Multi-class Motor Imagery Classification Research Articles

Optimal Channel Selection of Multiclass Motor Imagery Classification Based on Fusion Convolutional Neural Network with Attention Blocks.

The widely adopted paradigm in brain-computer interfaces (BCIs) involves motor imagery (MI), enabling improved communication between humans and machines. EEG signals derived from MI present several challenges due to their inherent characteristics, which lead to a complex process of classifying and finding the potential tasks of a specific participant. Another issue is that BCI systems can result in noisy data and redundant channels, which in turn can lead to increased equipment and computational costs. To address these problems, the optimal channel selection of a multiclass MI classification based on a Fusion convolutional neural network with Attention blocks (FCNNA) is proposed. In this study, we developed a CNN model consisting of layers of convolutional blocks with multiple spatial and temporal filters. These filters are designed specifically to capture the distribution and relationships of signal features across different electrode locations, as well as to analyze the evolution of these features over time. Following these layers, a Convolutional Block Attention Module (CBAM) is used to, further, enhance EEG signal feature extraction. In the process of channel selection, the genetic algorithm is used to select the optimal set of channels using a new technique to deliver fixed as well as variable channels for all participants. The proposed methodology is validated showing 6.41% improvement in multiclass classification compared to most baseline models. Notably, we achieved the highest results of 93.09% for binary classes involving left-hand and right-hand movements. In addition, the cross-subject strategy for multiclass classification yielded an impressive accuracy of 68.87%. Following channel selection, multiclass classification accuracy was enhanced, reaching 84.53%. Overall, our experiments illustrated the efficiency of the proposed EEG MI model in both channel selection and classification, showing superior results with either a full channel set or a reduced number of channels.

Multiclass motor imagery classification with Riemannian geometry and temporal-spectral selection.

Motor imagery (MI) based brain-computer interfaces (BCIs) decode the users' intentions from electroencephalography (EEG) to achieve information control and interaction between the brain and external devices. In this paper, firstly, we apply Riemannian geometry to the covariance matrix extracted by spatial filtering to obtain robust and distinct features. Then, a multiscale temporal-spectral segmentation scheme is developed to enrich the feature dimensionality. In order to determine the optimal feature configurations, we utilize a linear learning-based temporal window and spectral band (TWSB) selection method to evaluate the feature contributions, which efficiently reduces the redundant features and improves the decoding efficiency without excessive loss of accuracy. Finally, support vector machines are used to predict the classification labels based on the selected MI features. To evaluate the performance of our model, we test it on the publicly available BCI Competition IV dataset 2a and 2b. The results show that the method has an average accuracy of 79.1% and 83.1%, which outperforms other existing methods. Using TWSB feature selection instead of selecting all features improves the accuracy by up to about 6%. Moreover, the TWSB selection method can effectively reduce the computational burden. We believe that the framework reveals more interpretable feature information of motor imagery EEG signals, provides neural responses discriminative with high accuracy, and facilitates the performance of real-time MI-BCI.

Kernel-Based Regularized EEGNet Using Centered Alignment and Gaussian Connectivity for Motor Imagery Discrimination

Brain–computer interfaces (BCIs) from electroencephalography (EEG) provide a practical approach to support human–technology interaction. In particular, motor imagery (MI) is a widely used BCI paradigm that guides the mental trial of motor tasks without physical movement. Here, we present a deep learning methodology, named kernel-based regularized EEGNet (KREEGNet), leveled on centered kernel alignment and Gaussian functional connectivity, explicitly designed for EEG-based MI classification. The approach proactively tackles the challenge of intrasubject variability brought on by noisy EEG records and the lack of spatial interpretability within end-to-end frameworks applied for MI classification. KREEGNet is a refinement of the widely accepted EEGNet architecture, featuring an additional kernel-based layer for regularized Gaussian functional connectivity estimation based on CKA. The superiority of KREEGNet is evidenced by our experimental results from binary and multiclass MI classification databases, outperforming the baseline EEGNet and other state-of-the-art methods. Further exploration of our model’s interpretability is conducted at individual and group levels, utilizing classification performance measures and pruned functional connectivities. Our approach is a suitable alternative for interpretable end-to-end EEG-BCI based on deep learning.

