Motor Imagery Electroencephalogram Signals Research Articles

A Classification Method for Multichannel MI-EEG Signal with FPCA and DNN

Abstract A new accurate identification method has been proposed to address the lack of interpretability in current deep learning-based feature extraction methods for motor imagery electroencephalogram (MI-EEG) signals. This method combines functional principal component analysis (FPCA) and deep neural networks (DNN) for four classifications of MI-EEG signals. The process involves preprocessing the acquired MI-EEG signals and obtaining power spectral density (PSD) versus frequency curves in the alpha band for multiple channels and samples through FIR filtering. All PSD-frequency curves are then functionally smoothed according to the theory of functional data analysis (FDA). Feature parameters are derived using FPCA, and the parameters of all samples are normalized. Training samples are selected randomly for clustering training with DNNs. Category prediction is carried out on the test data classification samples. This method is applied to 4×120 four-categorized MI-EEG samples, each from six channels obtained from Enobio test, a wireless EEG system from Spain Neuroelectrics, involving left hand, right hand, left foot, and right foot motor imagery at a sampling rate of 500Hz. 80% of the samples were used for training, and the remaining 20% were used for testing. The prediction accuracy ranged from 84.3% to 91.66%. While this multivariate feature parameter extraction method has clear mathematical and physical significance, it does demand a high sampling rate of 500Hz.

A multiscale feature fusion network based on attention mechanism for motor imagery EEG decoding

The decoding of motor imagery (MI) electroencephalogram (EEG) is an essential component of the brain–computer interface (BCI), which can help patients with motor impairment communicate directly with the outside world through assistive devices. The key to motor imagery electroencephalogram (MI-EEG) classification is to extract multiple temporal, spatial, and spectral features, to obtain more comprehensive and representative information. However, current deep learning methods must fully consider the depth of temporal features and multi-spectral knowledge in EEG and often ignore the temporal or spectrum dependence in MI-EEG. In addition, the lack of effective feature fusion methods can lead to information redundancy, which affects decoding performance. To solve the above problems, this paper proposes a novel MI-EEG decoding method, named multi-scale feature fusion network based on attention mechanism (MSFF-SENet). Firstly, the multi-scale spatio-temporal module (MS-STM) and the multi-scale temporal module (MSTM) extract spatial and high-dimensional temporal features from the original signal. Then, the power spectral density estimation (PSD) convolution module (PSD-Conv module) acquires the multi-spectral features of the MI-EEG signal. Secondly, the feature fusion module fuses spatio-temporal and multi-spectral features to generate integrated feature mappings and establish the dependencies between different features. Finally, we conducted a visual analysis of the results, explaining the neural activity patterns of various motor imagery tasks in different frequency ranges and revealing the potential relationship between body movement and changes related to brain activity. The experimental results show that the classification accuracy of this model in BCI Competition IV 2a (BCI IV 2a) and High Gamma (HGD) datasets is 85.37% and 96.60%, respectively, which is superior to the most advanced methods.

A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification.

Domain adaptation, as an important branch of transfer learning, can be applied to cope with data insufficiency and high subject variabilities in motor imagery electroencephalogram (MI-EEG) based brain-computer interfaces. The existing methods generally focus on aligning data and feature distribution; however, aligning each source domain with the informative samples of the target domain and seeking the most appropriate source domains to enhance the classification effect has not been considered. In this paper, we propose a dual alignment-based multi-source domain adaptation framework, denoted DAMSDAF. Based on continuous wavelet transform, all channels of MI-EEG signals are converted respectively and the generated time-frequency spectrum images are stitched to construct multi-source domains and target domain. Then, the informative samples close to the decision boundary are found in the target domain by using entropy, and they are employed to align and reassign each source domain with normalized mutual information. Furthermore, a multi-branch deep network (MBDN) is designed, and the maximum mean discrepancy is embedded in each branch to realign the specific feature distribution. Each branch is separately trained by an aligned source domain, and all the single branch transfer accuracies are arranged in descending order and utilized for weighted prediction of MBDN. Therefore, the most suitable number of source domains with top weights can be automatically determined. Extensive experiments are conducted based on 3 public MI-EEG datasets. DAMSDAF achieves the classification accuracies of 92.56%, 69.45% and 89.57%, and the statistical analysis is performed by the kappa value and t-test. Experimental results show that DAMSDAF significantly improves the transfer effects compared to the present methods, indicating that dual alignment can sufficiently use the different weighted samples and even source domains at different levels as well as realizing optimal selection of multi-source domains.

