Classification Of Motor Imagery Signals Research Articles

Multi-source transfer learning via optimal transport feature ranking for EEG classification

Motor imagery (MI) brain-computer interface (BCI) paradigms have been extensively used in neurological rehabilitation. However, due to the required long calibration time and non-stationary nature of electroencephalogram (EEG) signals, it is challenging to obtain a substantial sample size of EEG data. Transfer learning (TL), which leverages knowledge from existing subjects to enhance the learning performance in new subjects, has been employed to solve this problem. Previous studies often extract sample features directly from the two domains for transfer learning, leading to poor features and negative transfer. To overcome this limitation, an optimal transport feature selection method was developed in this study to select the most suitable features for migration to enhance the generalization capability of the TL. This was achieved by analyzing the diagonal value similarity of the optimal transport coupling matrix. First, the Riemannian tangent space mapping method was used to map the sample covariance matrix of EEG trials from the Riemannian manifold to tangent space. Secondly, the optimal subset of EEG features was selected via the optimal transport feature selection method. Subsequently, the separate distribution alignment method was employed to minimize dissimilarities between the source and target domains. Finally, the weighted voting mechanisms were integrated for decision fusion. The proposed multi-source transfer feature learning (MSTFL) method was validated based on two public BCI Competition IV datasets. Our results demonstrated superior classification accuracy of 85.93% and 79.48%, respectively, on the two public datasets, compared to state-of-the-art models. These findings indicate the effectiveness of our proposed MSTFL model for both feature extraction and classification of MI signals.

Improving cross-subject classification performance of motor imagery signals: a data augmentation-focused deep learning framework

Motor imagery brain-computer interfaces (MI-BCIs) have gained a lot of attention in recent years thanks to their potential to enhance rehabilitation and control of prosthetic devices for individuals with motor disabilities. However, accurate classification of motor imagery signals remains a challenging task due to the high inter-subject variability and non-stationarity in the electroencephalogram (EEG) data. In the context of MI-BCIs, with limited data availability, the acquisition of EEG data can be difficult. In this study, several data augmentation techniques have been compared with the proposed data augmentation technique adaptive cross-subject segment replacement (ACSSR). This technique, in conjunction with the proposed deep learning framework, allows for a combination of similar subject pairs to take advantage of one another and boost the classification performance of MI-BCIs. The proposed framework features a multi-domain feature extractor based on common spatial patterns with a sliding window and a parallel two-branch convolutional neural network. The performance of the proposed methodology has been evaluated on the multi-class BCI Competition IV Dataset 2a through repeated 10-fold cross-validation. Experimental results indicated that the implementation of the ACSSR method (80.47%) in the proposed framework has led to a considerable improvement in the classification performance compared to the classification without data augmentation (77.63%), and other fundamental data augmentation techniques used in the literature. The study contributes to the advancements for the development of effective MI-BCIs by showcasing the ability of the ACSSR method to address the challenges in motor imagery signal classification tasks.

Deep temporal networks for EEG-based motor imagery recognition.

The electroencephalogram (EEG) based motor imagery (MI) signal classification, also known as motion recognition, is a highly popular area of research due to its applications in robotics, gaming, and medical fields. However, the problem is ill-posed as these signals are non-stationary and noisy. Recently, a lot of efforts have been made to improve MI signal classification using a combination of signal decomposition and machine learning techniques but they fail to perform adequately on large multi-class datasets. Previously, researchers have implemented long short-term memory (LSTM), which is capable of learning the time-series information, on the MI-EEG dataset for motion recognition. However, it can not model very long-term dependencies present in the motion recognition data. With the advent of transformer networks in natural language processing (NLP), the long-term dependency issue has been widely addressed. Motivated by the success of transformer algorithms, in this article, we propose a transformer-based deep learning neural network architecture that performs motion recognition on the raw BCI competition III IVa and IV 2a datasets. The validation results show that the proposed method achieves superior performance than the existing state-of-the-art methods. The proposed method produces classification accuracy of 99.7% and 84% on the binary class and the multi-class datasets, respectively. Further, the performance of the proposed transformer-based model is also compared with LSTM.

