Common Spatial Pattern Features Research Articles

EEG-based brain-computer interface methods with the aim of rehabilitating advanced stage ALS patients

Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease that leads to progressive muscle weakness and paralysis, ultimately resulting in the loss of ability to communicate and control the environment. EEG-based Brain-Computer Interface (BCI) methods have shown promise in providing communication and control with the aim of rehabilitating ALS patients. In particular, P300-based BCI has been widely studied and used for ALS rehabilitation. Other EEG-based BCI methods, such as Motor Imagery (MI) based BCI and Hybrid BCI, have also shown promise in ALS rehabilitation. Nonetheless, EEG-based BCI methods hold great potential for improvement. This review article introduces and reviews FFT, WPD, CSP, CSSP, CSP, and GC feature extraction methods. The Common Spatial Pattern (CSP) is an efficient and common technique for extracting data properties used in BCI systems. In addition, Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Neural Networks (NN), and Deep Learning (DL) classification methods were introduced and reviewed. SVM is the most appropriate classifier due to its insensitivity to the curse of dimensionality. Also, DL is used in the design of BCI systems and is a good choice for BCI systems based on motor imagery with big datasets. Despite the progress made in the field, there are still challenges to overcome, such as improving the accuracy and reliability of EEG signal detection and developing more intuitive and user-friendly interfaces By using BCI, disabled patients can communicate with their caregivers and control their environment using various devices, including wheelchairs, and robotic arms.

Improved motor imagery classification using adaptive spatial filters based on particle swarm optimization algorithm.

As a typical self-paced brain-computer interface (BCI) system, the motor imagery (MI) BCI has been widely applied in fields such as robot control, stroke rehabilitation, and assistance for patients with stroke or spinal cord injury. Many studies have focused on the traditional spatial filters obtained through the common spatial pattern (CSP) method. However, the CSP method can only obtain fixed spatial filters for specific input signals. In addition, the CSP method only focuses on the variance difference of two types of electroencephalogram (EEG) signals, so the decoding ability of EEG signals is limited. To make up for these deficiencies, this study introduces a novel spatial filter-solving paradigm named adaptive spatial pattern (ASP), which aims to minimize the energy intra-class matrix and maximize the inter-class matrix of MI-EEG after spatial filtering. The filter bank adaptive and common spatial pattern (FBACSP), our proposed method for MI-EEG decoding, amalgamates ASP spatial filters with CSP features across multiple frequency bands. Through a dual-stage feature selection strategy, it employs the Particle Swarm Optimization algorithm for spatial filter optimization, surpassing traditional CSP approaches in MI classification. To streamline feature sets and enhance recognition efficiency, it first prunes CSP features in each frequency band using mutual information, followed by merging these with ASP features. Comparative experiments are conducted on two public datasets (2a and 2b) from BCI competition IV, which show the outstanding average recognition accuracy of FBACSP. The classification accuracy of the proposed method has reached 74.61 and 81.19% on datasets 2a and 2b, respectively. Compared with the baseline algorithm, filter bank common spatial pattern (FBCSP), the proposed algorithm improves by 11.44 and 7.11% on two datasets, respectively (p < 0.05). It is demonstrated that FBACSP has a strong ability to decode MI-EEG. In addition, the analysis based on mutual information, t-SNE, and Shapley values further proves that ASP features have excellent decoding ability for MI-EEG signals and explains the improvement of classification performance by the introduction of ASP features. These findings may provide useful information to optimize EEG-based BCI systems and further improve the performance of non-invasive BCI.

A New Bearing Fault Diagnosis Approach based on Common Spatial Pattern Features

This study offers a novel intelligent detection method of rolling bearings that applied: the Common Spatial Pattern (CSP) method for feature extraction of bearing faults. CSP maximizes the variance ratio of the two class signal matrices coming from different sources. Different from the frequency features, characteristic vibration features from each measurement that can distinguish between the faulty and the healthy bearings were extracted. Artificial Neural Network (ANN), Support Vector Machine (SVM), and K-Nearest Neighbour (k-NN) methods were tested on two different data sets. An 88.5% accuracy was obtained with ANN for two-class fault detection and 93.5% for fault classification. The classification results were compared with classical time domain feature sets. CSP features have achieved higher accuracies in all two-class and multiclass cases. Therefore, the CSP features can be a possible means for condition monitoring of bearings through vibration data.