Unsupervised Motor Imagery Saliency Detection Based on Self-Attention Mechanism.

Detecting the salient parts of motor-imagery electroencephalogram (MI-EEG) signals can enhance the performance of the brain-computer interface (BCI) system and reduce the computational burden required for processing lengthy MI-EEG signals. In this paper, we propose an unsupervised method based on the self-attention mechanism to detect the salient intervals of MI-EEG signals automatically. Our suggested method can be used as a preprocessing step within any BCI algorithm to enhance its performance. The effectiveness of the suggested method is evaluated on the most widely used BCI algorithm, the common spatial pattern (CSP) algorithm, using dataset 2a from BCI competition IV. The results indicate that the proposed method can effectively prune MI-EEG signals and significantly enhance the performance of the CSP algorithm in terms of classification accuracy.

Empirical Mode Decomposition and a Bidirectional LSTM Architecture Used to Decode Individual Finger MI-EEG Signals

Brain-Computer Interface (BCI) paradigms based on Motor Imagery Electroencephalogram (MI-EEG) signals have been developed because the related signals can be generated voluntarily to control further applications. Researches using strong and stout limbs MI-EEG signals reported performing significant classification rates for BCI applied systems. However, MI-EEG signals produced by imagined movements of small limbs present a real classification challenge to be effectively used in BCI systems. It is due to a reduced signal level and increased noisy distorted effects. This study aims to decode individual right-hand fingers’ imagined movements for BCI applications, using MI-EEG signals from C3, Cz, P3, and Pz channels. For this purpose, the Empirical Mode Decomposition (EMD) preprocesses the non-stationary and non-linear EEG signals to finally use a Bidirectional Long Short-Term Memory (BiLSTM) to classify corresponding feature sequences. An average accuracy of 98.8 % was achieved for ring-finger movements decoding using k-fold cross-validation on a public dataset (Scientific-Data). The obtained results support that the proposed framework can be used for BCI control applications.

A dynamic directed transfer function for brain functional network-based feature extraction

Directed transfer function (DTF) is good at characterizing the pairwise interactions from whole brain network and has been applied in discrimination of motor imagery (MI) tasks. Considering the fact that MI electroencephalogram signals are more non-stationary in frequency domain than in time domain, and the activated intensities of α band (8–13 Hz) and β band [13–30 Hz, with beta_{1}(13–21 Hz) and beta_{2}(21–30 Hz) included] have considerable differences for different subjects, a dynamic DTF (DDTF) with variable model order and frequency band is proposed to construct the brain functional networks (BFNs), whose information flows and outflows are further calculated as network features and evaluated by support vector machine. Extensive experiments are conducted based on a public BCI competition dataset and a real-world dataset, the highest recognition rate achieve 100% and 86%, respectively. The experimental results suggest that DDTF can reflect the dynamic evolution of BFN, the best subject-based DDTF appears in one of four frequency sub-bands (α, β, beta_{1} ,{ }beta_{2}) for discrimination of MI tasks and is much more related to the current and previous states. Besides, DDTF is superior compared to granger causality-based and traditional feature extraction methods, the t-test and Kappa values show its statistical significance and high consistency as well.

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

Motor Imagery Electroencephalogram (MI-EEG) signals are widely used in Brain-Computer Interfaces (BCI). MI-EEG signals of large limbs movements have been explored in recent researches because they deliver relevant classification rates for BCI systems. However, smaller and noisy signals corresponding to hand-finger imagined movements are less frequently used because they are difficult to classify. This study proposes a method for decoding finger imagined movements of the right hand. For this purpose, MI-EEG signals from C3, Cz, P3, and Pz sensors were carefully selected to be processed in the proposed framework. Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals. At the same time, the sequence classification is performed by a stacked Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed method was evaluated using k-fold cross-validation on a public dataset, obtaining an accuracy of 82.26%.

