Classification Performance Of Motor Imagery Research Articles

Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification.

In the brain-computer interface (BCI), motor imagery (MI) could be defined as the Electroencephalogram (EEG) signals through imagined movements, and ultimately enabling individuals to control external devices. However, the low signal-to-noise ratio, multiple channels and non-linearity are the essential challenges of accurate MI classification. To tackle these issues, we investigate the role of adaptive frequency bands selection and spatial-temporal feature learning in decoding motor imagery. We propose an Adaptive Filter of Frequency Bands based Coordinate Attention Network (AFFB-CAN) to improve the performance of MI classification. Specifically, we design the AFFB to adaptively obtain the upper and lower limits of frequency bands in order to alleviate information loss caused by manual selection. Next, we propose the CAN-based network to emphasize the key brain regions and temporal segments. And we design a multi-scale module to enhance temporal context learning. The conducted experiments on the BCI Competition IV-2a and 2b datasets reveal that our approach achieves an outstanding average accuracy, kappa values, and Macro F1-Score with 0.7825, 0.7104, and 0.7486 respectively. Similarly, for the BCI Competition IV-2b dataset, the average accuracy, kappa values, and F1-Score obtained are 0.8879, 0.7427, and 0.8734, respectively. The proposed AFFB-CAN method improves the performance of MI classification. In addition, our study confirms previous findings that motor imagery is mainly associated with µ and β rhythms. Moreover, we also find that γ rhythms also play an important role in MI classification.

Dynamic Convolution With Multilevel Attention for EEG-Based Motor Imagery Decoding

Brain-computer interface (BCI) is an innovative technology that utilizes artificial intelligence (AI) and wearable electroencephalography (EEG) sensors to decode brain signals and enhance the quality of life. EEG-based motor imagery (MI) brain signal is used in many BCI applications including smart healthcare, smart homes, and robotics control. However, the restricted ability to decode brain signals is a major factor preventing BCI technology from expanding significantly. In this study, we introduce a dynamic attention temporal convolutional network (D-ATCNet) for decoding EEG-based motor imagery signals. The D-ATCNet model uses dynamic convolution and multilevel attention to enhance the performance of MI classification with a relatively small number of parameters. D-ATCNet has two main blocks: dynamic and temporal convolution. Dynamic convolution uses multilevel attention to encode low-level MI-EEG information and temporal convolution uses shifted window with self-attention to extract high-level temporal information from the encoded signal. The proposed model performs better than the existing methods with an accuracy of 71.3% for subject-independent and 87.08% for subject-dependent using the BCI Competition IV-2a dataset.

Physics-Informed Attention Temporal Convolutional Network for EEG-Based Motor Imagery Classification

The brain-computer interface (BCI) is a cutting-edge technology that has the potential to change the world. Electroencephalogram (EEG) motor imagery (MI) signal has been used extensively in many BCI applications to assist disabled people, control devices or environments, and even augment human capabilities. However, the limited performance of brain signal decoding is restricting the broad growth of the BCI industry. In this article, we propose an attention-based temporal convolutional network (ATCNet) for EEG-based motor imagery classification. The ATCNet model utilizes multiple techniques to boost the performance of MI classification with a relatively small number of parameters. ATCNet employs scientific machine learning to design a domain-specific deep learning model with interpretable and explainable features, multihead self-attention to highlight the most valuable features in MI-EEG data, temporal convolutional network to extract high-level temporal features, and convolutional-based sliding window to augment the MI-EEG data efficiently. The proposed model outperforms the current state-of-the-art techniques in the BCI Competition IV-2a dataset with an accuracy of 85.38% and 70.97% for the subject-dependent and subject-independent modes, respectively.

Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification.

Motor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances in brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG). Previous studies have proposed various EEG-based classification algorithms to identify the MI, however, the performance of prior models was limited due to the cross-subject heterogeneity in EEG data and the shortage of EEG data for training. Therefore, inspired by generative adversarial network (GAN), this study aims to propose an improved domain adaption network based on Wasserstein distance, which utilizes existing labeled data from multiple subjects (source domain) to improve the performance of MI classification on a single subject (target domain). Specifically, our proposed framework consists of three components, including a feature extractor, a domain discriminator, and a classifier. The feature extractor employs an attention mechanism and a variance layer to improve the discrimination of features extracted from different MI classes. Next, the domain discriminator adopts the Wasserstein matrix to measure the distance between source domain and target domain, and aligns the data distributions of source and target domain via adversarial learning strategy. Finally, the classifier uses the knowledge acquired from the source domain to predict the labels in the target domain. The proposed EEG-based MI classification framework was evaluated by two open-source datasets, the BCI Competition IV Datasets 2a and 2b. Our results demonstrated that the proposed framework could enhance the performance of EEG-based MI detection, achieving better classification results compared with several state-of-the-art algorithms. In conclusion, this study is promising in helping the neural rehabilitation of different neuropsychiatric diseases.