Use of covariance matrix images for electroencephalography signal classification for multiclass motor imagery‐based brain computer interface

AbstractElectroencephalogram (EEG) signals can be used to control devices using brain computer interface (BCI) systems, which offer assistance to patients with neuromuscular diseases. This article aims to determine the feasibility of using spatial covariance matrices with deep convolutional neural networks for multiclass motor imagery (MI) task classification for EEG‐based BCIs. Covariance matrices derived from multichannel EEG data are converted into color‐scaled images, which are used to train the AlexNet neural network using transfer learning. Samples of 2‐s duration are extracted every 200 ms intervals from each MI activity EEG eventually increasing the training data size sixfold and reducing the latency in real‐time implementations. Observed the performance using two popular publicly available BCI datasets for two‐class and four‐class MI classification. BCI competition IV Dataset IIa has shown average accuracy of 93.99% (k = 0.88) for two‐class and 86.70% (k = 0.82) for four‐class MI classification. BCI competition III Dataset IVa exhibited average accuracy of 97.02% (k = 0.94) for two‐class classification. Good performance was observed for training with cross‐subject data for two‐class and four‐class classification. The proposed method has shown improved accuracy for multiclass MI classification compared with existing works. The CNN is able to extract features from the covariance matrix and classify the MI data with reasonable accuracy. Since this method can handle large‐dimension data, dimension reduction, and source separation techniques are not required.

A Sparse Multiclass Motor Imagery EEG Classification Using 1D-ConvResNet

Multiclass motor imagery classification is essential for brain–computer interface systems such as prosthetic arms. The compressive sensing of EEG helps classify brain signals in real-time, which is necessary for a BCI system. However, compressive sensing is limited, despite its flexibility and data efficiency, because of its sparsity and high computational cost in reconstructing signals. Although the constraint of sparsity in compressive sensing has been addressed through neural networks, its signal reconstruction remains slow, and the computational cost increases to classify the signals further. Therefore, we propose a 1D-Convolutional Residual Network that classifies EEG features in the compressed (sparse) domain without reconstructing the signal. First, we extract only wavelet features (energy and entropy) from raw EEG epochs to construct a dictionary. Next, we classify the given test EEG data based on the sparse representation of the dictionary. The proposed method is computationally inexpensive, fast, and has high classification accuracy as it uses a single feature to classify without preprocessing. The proposed method is trained, validated, and tested using multiclass motor imagery data of 109 subjects from the PhysioNet database. The results demonstrate that the proposed method outperforms state-of-the-art classifiers with 96.6% accuracy.

Comparison of multi-class motor imagery classification methods for EEG signals

This paper presents a comparative study of EEG-based multiclass motor imagery classifiers based on Kullback-Leiber regularised Riemann Mean and support vector machine, hybrid one versus one classifier, linear discriminant analysis, and convolutional neural network. The paper is felt to be of inter- est to those researchers working in the motor imagery classification of EEG signals. The work presented in this paper helps to understand the basics of different multi-class motor imagery classifiers, their accuracy, and the number of channels involved.

Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain–computer interface

Objective.Deep learning (DL)-based brain–computer interface (BCI) in motor imagery (MI) has emerged as a powerful method for establishing direct communication between the brain and external electronic devices. However, due to inter-subject variability, inherent complex properties, and low signal-to-noise ratio (SNR) in electroencephalogram (EEG) signals are major challenges that significantly hinder the accuracy of the MI classifier. Approach.To overcome this, the present work proposes an efficient transfer learning (TL)-based multi-scale feature fused CNN (MSFFCNN) which can capture the distinguishable features of various non-overlapping canonical frequency bands of EEG signals from different convolutional scales for multi-class MI classification. Significance.In order to account for inter-subject variability from different subjects, the current work presents 4 different model variants including subject-independent and subject-adaptive classification models considering different adaptation configurations to exploit the full learning capacity of the classifier. Each adaptation configuration has been fine-tuned in an extensively trained pre-trained model and the performance of the classifier has been studied for a vast range of learning rates and degrees of adaptation which illustrates the advantages of using an adaptive transfer learning-based model. Results.The model achieves an average classification accuracy of 94.06% (±0.70%) and the kappa value of 0.88 outperforming several baseline and current state-of-the-art EEG-based MI classification models with fewer training samples. The present research provides an effective and efficient transfer learning-based end-to-end MI classification framework for designing a high-performance robust MI-BCI system.

Attention-Based DSC-ConvLSTM for Multiclass Motor Imagery Classification.