Progress of classification algorithms for motor imagery electroencephalogram signals

Motor imagery (MI), motion intention of the specific body without actual movements, has attracted wide attention in fields as neuroscience. Classification algorithms for motor imagery electroencephalogram (MI-EEG) signals are able to distinguish different MI tasks based on the physiological information contained by the EEG signals, especially the features extracted from them. In recent years, there have been some new advances in classification algorithms for MI-EEG signals in terms of classifiers versus machine learning strategies. In terms of classifiers, traditional machine learning classifiers have been improved by some researchers, deep learning and Riemannian geometry classifiers have been widely applied as well. In terms of machine learning strategies, ensemble learning, adaptive learning, and transfer learning strategies have been utilized to improve classification accuracies or reach other targets. This paper reviewed the progress of classification algorithms for MI-EEG signals, summarized and evaluated the existing classifiers and machine learning strategies, to provide new ideas for developing classification algorithms with higher performance.

CluSem: Accurate clustering-based ensemble method to predict motor imagery tasks from multi-channel EEG data

BackgroundThe classification of motor imagery electroencephalogram (MI-EEG) is a pivotal task in the biosignal classification process in the brain-computer interface (BCI) applications. Currently, this bio-engineering-based technology is being employed by researchers in various fields to develop cutting-edge applications. The classification of real-time MI-EEG signals is the most challenging task in these applications. The prediction performance of the existing classification methods is still limited due to the high dimensionality and dynamic behaviors of the real-time EEG data. Proposed methodTo enhance the classification performance of real-time BCI applications, this paper presents a new clustering-based ensemble technique called CluSem to mitigate this problem. We also develop a new brain game called CluGame using this method to evaluate the classification performance of real-time motor imagery movements. In this game, real-time EEG signal classification and prediction tabulation through animated balls are controlled via threads. By playing this game, users can control the movements of the balls via the brain signals of motor imagery movements without using any traditional input devices. ResultsOur results demonstrate that CluSem is able to improve the classification accuracy between 5% and 15% compared to the existing methods on our collected as well as the publicly available EEG datasets. The source codes used to implement CluSem and CluGame are publicly available at https://github.com/MdOchiuddinMiah/MI-BCI_ML.

Multi-feature fusion method based on WOSF and MSE for four-class MI EEG identification

BackgroundBrain-Computer Interface (BCI) can bring great convenience to patients in the process of rehabilitation training and prosthetic control. However, how to extract effective features is a core issue in a BCI system. MethodsWe proposes the Multi-Feature Fusion Method based on Wavelength Optimal Spatial Filter and Multiscale Entropy for classifying the electroencephalogram signals (EEG) in four kinds of motor imagery tasks. The method can combine Wavelength features with Multiscale Entropy. ResultsTwo groups of experiments were conducted. One for simple four types of motor imagery (MI) tasks and another for unilateral limb. Experiments show that our proposed method has better performance compared to other methods. (82.55% versus 73.08% average accuracy respectively). ConclusionsThe proposed method can effectively improve the accuracy of EEG classification in multiclass motor imagery and will be useful for neurorehabilitation through motor imagery for hemiplegic patients.

Motor imagery EEG classification based on flexible analytic wavelet transform

Motor imagery electroencephalogram (MI-EEG) based brain-computer interface (BCI) is a burgeoning auxiliary means to realize rehabilitation therapy. One of the major concerns in MI-EEG based BCI is to have an accurate classification, and effective and fast feature extraction is the key to build a successful MI-EEG classification model. In this paper, a novel classification system for MI-EEG signals is proposed based on flexible analytic wavelet transform (FAWT). The filtered MI-EEG signals are firstly subjected to the FAWT to obtain sub-bands, and time-frequency features are calculated from the sub-bands. MDS is then adopted to reduce the dimension of the extracted features, and principal component analysis (PCA), kernel principal component analysis (KPCA), locally linear embedding (LLE) and Laplacian Eigenmaps (LE) are utilized as comparison. Finally, linear discriminant analysis (LDA) is utilized to complete the classification of left-hand (LH) and right-hand (RH) MI-EEG signals. The proposed method is experimentally validated on BCI Competition II Data Set III (BCI Dataset III) and BCI Competition III Data Set IIIb (BCI Dataset IIIb). As a result, the combined method of FAWT, MDS attains the maximal mutual information (MaI) of 0.95 and the maximum accuracy (ACC) of 94.29% using BCI Dataset III, and the mean of the maximal MaI steepness of 0.3740 using BCI Dataset IIIb. The proposed method yields better performance in comparison to the existing methods. Overall, the effectiveness of the proposed approach suggests that it can be a worthwhile and promising method for a MI-EEG based BCI system.