Cross-dataset transfer learning for motor imagery signal classification via multi-task learning and pre-training

Objective. Deep learning (DL) models have been proven to be effective in decoding motor imagery (MI) signals in Electroencephalogram (EEG) data. However, DL models’ success relies heavily on large amounts of training data, whereas EEG data collection is laborious and time-consuming. Recently, cross-dataset transfer learning has emerged as a promising approach to meet the data requirements of DL models. Nevertheless, transferring knowledge across datasets involving different MI tasks remains a significant challenge in cross-dataset transfer learning, limiting the full utilization of valuable data resources. Approach: This study proposes a pre-training-based cross-dataset transfer learning method inspired by Hard Parameter Sharing in multi-task learning. Different datasets with distinct MI paradigms are considered as different tasks, classified with shared feature extraction layers and individual task-specific layers to allow cross-dataset classification with one unified model. Then, Pre-training and fine-tuning are employed to transfer knowledge across datasets. We also designed four fine-tuning schemes and conducted extensive experiments on them. Main results: The results showed that compared to models without pre-training, models with pre-training achieved a maximum increase in accuracy of 7.76%. Moreover, when limited training data were available, the pre-training method significantly improved DL model’s accuracy by 27.34% at most. The experiments also revealed that pre-trained models exhibit faster convergence and remarkable robustness. The training time per subject could be reduced by up to 102.83 s, and the variance of classification accuracy decreased by 75.22% at best. Significance: This study represents the first comprehensive investigation of the cross-dataset transfer learning method between two datasets with different MI tasks. The proposed pre-training method requires only minimal fine-tuning data when applying DL models to new MI paradigms, making MI-Brain–computer interface more practical and user-friendly.

A convolutional spiking neural network with adaptive coding for motor imagery classification

Motor imagery (MI) signal classification is crucial for brain-computer interfaces (BCI). The third-generation neural network, spiking neural network (SNN), has rich neurodynamic properties in the spatiotemporal domain, and therefore it is more suitable for processing EEG signals. However, the feature extraction capability of the SNN previously applied to MI signal classification is limited by its structure, and the model’s classification accuracy is not comparable to the state-of-the-art algorithms. In this paper, we propose a spiking neural network model called SCNet, which combines the feature extraction capability of CNN with the biological interpretability of SNN, making the model structurally closer to the biological neuronal dynamical system and improving the classification accuracy. SCNet reduces information loss by adaptive coding with learnability and solves the training difficulties of spiking neural networks by surrogate gradient learning. We evaluated the performance of the proposed SCNet on three typically representative motor imagery datasets. The validation shows that the model outperforms state-of-the-art SNN-based MI classification methods and various ANN and machine learning methods. The experimental results demonstrate the generality and effectiveness of the proposed motor imagery EEG signal classification model. Better classification results can be obtained by designing a well-structured spiking neural network.

Input Shape Effect on Classification Performance of Raw EEG Motor Imagery Signals with Convolutional Neural Networks for Use in Brain—Computer Interfaces

EEG signals are interpreted, analyzed and classified by many researchers for use in brain-computer interfaces. Although there are many different EEG signal acquisition methods, one of the most interesting is motor imagery signals. Many different signal processing methods, machine learning and deep learning models have been developed for the classification of motor imagery signals. Among these, Convolutional Neural Network models generally achieve better results than other models. Because the size and shape of the data is important for training Convolutional Neural Network models and discovering the right relationships, researchers have designed and experimented with many different input shape structures. However, no study has been found in the literature evaluating the effect of different input shapes on model performance and accuracy. In this study, the effects of different input shapes on model performance and accuracy in the classification of EEG motor imagery signals were investigated, which had not been specifically studied before. In addition, signal preprocessing methods, which take a long time before classification, were not used; rather, two CNN models were developed for training and classification using raw data. Two different datasets, BCI Competition IV 2A and 2B, were used in classification processes. For different input shapes, 53.03-89.29% classification accuracy and 2-23 s epoch time were obtained for 2A dataset, 64.84-84.94% classification accuracy and 4-10 s epoch time were obtained for 2B dataset. This study showed that the input shape has a significant effect on the classification performance, and when the correct input shape is selected and the correct CNN architecture is developed, feature extraction and classification can be done well by the CNN architecture without any signal preprocessing.

Motor imagery signal classification using Wavelet packet decomposition and modified binary grey wolf optimization

Nowadays, Electroencephalogram (EEG) signals are widely used in brain-computer interfaces (BCIs), including the identification of motor imagery (MI) activities and prostheses. In this proposed scheme, wavelet packet decomposition (WPD) is used with approximate entropy (ApEn) as a mechanism for generating features of Electroencephalogram (EEG) signals for the MI-BCI system. Usually, features extracted from an EEG signal include redundant and irrelevant features. This paper proposes a novel scheme of feature selection using Modified Binary grey wolf optimization (MBGWO) for MI-BCI with EEG. Finally, performance of the proposed approach is evaluated using machine learning technique K-nearest Neighbors (KNN). In this study, KNN showed classification accuracy for subjects “a" and “b" is 92.86% and 91.53% respectively. Where “a" and “b" are two participants in Dataset I from BCI competition IV. The results show that the suggested algorithm considerably impacts classification performance. Classification results suggest that the proposed method used in this study can achieve better performance in BCI applications for understanding MI activities in patients with physical disabilities.