Convolutional neural network and riemannian geometry hybrid approach for motor imagery classification

The electroencephalogram (EEG) signal is commonly applied in the brain-computer interface (BCI) system of the motor imagery paradigm because it is noninvasive and has a high time resolution. This paper proposes a motor imagery classification method based on convolutional neural networks and Riemannian geometry to overcome the problem of noise and extreme values impacting motor imagery classification performance. The time-domain properties of EEG signals are extracted using multiscale temporal convolutions, whereas the spatial aspects of EEG signals are extracted using multiple convolutional kernels learned by spatial convolution. The extracted features are mapped to a Riemannian manifold space, and bilinear mapping and logarithmic operations are performed on the features to solve the problem of noise and extreme values. The effectiveness of the proposed method is validated using four types of motor imagery in the BCI competition IV dataset 2a to evaluate the classification ability. The experimental results show that the proposed approach has obvious advantages in the classification performance of motor imagery.

Multi-Hierarchical Fusion to Capture the Latent Invariance for Calibration-Free Brain-Computer Interfaces.

Brain-computer interfaces (BCI) based motor imagery (MI) has become a research hotspot for establishing a flexible communication channel for patients with apoplexy or degenerative pathologies. Accurate decoding of motor imagery electroencephalography (MI-EEG) signals, while essential for effective BCI systems, is still challenging due to the significant noise inherent in the EEG signals and the lack of informative correlation between the signals and brain activities. The application of deep learning for EEG feature representation has been rarely investigated, nevertheless bringing improvements to the performance of motor imagery classification. This paper proposes a deep learning decoding method based on multi-hierarchical representation fusion (MHRF) on MI-EEG. It consists of a concurrent framework constructed of bidirectional LSTM (Bi-LSTM) and convolutional neural network (CNN) to fully capture the contextual correlations of MI-EEG and the spectral feature. Also, the stacked sparse autoencoder (SSAE) is employed to concentrate these two domain features into a high-level representation for cross-session and subject training guidance. The experimental analysis demonstrated the efficacy and practicality of the proposed approach using a public dataset from BCI competition IV and a private one collected by our MI task. The proposed approach can serve as a robust and competitive method to improve inter-session and inter-subject transferability, adding anticipation and prospective thoughts to the practical implementation of a calibration-free BCI system.

Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces

BackgroundCommon spatial pattern (CSP) is a prevalent method applied to feature extraction in motor imagery (MI)-based brain-computer interfaces (BCIs) recorded by electroencephalogram (EEG). The selection of time windows and frequency bands prominently affects the performance of CSP algorithms. Concerning the joint optimization of these two parameters, several studies have utilized a unified framework based on different feature selection strategies and achieved considerable improvement. However, during the feature selection process, useful information could be discarded inevitably and the underlying internal structure of features could be neglected. New methodIn this paper, we proposed a novel framework termed time window filter bank common spatial pattern with multi-view optimization (TWFBCSP-MVO) to further boost the decoding of MI tasks. Concretely, after extracting CSP features from different time-frequency decompositions of EEG signals, a preliminary screening strategy based on variance ratio was devised to filter out the unrelated spatial patterns. We then introduced a multi-view learning strategy for the simultaneous optimization of time windows and frequency bands. A support vector machine classifier was trained to determine the output of the brain. ResultsAn experimental study was conducted on two public datasets to verify the effectiveness of TWFBCSP-MVO. Results showed that the proposed TWFBCSP-MVO could help improve the performance of MI classification. Comparison with existing methodsIn comparison to other competing methods, the proposed method performed significantly better (p<0.01). ConclusionsThe proposed method is a promising contestant to improve the performance of practical MI-based BCIs.