A Novel Simplified Convolutional Neural Network Classification Algorithm of Motor Imagery EEG Signals Based on Deep Learning

Left and right hand motor imagery electroencephalogram (MI-EEG) signals are widely used in brain-computer interface (BCI) systems to identify a participant intent in controlling external devices. However, due to a series of reasons, including low signal-to-noise ratios, there are great challenges for efficient motor imagery classification. The recognition of left and right hand MI-EEG signals is vital for the application of BCI systems. Recently, the method of deep learning has been successfully applied in pattern recognition and other fields. However, there are few effective deep learning algorithms applied to BCI systems, particularly for MI based BCI. In this paper, we propose an algorithm that combines continuous wavelet transform (CWT) and a simplified convolutional neural network (SCNN) to improve the recognition rate of MI-EEG signals. Using the CWT, the MI-EEG signals are mapped to time-frequency image signals. Then the image signals are input into the SCNN to extract the features and classify them. Tested by the BCI Competition IV Dataset 2b, the experimental results show that the average classification accuracy of the nine subjects is 83.2%, and the mean kappa value is 0.651, which is 11.9% higher than that of the champion in the BCI Competition IV. Compared with other algorithms, the proposed CWT-SCNN algorithm has a better classification performance and a shorter training time. Therefore, this algorithm could enhance the classification performance of MI based BCI and be applied in real-time BCI systems for use by disabled people.

A novel hybrid deep learning scheme for four-class motor imagery classification

Objective. Learning the structures and unknown correlations of a motor imagery electroencephalogram (MI-EEG) signal is important for its classification. It is also a major challenge to obtain good classification accuracy from the increased number of classes and increased variability from different people. In this study, a four-class MI task is investigated. Approach. An end-to-end novel hybrid deep learning scheme is developed to decode the MI task from EEG data. The proposed algorithm consists of two parts: a. A one-versus-rest filter bank common spatial pattern is adopted to preprocess and pre-extract the features of the four-class MI signal. b. A hybrid deep network based on the convolutional neural network and long-term short-term memory network is proposed to extract and learn the spatial and temporal features of the MI signal simultaneously. Main results. The main contribution of this paper is to propose a hybrid deep network framework to improve the classification accuracy of the four-class MI-EEG signal. The hybrid deep network is a subject-independent shared neural network, which means it can be trained by using the training data from all subjects to form one model. Significance. The classification performance obtained by the proposed algorithm on brain–computer interface (BCI) competition IV dataset 2a in terms of accuracy is 83% and Cohen’s kappa value is 0.80. Finally, the shared hybrid deep network is evaluated by every subject respectively, and the experimental results illustrate that the shared neural network has satisfactory accuracy. Thus, the proposed algorithm could be of great interest for real-life BCIs.

An Improved Refined Composite Multivariate Multiscale Fuzzy Entropy Method for MI-EEG Feature Extraction.

Feature extraction of motor imagery electroencephalogram (MI-EEG) has shown good application prospects in the field of medical health. Also, multivariate entropy-based feature extraction methods have been gradually applied to analyze complex multichannel biomedical signals, such as EEG and electromyography. Compared with traditional multivariate entropies, refined composite multivariate multiscale fuzzy entropy (RCmvMFE) overcomes the defect of unstable entropy values caused by the scale factor increase and is beneficial towards obtaining richer feature information. However, the coarse-grained process of RCmvMFE is mean filtered, which weakens Gaussian noise and is powerless against random impulse noise interference. This yields poor quality feature information and low accuracy classification. In this paper, RCmvMFE is improved (IRCmvMFE) by using composite filters in the coarse-grained procedure to enhance filter performance. Median filters are employed to remove the impulse noise interference from multichannel MI-EEG signals, and these filtered MI-EEGs are further smoothed by the mean filters. The multiscale IRCmvMFEs are calculated for all channels of composite filtered MI-EEGs, forming a feature vector, and a support vector machine is used for pattern classification. Based on two public datasets with different motor imagery tasks, the recognition results of 10 × 10-fold cross-validation achieved 99.43% and 99.86%, respectively, and the statistical analysis of experimental results was completed, showing the effectiveness of IRCmvMFE, as well. The proposed IRCmvMFE-based feature extraction method is superior compared to entropy-based and traditional methods.