracy compared with the CSP-rank channel selection method.

An Automatic Channel Selection Approach for ICA-Based Motor Imagery Brain Computer Interface

Independent component analysis (ICA) is a potential spatial filtering method for the implementation of motor imagery brain-computer interface (MIBCI). However, ICA-based MIBCI (ICA-MIBCI) is sensitive to electroencephalogram (EEG) channels and the quality of the training data, which are two crucial factors affecting the stability and classification performance of ICA-MIBCI. To address these problems, this paper is mainly focused on the investigation of EEG channel optimization. As a reference, we constructed a single-trial-based ICA-MIBCI system with commonly used channels and common spatial pattern-based MIBCI (CSP-MIBCI). To minimize the impact of artifacts on EEG channel optimization, a data-quality evaluation method, named "self-testing" in this paper, was used in a single-trial-based ICA-MIBCI system to evaluate the quality of single trials in each dataset; the resulting self-testing accuracies were used for the selection of high-quality trials. Given several candidate channel configurations, ICA filters were calculated using selected high-quality trials and applied to the corresponding ICA-MIBCI implementation. Optimal channels for each dataset were assessed and selected according to the self-testing results related to various candidate configurations. Forty-eight MI datasets of six subjects were employed in this study to validate the proposed methods. Experimental results revealed that the average classification accuracy of the optimal channels yielded a relative increment of 2.8% and 8.5% during self-testing, 14.4% and 9.5% during session-to-session transfer, and 36.2% and 26.7% during subject-to-subject transfer compared to CSP-MIBCI and ICA-MIBCI with fixed the channel configuration. This work indicates that the proposed methods can efficiently improve the practical feasibility of ICA-MIBCI.

Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems

Phase synchronisation between different neural groups is considered an important source of information to understand the underlying mechanisms of brain cognition. This Letter investigated phase-synchronisation patterns from electroencephalogram (EEG) signals recorded from ten healthy participants performing motor imagery (MI) tasks using schematic emotional faces as stimuli. These phase-synchronised states, named synchrostates, are specific for each cognitive task performed by the user. The maximum and minimum number of occurrence states were selected for each subject and task to extract the connectivity network measures based on graph theory to feed a set of classification algorithms. Two MI tasks were successfully classified with the highest accuracy of 85% with corresponding sensitivity and specificity of 85%. In this work, not only the performance of different supervised learning techniques was studied, as well as the optimal subset of features to obtain the best discrimination rates. The robustness of this classification method for MI tasks indicates the possibility of expanding its use for online classification of the brain-computer interface (BCI) systems.

Correlation Assisted Strong Uncorrelating Transform Complex Common Spatial Patterns for Spatially Distant Channel Data

The Strong Uncorrelating Transform Complex Common Spatial Patterns (SUTCCSP) algorithm, designed for multichannel data analysis, has a limitation on keeping the correlation information among channels during the simultaneous diagonalization process of the covariance and pseudocovariance matrices. This paper focuses on the importance of preserving the correlation information among multichannel data and proposes the correlation assisted SUTCCSP (CASUT) algorithm to address this issue. The performance of the proposed algorithm was demonstrated by classifying the motor imagery electroencephalogram (EEG) dataset. The features were first extracted using CSP algorithms including the proposed method, and then the random forest classifier was utilized for the classification. Experiments using CASUT yielded an average classification accuracy of 78.10 (%), which significantly outperformed those of original CSP, Complex Common Spatial Patterns (CCSP), and SUTCCSP with p-values less than 0.01, tested by the Wilcoxon signed rank test.

A Study of the Effects of Electrode Number and Decoding Algorithm on Online EEG-Based BCI Behavioral Performance

Motor imagery–based brain–computer interface (BCI) using electroencephalography (EEG) has demonstrated promising applications by directly decoding users' movement related mental intention. The selection of control signals, e.g., the channel configuration and decoding algorithm, plays a vital role in the online performance and progressing of BCI control. While several offline analyses report the effect of these factors on BCI accuracy for a single session—performance increases asymptotically by increasing the number of channels, saturates, and then decreases—no online study, to the best of our knowledge, has yet been performed to compare for a single session or across training. The purpose of the current study is to assess, in a group of forty-five subjects, the effect of channel number and decoding method on the progression of BCI performance across multiple training sessions and the corresponding neurophysiological changes. The 45 subjects were divided into three groups using Laplacian Filtering (LAP/S) with nine channels, Common Spatial Pattern (CSP/L) with 40 channels and CSP (CSP/S) with nine channels for online decoding. At the first training session, subjects using CSP/L displayed no significant difference compared to CSP/S but a higher average BCI performance over those using LAP/S. Despite the average performance when using the LAP/S method was initially lower, but LAP/S displayed improvement over first three sessions, whereas the other two groups did not. Additionally, analysis of the recorded EEG during BCI control indicates that the LAP/S produces control signals that are more strongly correlated with the target location and a higher R-square value was shown at the fifth session. In the present study, we found that subjects' average online BCI performance using a large EEG montage does not show significantly better performance after the first session than a smaller montage comprised of a common subset of these electrodes. The LAP/S method with a small EEG montage allowed the subjects to improve their skills across sessions, but no improvement was shown for the CSP method.

Motor Imagery Classification Using Mu and Beta Rhythms of EEG with Strong Uncorrelating Transform Based Complex Common Spatial Patterns

Recent studies have demonstrated the disassociation between the mu and beta rhythms of electroencephalogram (EEG) during motor imagery tasks. The proposed algorithm in this paper uses a fully data-driven multivariate empirical mode decomposition (MEMD) in order to obtain the mu and beta rhythms from the nonlinear EEG signals. Then, the strong uncorrelating transform complex common spatial patterns (SUTCCSP) algorithm is applied to the rhythms so that the complex data, constructed with the mu and beta rhythms, becomes uncorrelated and its pseudocovariance provides supplementary power difference information between the two rhythms. The extracted features using SUTCCSP that maximize the interclass variances are classified using various classification algorithms for the separation of the left- and right-hand motor imagery EEG acquired from the Physionet database. This paper shows that the supplementary information of the power difference between mu and beta rhythms obtained using SUTCCSP provides an important feature for the classification of the left- and right-hand motor imagery tasks. In addition, MEMD is proved to be a preferred preprocessing method for the nonlinear and nonstationary EEG signals compared to the conventional IIR filtering. Finally, the random forest classifier yielded a high performance for the classification of the motor imagery tasks.