CNN models for EEG motor imagery signal classification

CNN models for EEG motor imagery signal classification

A novel multi-branch hybrid neural network for motor imagery EEG signal classification

As a typical spontaneous brain-computer interface system, motor imagery has been widely used in areas such as robot control and stroke rehabilitation. Recently, researchers have started to study and propose various Convolutional Neural Network (CNN) structures based on motor imagery signals and have obtained better decoding accuracy compared with traditional machine learning algorithms. In this paper, we focus on a four-class motor imagery task. Therefore, we propose an end-to-end novel multi-branch hybrid neural network for motor imagery EEG signal classification. Notably, we divide the input signal into four frequency bands associated with the motor imagery signal. Meanwhile, we also introduced a Bidirectional Gated Recurrent Unit (BGRU) to identify EEG features. Nevertheless, it is extremely difficult to collect high-quality EEG data and the classification accuracy is degraded due to the strict requirements of the subjects and the experimental environment. To address this issue, we propose a novel data augmentation approach for frequency domain segmentation swap (Seg-Swap) for improving EEG motor imagery signal classification accuracy. We make use of the publicly available BCI IV 2a dataset and High Gamma dataset to evaluate the decoding performance of the model. The proposed multi-branch hybrid neural network (MBHNN) achieves 86.15% and 95.04% on the both datasets. Compared with several state-of-the-art (SOA) algorithms, our proposed model has a slight improvement in classification accuracy. Experimental results show that our proposed MBHNN has higher decoding classification and stronger robustness.

A lightweight and accurate double-branch neural network for four-class motor imagery classification

Deep learning is an important pathway for investigation of motor imagery signal classification. Nevertheless, maintaining a good compromise between performance and computational cost has been a major challenge in developing deep models for decoding motor imagery EEG. In this paper, a novel shallow double-branch convolutional neural network (DSCNN) is proposed for four-class motor imagery classification. The proposed CNN adopts parallel extraction of two branches to improve classification accuracy. Meanwhile, in order to constrain the depth of the whole network, the left branch only contained two single temporal and spatial convolutional layers to extract common EEG features. Similarly, the right branch first introduced 1D convolution to exploit the channel dependency and temporal features across multiple time-scales, secondly a depth-wise separable convolutional layer was applied for optimizing EEG signal series. Then the feature representation for final classification was obtained by merging intermediate features extracted from the two branches. Also, the DSCNN is an end-to-end decoder, as it employs the raw EEG data as inputs and does not require additional complex preprocessing. The proposed model was evaluated on public benchmark BCI competition IV dataset 2a and achieved in terms of accuracy is 85% and kappa value is 0.79. Compared with other state-of-the-art algorithms, the experiment results reveal that the DSCNN has higher decoding accuracy and robustness, as well as a 10% improvement in accuracy than the single general shallow model. Furthermore, as a lightweight architecture, the DSCNN relies on a lower computational power than similar mainstream models, which is more in line with the requirements of low delay and real-time performance in practical BCI applications.

Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach

The technology of the brain-computer interface (BCI) employs electroencephalogram (EEG) signals to establish direct interaction between the human body and its surroundings with promising applications in medical rehabilitative services and cognitive science. Deep learning approaches, particularly the detection and analysis of motor imagery signals using convolutional neural network (CNN) frameworks have produced outstanding results in the BCI system in recent years. The complex process of data representation, on the other hand, limits practical applications, and the end-to-end approach reduces the accuracy of recognition. Moreover, since noise and other signal sources can interfere with brain electrical capacitance, EEG classifiers are difficult to improve and have limited generalisation ability. To address these issues, this paper proposes a new approach for EEG motor imagery signal classification by using a variational autoencoder to remove noise from the signals, followed by a combination of deep autoencoder (DAE) and a CNN architecture to classify EEG motor imagery signals which is capable of training a deep neural network to replicate its input to output using encoding and decoding operations. Experimental results show that the proposed approach for motor imagery EEG signal classification is feasible and that it outperforms current CNN-based approaches and several traditional machine learning approaches.

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network.

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.