With the rapid development of deep learning, researchers have gradually applied it to motor imagery brain computer interface (MI-BCI) and initially demonstrated its advantages over traditional machine learning. However, its application still faces many challenges, and the recognition rate of electroencephalogram (EEG) is still the bottleneck restricting the development of MI-BCI. In order to improve the accuracy of EEG classification, a DSC-ConvLSTM model based on the attention mechanism is proposed for the multi-classification of motor imagery EEG signals. To address the problem of the small sample size of well-labeled and accurate EEG data, the preprocessing uses sliding windows for data augmentation, and the average prediction loss of each sliding window is used as the final prediction loss for that trial. This not only increases the training sample size and is beneficial to train complex neural network models, but also the network no longer extracts the global features of the whole trial so as to avoid learning the difference features among trials, which can effectively eliminate the influence of individual specificity. In the aspect of feature extraction and classification, the overall network structure is designed according to the characteristics of the EEG signals in this paper. Firstly, depth separable convolution (DSC) is used to extract spatial features of EEG signals. On the one hand, this reduces the number of parameters and improves the response speed of the system. On the other hand, the network structure we designed is more conducive to extract directly the direct extraction of spatial features of EEG signals. Secondly, the internal structure of the Long Short-Term Memory (LSTM) unit is improved by using convolution and attention mechanism, and a novel bidirectional convolution LSTM (ConvLSTM) structure is proposed by comparing the effects of embedding convolution and attention mechanism in the input and different gates, respectively. In the ConvLSTM module, the convolutional structure is only introduced into the input-to-state transition, while the gates still remain the original fully connected mechanism, and the attention mechanism is introduced into the input to further improve the overall decoding performance of the model. This bidirectional ConvLSTM extracts the time-domain features of EEG signals and integrates the feature extraction capability of the CNN and the sequence processing capability of LSTM. The experimental results show that the average classification accuracy of the model reaches 73.7% and 92.6% on two datasets, BCI Competition IV Dataset 2a and High Gamma Dataset, respectively, which proves the robustness and effectiveness of the model we proposed. It can be seen that the model in this paper can deeply excavate significant EEG features from the original EEG signals, show good performance in different subjects and different datasets, and improve the influence of individual variability on the classification performance, which is of practical significance for promoting the development of brain-computer interface technology towards a practical and marketable direction.

FB-CGANet: filter bank channel group attention network for multi-class motor imagery classification

Objective. Motor imagery-based brain–computer interface (MI-BCI) is one of the most important BCI paradigms and can identify the target limb of subjects from the feature of MI-based Electroencephalography signals. Deep learning methods, especially lightweight neural networks, provide an efficient technique for MI decoding, but the performance of lightweight neural networks is still limited and need further improving. This paper aimed to design a novel lightweight neural network for improving the performance of multi-class MI decoding. Approach. A hybrid filter bank structure that can extract information in both time and frequency domain was proposed and combined with a novel channel attention method channel group attention (CGA) to build a lightweight neural network Filter Bank CGA Network (FB-CGANet). Accompanied with FB-CGANet, the band exchange data augmentation method was proposed to generate training data for networks with filter bank structure. Main results. The proposed method can achieve higher 4-class average accuracy (79.4%) than compared methods on the BCI Competition IV IIa dataset in the experiment on the unseen evaluation data. Also, higher average accuracy (93.5%) than compared methods can be obtained in the cross-validation experiment. Significance. This work implies the effectiveness of channel attention and filter bank structure in lightweight neural networks and provides a novel option for multi-class motor imagery classification.

A Computationally Efficient Multiclass Time-Frequency Common Spatial Pattern Analysis on EEG Motor Imagery.

Common spatial pattern (CSP) is a popular feature extraction method for electroencephalogram (EEG) motor imagery (MI). This study modifies the conventional CSP algorithm to improve the multi-class MI classification accuracy and ensure the computation process is efficient. The EEG MI data is gathered from the Brain-Computer Interface (BCI) Competition IV. At first, a bandpass filter and a timefrequency analysis are performed for each experiment trial. Then, the optimal EEG signals for every experiment trials are selected based on the signal energy for CSP feature extraction. In the end, the extracted features are classified by three classifiers, linear discriminant analysis (LDA), naïve Bayes (NVB), and support vector machine (SVM), in parallel for classification accuracy comparison.The experiment results show the proposed algorithm average computation time is 37.22% less than the FBCSP (1st winner in the BCI Competition IV) and 4.98% longer than the conventional CSP method. For the classification rate, the proposed algorithm kappa value achieved 2nd highest compared with the top 3 winners in BCI Competition IV.

Motor Imagery Classification of Finger Motions Using Multiclass CSP.

Electroencephalogram (EEG) data during motor imagery tasks regarding small-scale physical dynamics such as finger motions have low discriminability because capturing the spatial difference of the motions is difficult. We assumed that more discriminative features can be captured if spatial filters maximize the independence of each class data. This study constructed spatial filters named multiclass common spatial pattern (CSP), which maximize an approximation of mutual in-formation of extracted components and class labels, and applied them to a five-class motor-imagery dataset containing finger motion tasks. By applying multiclass CSP, the classification accuracies were improved (Mean SD: 40.6 ± 10.1%) compared with classical CSP (21.8 ± 2.5%) and no spatial filtering case (38.7±10.0%). In addition, we visualized learned spatial filters to assess the trend of discriminative features of finger motions. For these results, it was clear that multiclass CSP captured task-specific spatial maps for each finger motion and outperformed multiclass motor-imagery classification performance about 2% even when the tasks are small-scale physical dynamics.