Motor imagery EEG signal classification using upper triangle filter bank auto-encode method

In motor-imagery-based brain–computer interfaces, the frequency, and spatial information of electroencephalography signals can be used to improve the performance of motor imagery classification. However, the problem of subject-specific frequency band selection occurs frequently in spatial feature extraction. In this study, to enhance the frequency information in a spatial filter, we design an upper triangle filter bank to determine discriminative frequency components and apply the common spatial pattern to extract spatial features from sub-bands. Furthermore, an autoencoder neural network is constructed to reduce the high dimensionality of spatial features. The classification performance of the proposed method is experimentally evaluated on motor imagery datasets. The proposed method provides more discriminative features and higher classification performance in comparison with competing algorithms. This proposed filter bank method can be used to extend the other spatial and spectral processing method for motor imagery classification.

Decoding Finger Tapping With the Affected Hand in Chronic Stroke Patients During Motor Imagery and Execution.

In stroke rehabilitation, motor imagery based on a brain-computer interface is an extremely useful method to control an external device and utilize neurofeedback. Many studies have reported on the classification performance of motor imagery to decode individual fingers in stroke patients compared with healthy controls. However, classification performance for a given limb is still low because the differences between patients owing to brain reorganization after stroke are not considered. We used electroencephalography signals from eleven healthy controls and eleven stroke patients in this study. The subjects performed a finger tapping task during motor execution, and motor imagery was performed with the dominant and affected hands in the healthy controls and stroke patients, respectively. All fingers except for the thumb were classified using the proposed framework based on a voting module. The averaged four-class accuracies during motor execution and motor imagery were 53.16 ± 8.42% and 46.94 ± 5.99% for the healthy controls and 53.17 ± 14.09% and 66.00 ± 14.96% for the stroke patients, respectively. Importantly, the classification accuracies in the stroke patients were statistically higher than those in healthy controls during motor imagery. However, there was no significant difference between the accuracies of motor execution and motor imagery. These findings show the potential for high classification performance for a given limb during motor imagery in stroke patients. These results can also provide insights into controlling an external device on the basis of a brain-computer interface.

A Lasso quantile periodogram based feature extraction for EEG-based motor imagery

BackgroundThe extraction of relevant and distinct features from the electroencephalogram (EEG) signals is one of the most challenging task when implementing Brain Computer Interface (BCI) based systems. Frequency analysis techniques are recognised as one of the most suitable methods to have distinct information from EEG signals. However, existing studies use mostly classical approaches assuming that the signal is Gaussian, stationary and linear. These properties are not verified in the EEG case considering the complexity of the brain electrical activity. New methodThis paper proposes two new spectral estimators that are robust against non-Gaussian, non-linear and non-stationary signals. These two approaches use quantile regression and L1-norm regularisation to estimate the spectrum of the motor imagery (MI) related EEG. ResultsA dataset collected during a study of BCI motor imagery project conducted at Tshwane University of Technology (TUT), Pretoria, South Africa, is used to validate the proposed estimators. Experimental results demonstrate that the newly proposed approaches help improve the classification performance of MI. Comparison with existing methodsIn order to show the effectiveness of the proposed estimators, a comparative study is conducted, considering classical commonly used techniques such as FFT and Welch periodogram through 5 classification algorithms. ConclusionsThe proposed Quantile-based spectral estimators are potential methods to improve the classification performance of the EEG-Based motor imagery systems.

Classification of EEG Signals Based on Filter Bank and Sparse Representation in Motor Imagery Brain-Computer Interfaces

To improve the classification performance of motor imagery (MI) based brain-computer interfaces (BCIs), a new signal processing algorithm for classifying electroencephalogram (EEG) signals by combining filter bank and sparse representation is proposed. The broadband EEG signals of 8–30[Formula: see text]Hz are segmented into 10 sub-band signals using a filter bank. EEG signals in each sub-band are spatially filtered by common spatial pattern (CSP). Fisher score combined with grid search is used for selecting the optimal sub-band, the band power of which is employed for designing a dictionary matrix. A testing signal can be sparsely represented as a linear combination of some columns of the dictionary. The sparse coefficients are estimated by [Formula: see text] norm optimization, and the residuals of sparse coefficients are exploited for classification. The proposed classification algorithm was applied to two BCI datasets and compared with two traditional broadband CSP-based algorithms. The results showed that the proposed algorithm provided superior classification accuracies, which were better than those yielded by traditional algorithms, verifying the efficacy of the present algorithm.