Multiclass Classification of Spatially Filtered Motor Imagery EEG Signals Using Convolutional Neural Network for BCI Based Applications

Brain–Computer Interface (BCI) system offers a new means of communication for those with paralysis or severe neuromuscular disorders. BCI systems based on Motor Imagery (MI) Electroencephalography (EEG) signals enable the user to convert their thoughts into actions without any voluntary muscle movement. Recently, Convolutional neural network (CNN) is used for the classification of MI signals. However, to produce good MI classification, it is necessary to effectively represent the signal as an input image to the CNN and train the deep learning classifier using large training data. In this work, EEG signals are acquired over 16 channels and are filtered using a bandpass filter with the frequency range of 1 to 100 Hz. The processed signal is spatially filtered using Common Spatial Pattern (CSP) filter. The spectrograms of the spatially filtered signals are given as input to CNN. A single convolutional layer CNN is designed to classify left hand, right hand, both hands, and feet MI EEG signals. The size of the training data is increased by augmenting the spectrograms of the EEG signals. The CNN classifier was evaluated using MI signals acquired from twelve healthy subjects. Results show that the proposed method achieved an average classification accuracy of 95.18 ± 2.51% for two-class (left hand and right hand) and 87.37 ± 1.68% for four-class (Left hand, Right hand, Both hands, and Feet) MI. Thus, the method manifests that this 2D representation of 1D EEG signal along with image augmentation shows a high potential for classification of MI EEG signals using the designed CNN model.

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.

Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals

In motor imagery (MI) based brain–computer interface (BCI) signal analysis, mu and beta rhythms of electroencephalograms (EEGs) are widely investigated due to their high temporal resolution and capability to define the different movement-related mental tasks separately. However, due to the high dimensions and subject-specific behaviour of EEG features, there is a need for a suitable feature selection algorithm that can select the optimal features to give the best classification performance along with increased computational efficiency. The present study proposes a feature selection algorithm based on neighbourhood component analysis (NCA) with modification of the regularization parameter. In the experiment, time, frequency, and phase features of the EEG are extracted using a dual-tree complex wavelet transform (DTCWT). Afterwards, the proposed algorithm selects the most significant EEG features, and using these selected features, a support vector machine (SVM) classifier performs the classification of MI signals. The proposed algorithm has been validated experimentally on two public BCI datasets (BCI Competition II Dataset III and BCI Competition IV Dataset 2b). The classification performance of the algorithm is quantified by the average accuracy and kappa coefficient, whose values are 80.7% and 0.615 respectively. The performance of the proposed algorithm is compared with standard feature selection methods based on Genetic Algorithm (GA), Principal Component Analysis (PCA), and ReliefF and performs better than these methods. Further, the proposed algorithm selects the lowest number of features and results in increased computational efficiency, which makes it a promising feature selection tool for an MI-based BCI system.

Stockwell-common spatial pattern technique for motor imagery-based Brain Computer Interface design

In this paper, an attempt is made to obtain optimal S-Transform based Common Spatial features for automated recognition of motor imagery signals. The combined approach of S-Transform and Common Spatial Pattern is established as an efficient technique for binary class Brain Computer Interface implementation. The method is carried out in four methodological steps. In the first step, Electroencephalogram signals are decomposed into time-frequency sub-bands using S-Transform based decomposition technique. The S-Transform coefficients are grouped to represent distinct frequency sub-bands of Electroencephalogram activity in the second step. In the third step, the Common Spatial Pattern method is applied on fundamental sub-bands to prepare discriminative feature vector. The classification of motor imagery signals is performed using three soft computing techniques viz. Least Square-Support Vector Machine, Random Forest and Artificial Neural Network in the fourth step. Classification results illustrate the efficacy of proposed technique in motor imagery signal classification task.

Some considerations of common spatial pattern for better classification in brain-computer interfaces

EEG-based motor imagery signal classification is very important in brain-computer interface (BCI) technology. In this work, we develop a common spatial pattern (CSP) technique for feature extraction in a BCI system. To confirm classification improvement, classification accuracy was analysed by using four statistics, namely mean, variance, skewness, and kurtosis within the CSP paradigm. The data from the dataset III of BCI competition II were used and simulated using MATLAB. The results show that the best classification accuracy is obtained when the CSP algorithm uses the variance statistic for feature extraction.

A neural network-based optimal spatial filter design method for motor imagery classification.

In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN) is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP) algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.

An Analysis of the Effect of EEG Frequency Bands on the Classification of Motor Imagery Signals

An Analysis of the Effect of EEG Frequency Bands on the Classification of Motor Imagery Signals