Online Classification of Multiple Motor Imagery Tasks Using Filter Bank Based Maximum-a-Posteriori Common Spatial Pattern Filters

ObjectiveThe main objective of this paper is to propose a novel technique, called filter bank maximum a-posteriori common spatial pattern (FB-MAP-CSP) algorithm, for online classification of multiple motor imagery activities using electroencephalography (EEG) signals. The proposed technique addresses the overfitting issue of CSP in addition to utilizing the spectral information of EEG signals inside the framework of filter banks while extending it to more than two conditions. Materials and methodsThe classification of motor imagery signals is based upon the detection of event-related de-synchronization (ERD) phenomena in the μ and β rhythms of EEG signals. Accordingly, two modifications in the existing MAP-CSP technique are presented: (i) The (pre-processed) EEG signals are spectrally filtered by a bank of filters lying in the μ and β brainwave frequency range, (ii) the framework of MAP-CSP is extended to deal with multiple (more than two) motor imagery tasks classification and the spatial filters thus obtained are calculated for each sub-band, separately. Subsequently, the most imperative features over all sub-bands are selected and un-regularized linear discriminant analysis is employed for classification of multiple motor imagery tasks. ResultsPublicly available dataset (BCI Competition IV Dataset I) is used to validate the proposed method i.e. FB-MAP-CSP. The results show that the proposed method yields superior classification results, in addition to be computationally more efficient in the case of online implementation, as compared to the conventional CSP based techniques and its variants for multiclass motor imagery classification. ConclusionThe proposed FB-MAP-CSP algorithm is found to be a potential / superior method for classifying multi-condition motor imagery EEG signals in comparison to FBCSP based techniques.

Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification

The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.

FBCSP-based Multi-class Motor Imagery Classification using BP and TDP features.

Use of Motor Imagery in EEG signals is gaining importance to develop Brain Computer Interface (BCI) applications in various fields ranging from bio-medical to entertainment. Filter Bank Common Spatial Pattern (FBCSP) algorithm is a promising feature extraction technique to deal with subject-specific behavior in Motor Imagery classification. Using FBCSP on EEG we have developed an accurate but less computationally expensive approach by making use of Time Domain Parameters (TDP) and Band Power (BP) features to form a combined feature set. The novelty of our approach is also the use of optimal time segmentation to overcome non-stationary state behavior of Event-Related Desynchronization (ERD) and Event-Related Synchronization (ERS) over time. We analyzed the impact of parameter variations on classification accuracy and achieved 0.59 mean kappa value for Dataset 2a BCI competition IV, the highest reported for FBCSP approaches, along with the lowest inter-subject variation.

A Randomised Ensemble Learning Approach for Multiclass Motor Imagery Classification Using Error Correcting Output Coding.

Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands $\alpha$ (8-12Hz) and $\beta$ (12-30Hz) along with $HG$ (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98ȥ and 84ȥ in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.

Subject and class specific frequency bands selection for multiclass motor imagery classification

AbstractEEG‐based discrimination among motor imagery states has been widely studied for brain‐computer interfaces (BCIs) due to the great potential for real‐life applications. However, in terms of designing a motor imagery‐based BCI system, a lot of research in the literature either uses a frequency band of interest selected manually based on the visual analysis of EEG data or is set to a general broad band, causing performance degradation in classification. In this article, we propose a novel method of selecting subject and class specific frequency bands based on the analysis of a channel‐frequency matrix, which we call a channel‐frequency map. We operate the classification process for each frequency band individually, i.e., spatial filtering, feature extraction, and classification, and determine a class label for an input EEG by considering the outputs from multiple classifiers together at the end. From our experiments on a public dataset of BCI Competition IV (2008) II‐a that includes four motor imagery tasks from nine subjects, the proposed algorithm outperformed the common spatial pattern (CSP) algorithm in a broad band and a filter bank CSP algorithm on average in terms of cross‐validation and session‐to‐session transfer rate. Furthermore, a considerable increase of classification accuracy has been achieved for certain subjects. We also would like to note that the proposed data‐driven frequency bands selection method is applicable to other kinds of single‐trial EEG classifications that are based on modulations of brain rhythms, by no means limited to motor imagery‐based BCI applications. © 2011 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 21, 123–130, 2011