One-Dimensional Local Binary Pattern and Common Spatial Pattern Feature Fusion Brain Network for Central Neuropathic Pain

Central neuropathic pain (CNP) after spinal cord injury (SCI) is related to the plasticity of cerebral cortex. The plasticity of cortex recorded by electroencephalogram (EEG) signal can be used as a biomarker of CNP. To analyze changes in the brain network mechanism under the combined effect of injury and pain or under the effect of pain, this paper mainly studies the changes of brain network functional connectivity in patients with neuropathic pain and without neuropathic pain after SCI. This paper has recorded the EEG with the CNP group after SCI, without the CNP group after SCI, and a healthy control group. Phase-locking value has been used to construct brain network topological connectivity maps. By comparing the brain networks of the two groups of SCI with the healthy group, it has been found that in the [Formula: see text] and [Formula: see text] frequency bands, the injury increases the functional connectivity between the frontal lobe and occipital lobes, temporal, and parietal of the patients. Furthermore, the comparison of brain networks between the group with CNP and the group without CNP after SCI has found that pain has a greater effect on the increased connectivity within the patients’ frontal lobes. Motor imagery (MI) data of CNP patients have been used to extract one-dimensional local binary pattern (1D-LBP) and common spatial pattern (CSP) features, the left and right hand movements of the patients’ MI have been classified. The proposed LBP-CSP feature method has achieved the highest accuracy of 98.6% and the average accuracy of 91.5%. The results of this study have great clinical significance for the neural rehabilitation and brain–computer interface of CNP patients.

EM-CSP: An efficient multiclass common spatial pattern feature method for speech imagery EEG signals recognition

BackgroundBrain-computer interface (BCI) technology has many applications in various scientific fields, such as used in communication (speech recognition). The data of imagery speech has been collected in electroencephalogram (EEG) signals. MethodIn this paper, we propose an approach for EEG feature extraction of imagined speech with high accuracy and efficiency. In this way, we improve the common spatial pattern (CSP) binary algorithm to multiclass level in two parts ‘One-vs-One’ and ‘One-vs-All’. The “Kara One” dataset is used in this research that includes EEG signals of thirteen subjects with twelve trials and sixty-four channels for any four English words signals and seven English phonemes signals. ResultsWe compared our proposed CSP to other imagined speech feature methods. The classification accuracy of the second part of the proposed method is 97.34% in the subject-wise overall model which is 19.97% better than the best previous result. ConclusionWe have obtained the highest classification accuracy for sixty-four channels, which is the highest accuracy ever achieved using this database. Our proposed model is ready to be tested with more EEG data. This proposed work, which includes an ensemble method for classifying speech imagery words, can greatly contribute to intuitive BCI development using silent speech.

Review of public motor imagery and execution datasets in brain-computer interfaces.

The demand for public datasets has increased as data-driven methodologies have been introduced in the field of brain-computer interfaces (BCIs). Indeed, many BCI datasets are available in various platforms or repositories on the web, and the studies that have employed these datasets appear to be increasing. Motor imagery is one of the significant control paradigms in the BCI field, and many datasets related to motor tasks are open to the public already. However, to the best of our knowledge, these studies have yet to investigate and evaluate the datasets, although data quality is essential for reliable results and the design of subject- or system-independent BCIs. In this study, we conducted a thorough investigation of motor imagery/execution EEG datasets recorded from healthy participants published over the past 13 years. The 25 datasets were collected from six repositories and subjected to a meta-analysis. In particular, we reviewed the specifications of the recording settings and experimental design, and evaluated the data quality measured by classification accuracy from standard algorithms such as Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) for comparison and compatibility across the datasets. As a result, we found that various stimulation types, such as text, figure, or arrow, were used to instruct subjects what to imagine and the length of each trial also differed, ranging from 2.5 to 29 s with a mean of 9.8 s. Typically, each trial consisted of multiple sections: pre-rest (2.38 s), imagination ready (1.64 s), imagination (4.26 s, ranging from 1 to 10 s), the post-rest (3.38 s). In a meta-analysis of the total of 861 sessions from all datasets, the mean classification accuracy of the two-class (left-hand vs. right-hand motor imagery) problem was 66.53%, and the population of the BCI poor performers, those who are unable to reach proficiency in using a BCI system, was 36.27% according to the estimated accuracy distribution. Further, we analyzed the CSP features and found that each dataset forms a cluster, and some datasets overlap in the feature space, indicating a greater similarity among them. Finally, we checked the minimal essential information (continuous signals, event type/latency, and channel information) that should be included in the datasets for convenient use, and found that only 71% of the datasets met those criteria. Our attempts to evaluate and compare the public datasets are timely, and these results will contribute to understanding the dataset's quality and recording settings as well as the use of using public datasets for future work on BCIs.