An advanced bispectrum features for EEG-based motor imagery classification

Motor imagery (MI)-related brain activities can be effectively described by frequency analysis. Bispectrum is developed to overcome the drawback of power spectrum that the estimation of power spectrum discards the phase relationship among frequency components. However, the widely used bispectral features extraction method adds up all bispectral values as one feature, which could lead to the loss of effective information and increase of the sensitivity to non-linear and non-Gaussian noises. Thus, the representative bispectral features extraction method may be inefficient for MI classification. In addition, recent research suggests that the variations of EEG signals could provide more useful underlying information of event-related brain responses. This paper presents an advanced variations based bispectral feature extraction method to improve the performance of MI classification. The proposed method calculates the variations of MI-related EEG signals as input to bispectrum estimation. Besides, a new segmented bispectral sum features are developed to reduce the influence of non-linear and non-Gaussian noises and emphasize the valuable information for MI classification. The dataset collected in our laboratory and BCI Competition IV dataset 2b were adopted to validate the proposed method. The results indicate that the proposed method outperforms the power spectrum based methods and the representative bispectral features based methods. Moreover, compared to other state-of-the-art works, our approach also achieves the greater performance for MI classification.

WaveCSP: a robust motor imagery classifier for consumer EEG devices.

There is an increasing demand for reliable motor imagery (MI) classification algorithms for applications in consumer level brain-computer interfacing (BCI). For the practical use, such algorithms must be robust to both device limitations and subject variability, which make MI classification a challenging task. This study proposes methods to study the effect of limitations including a limited number of electrodes, limited spatial distribution of electrodes, lower signal quality, subject variabilities and BCI literacy, on the performance of MI classification. To mitigate these limitations, we propose a machine learning approach, WaveCSP that uses 24 features extracted from EEG signals using wavelet transform and common spatial pattern (CSP) filtering techniques. The algorithm shows better performance in terms of subject variability compared to existing work. The application of WaveCSP to Physionet MI database shows more than 50% of the 109 subjects achieving accuracy higher than 64%. The data obtained from a commercial EEG headset using the same experimental protocol result in up to four out of five subjects who had prior BCI experience (out of a total of 25 subjects) performing with accuracy higher than 64%.

Enhancing the performance of motor imagery classification to design a robust brain computer interface using feed forward back-propagation neural network

Abstract This paper proposes a feed forward back-propagation neural network (FFBPNN) based method to enhance the performance of the motor imagery classification. The dataset consists of fifty nine channels of EEG signals which are first normalised using minmax method and then given as input to the FFBPNN network. Experimental outcomes of the FFBPNN are recorded in term of ‘0’s or ‘1’s for two classes of motor imagery signals. The accuracy of the proposed FFBPNN method has been measured using confusion matrix, mean square error and percentage accuracy. However, accuracy of the FFBPNN based method is recorded up to 99.8%. Hence the proposed method gives better accuracy of the classification which will ultimately help in designing robust BCI.

EEG classification using sparse Bayesian extreme learning machine for brain–computer interface

Mu rhythm is a spontaneous neural response occurring during a motor imagery (MI) task and has been increasingly applied to the design of brain–computer interface (BCI). Accurate classification of MI is usually rather difficult to be achieved since mu rhythm is very weak and likely to be contaminated by other background noises. As an extension of the single layer feedforward network, extreme learning machine (ELM) has recently proven to be more efficient than support vector machine that is a benchmark for MI-related EEG classification. With probabilistic inference, this study introduces a sparse Bayesian ELM (SBELM)-based algorithm to improve the classification performance of MI. SBELM is able to automatically control the model complexity and exclude redundant hidden neurons by combining advantageous of both ELM and sparse Bayesian learning. The effectiveness of SBELM for MI-related EEG classification is validated on a public dataset from BCI Competition IV IIb in comparison with several other competing algorithms. Superior classification accuracy confirms that the proposed SBELM-based algorithm is a promising candidate for performance improvement of an MI BCI.

Improvements in event-related desynchronization and classification performance of motor imagery using instructive dynamic guidance and complex tasks