Hybrid EEG-fNIRS Brain Computer Interface Based on Common Spatial Pattern by Using EEG-Informed General Linear Model

Hybrid brain computer interfaces (BCI) utilizing the high temporal resolution of electroencephalography (EEG) and the high spatial resolution of near-infrared spectroscopy (fNIRS) are preferred over single-modal BCIs. However, due to the large dimensionality of the multi-class statistical features commonly used in fNIRS signals, it is easy to cause overfitting of the EEG-fNIRS hybrid BCI classifier. Therefore, a low-dimensional feature extraction method for fNIRS based on the EEG-informed fNIRS general linear model (GLM) analysis is proposed in this paper. First, a regression coefficient matrix is obtained by using the EEG-informed fNIRS GLM with a time window added, and the common spatial pattern (CSP) features of this regression coefficient matrix are extracted as the fNIRS features. Lastly, the fNIRS features were combined with the CSP features extracted from the optimal narrow band of EEG as hybrid features, and the support vector machine (SVM) method is used to classify the samples with hybrid features. The proposed method was tested on a publicly available motor imagery dataset. The classification accuracy using fNIRS signals alone reached 68.79% (oxygenated hemoglobin) and 68.62% (deoxygenated hemoglobin), and the classification accuracy of combining EEG-fNIRS features reached 79.48%, which was higher than other existing methods using the same dataset. By using this fNIRS feature extraction method, the problem of poor performance of CSP on fNIRS signals is solved, which not only enriches the processing methods of fNIRS signals, but also improves the classification accuracy of hybrid EEG-fNIRS BCI in motor imagery tasks.

Feature optimization based on improved novel global harmony search algorithm for motor imagery electroencephalogram classification.

Effectively decoding electroencephalogram (EEG) pattern for specific mental tasks is a crucial topic in the development of brain-computer interface (BCI). Extracting common spatial pattern (CSP) features from motor imagery EEG signals is often highly dependent on the selection of frequency band and time interval. Therefore, optimizing frequency band and time interval would contribute to effective feature extraction and accurate EEG decoding. This study proposes an approach based on an improved novel global harmony search (INGHS) to optimize frequency-time parameters for effective CSP feature extraction. The INGHS algorithm is applied to find the optimal frequency band and temporal interval. The linear discriminant analysis and support vector machine are used for EEG pattern decoding. Extensive experimental studies are conducted on three EEG datasets to assess the effectiveness of our proposed method. The average test accuracy obtained by the time-frequency parameters selected by the proposed INGHS method is slightly better than artificial bee colony (ABC) and particle swarm optimization (PSO) algorithms. Furthermore, the INGHS algorithm is superior to PSO and ABC in running time. These superior experimental results demonstrate that the optimal frequency band and time interval selected by the INGHS algorithm could significantly improve the decoding accuracy compared with the traditional CSP method. This method has a potential to improve the performance of MI-based BCI systems.

Towards real-world BCI: CCSPNet, a compact subject-independent motor imagery framework

A conventional brain-computer interface (BCI) requires a complete data gathering, training, and calibration phase for each user before it can be used. In recent years, a number of subject-independent (SI) BCIs have been developed. Many of these methods yield a weaker performance compared to the subject-dependent (SD) approach, and some are computationally expensive. A potential real-world application would greatly benefit from a more accurate, compact, and computationally efficient subject-independent BCI. In this work, we propose a novel subject-independent BCI framework, named CCSPNet (Convolutional Common Spatial Pattern Network) that is trained on the motor imagery (MI) paradigm of a large-scale electroencephalography (EEG) signals database consisting of 400 trials for every 54 subjects who perform two-class hand-movement MI tasks. The proposed framework applies a wavelet kernel convolutional neural network (WKCNN) and a temporal convolutional neural network (TCNN) in order to represent and extract the spectral features of EEG signals. A common spatial pattern (CSP) algorithm is implemented for spatial feature extraction, and the number of CSP features is reduced by a dense neural network. Finally, the class label is determined by a linear discriminant analysis (LDA) classifier. The CCSPNet evaluation results show that it is possible to have a compact BCI that achieves both SD and SI state-of-the-art performance comparable to complex and computationally expensive models.