Background and objectiveThe motor-imagery based brain-computer interface supplies a potential approach for motor-impaired patients, not only to control rehabilitation facilities but also to promote recovery from motor dysfunctions. To improve event-related desynchronization during motor imagery and obtain improved brain-computer interface classification accuracy, we introduce dynamic video guidance and complex motor tasks to the motor imagery paradigm. MethodsEleven participants were included in the experiment; 64-channel electroencephalographic data were collected and analyzed during four motor imagery tasks with different guidance. Time-frequency analysis, spectral-time variation analysis, topographical distribution maps, and statistical analysis were utilized to analyze the event-related desynchronization patterns. Common spatial patterns were used to extract spatial pattern features and support vector machines were used to discriminate the offline classification accuracies in three bands (the alpha band, beta band, alpha and beta band) for comparison. ResultsThe experimental outcomes showed that complex motor imagery tasks coupled with dynamic video guidance induced significantly stronger event-related desynchronization than other paradigms, which use simple motor imagery tasks or static guidance. Similar results were obtained during analysis of the motor imagery brain-computer interface classification performance; namely, the highest average classification accuracy in complex and dynamic guidance was improved by approximately 14%, compared with static guidance. For individually specified paradigms, all participants obtained a classification accuracy that exceeded or was equal to 87.5%. ConclusionsThis study provides an optional route to enhance the event-related desynchronization activities and classification accuracy of a motor imagery brain-computer interface through optimization of motor imagery tasks and instructive guidance.

Classification of EEG Motor Imagery Multi Class Signals Based on Cross Correlation

Many techniques are developed for improving the classification performance of motor imagery (MI) signals used in Brain computer interfacing (BCI). Still there is scope for improvement of performance using various techniques. In this paper, cross correlation (CC) technique has been used for features extraction from EEG signal and the final classification was done based on voting method which selects the best classifier among the five classifiers used for classification. Our approach was tested on public data set 2a from BCI competition IV. The results proved that our approach outperformed already existing approaches with 29.82% improvement in kappa values.

Optimizing spatial patterns with sparse filter bands for motor-imagery based brain–computer interface

BackgroundCommon spatial pattern (CSP) has been most popularly applied to motor-imagery (MI) feature extraction for classification in brain–computer interface (BCI) application. Successful application of CSP depends on the filter band selection to a large degree. However, the most proper band is typically subject-specific and can hardly be determined manually. New methodThis study proposes a sparse filter band common spatial pattern (SFBCSP) for optimizing the spatial patterns. SFBCSP estimates CSP features on multiple signals that are filtered from raw EEG data at a set of overlapping bands. The filter bands that result in significant CSP features are then selected in a supervised way by exploiting sparse regression. A support vector machine (SVM) is implemented on the selected features for MI classification. ResultsTwo public EEG datasets (BCI Competition III dataset IVa and BCI Competition IV IIb) are used to validate the proposed SFBCSP method. Experimental results demonstrate that SFBCSP help improve the classification performance of MI. Comparison with existing methodsThe optimized spatial patterns by SFBCSP give overall better MI classification accuracy in comparison with several competing methods. ConclusionsThe proposed SFBCSP is a potential method for improving the performance of MI-based BCI.

Structure constrained semi-nonnegative matrix factorization for EEG-based motor imagery classification

BackgroundElectroencephalogram (EEG) provides a non-invasive approach to measure the electrical activities of brain neurons and has long been employed for the development of brain-computer interface (BCI). For this purpose, various patterns/features of EEG data need to be extracted and associated with specific events like cue-paced motor imagery. However, this is a challenging task since EEG data are usually non-stationary time series with a low signal-to-noise ratio. New methodIn this study, we propose a novel method, called structure constrained semi-nonnegative matrix factorization (SCS-NMF), to extract the key patterns of EEG data in time domain by imposing the mean envelopes of event-related potentials (ERPs) as constraints on the semi-NMF procedure. The proposed method is applicable to general EEG time series, and the extracted temporal features by SCS-NMF can also be combined with other features in frequency domain to improve the performance of motor imagery classification. ResultsReal data experiments have been performed using the SCS-NMF approach for motor imagery classification, and the results clearly suggest the superiority of the proposed method. Comparison with existing methodsComparison experiments have also been conducted. The compared methods include ICA, PCA, Semi-NMF, Wavelets, EMD and CSP, which further verified the effectivity of SCS-NMF. ConclusionsThe SCS-NMF method could obtain better or competitive performance over the state of the art methods, which provides a novel solution for brain pattern analysis from the perspective of structure constraint.

Enhancing the performance of motor imagery EEG classification using phase features.

An electroencephalogram recognition system considering phase features is proposed to enhance the performance of motor imagery classification in this study. It mainly consists of feature extraction, feature selection and classification. Surface Laplacian filter is used for background removal. Several potential features, including phase features, are then extracted to enhance the classification accuracy. Next, genetic algorithm is used to select sub-features from feature combination. Finally, selected features are classified by extreme learning machine. Compared with "without phase features" and linear discriminant analysis on motor imagery data from 2 data sets, the results denote that the proposed system achieves enhanced performance, which is suitable for the brain-computer interface applications.