Parallel genetic algorithm based common spatial patterns selection on time–frequency decomposed EEG signals for motor imagery brain-computer interface

Since the nonlinear and non-stationary characteristics of electroencephalogram (EEG) signals, motor imagery based brain-computer interface (MI-BCI) have problems of poor recognition accuracy and robustness across subjects and recording sessions. To address such problems, we extract common spatial pattern features on a detailed decomposition of time segments and frequency bands (TSFBCSP) on EEG signals, and propose a novel encoding approach of genetic algorithm (GA) for features selection. The proposed approach selects the most robust and discriminative CSP features to enhance the accuracy and robustness of EEG signals recognition. To improve the efficiency of TSFBCSP features selection, the parallel GA is implemented on a MapReduce framework (MRPGA). Comparative experiments have been done on two publicly available datasets (2a and 2b) from BCI competition IV. The excellent average recognition accuracy shows that the proposed TSFBCSP-GA/MRPGA has a promising candidate performance improvement on MI-BCI. Classification accuracies based on the optimal EEG segments and sub-bands have achieved 74.92 % and 81.04 % for the dataset 2a and 2b, respectively, and the faster classification accuracies of 74.54 % and 79.78 % has been achieved for the MRPGA architecture. Ablation study further proves the feasibility and effectiveness of the proposed algorithm, and discusses the parameters setting of applying it to actual MI-BCI applications.

Learning Optimal Time-Frequency-Spatial Features by the CiSSA-CSP Method for Motor Imagery EEG Classification.

The common spatial pattern (CSP) is a popular method in feature extraction for motor imagery (MI) electroencephalogram (EEG) classification in brain-computer interface (BCI) systems. However, combining temporal and spectral information in the CSP-based spatial features is still a challenging issue, which greatly affects the performance of MI-based BCI systems. Here, we propose a novel circulant singular spectrum analysis embedded CSP (CiSSA-CSP) method for learning the optimal time-frequency-spatial features to improve the MI classification accuracy. Specifically, raw EEG data are first segmented into multiple time segments and spectrum-specific sub-bands are further derived by CiSSA from each time segment in a set of non-overlapping filter bands. CSP features extracted from all time-frequency segments contain more sufficient time-frequency-spatial information. An experimental study was implemented on the publicly available EEG dataset (BCI Competition III dataset IVa) and a self-collected experimental EEG dataset to validate the effectiveness of the CiSSA-CSP method. Experimental results demonstrate that discriminative and robust features are extracted effectively. Compared with several state-of-the-art methods, the proposed method exhibited optimal accuracies of 96.6% and 95.2% on the public and experimental datasets, respectively, which confirms that it is a promising method for improving the performance of MI-based BCIs.

A machine-learning approach for predicting impaired consciousness in absence epilepsy.

Behavior during 3–4 Hz spike‐wave discharges (SWDs) in absence epilepsy can vary from obvious behavioral arrest to no detectible deficits. Knowing if behavior is impaired is crucial for clinical care but may be difficult to determine without specialized behavioral testing, often inaccessible in practice. We aimed to develop a pure electroencephalography (EEG)‐based machine‐learning method to predict SWD‐related behavioral impairment. Our classification goals were 100% predictive value, with no behaviorally impaired SWDs misclassified as spared; and maximal sensitivity. First, using labeled data with known behavior (130 SWDs in 34 patients), we extracted EEG time, frequency domain, and common spatial pattern features and applied support vector machines and linear discriminant analysis to classify SWDs as spared or impaired. We evaluated 32 classification models, optimized with 10‐fold cross‐validation. We then generalized these models to unlabeled data (220 SWDs in 41 patients), where behavior during individual SWDs was not known, but observers reported the presence of clinical seizures. For labeled data, the best classifier achieved 100% spared predictive value and 93% sensitivity. The best classifier on the unlabeled data achieved 100% spared predictive value, but with a lower sensitivity of 35%, corresponding to a conservative classification of 8 patients out of 23 as free of clinical seizures. Our findings demonstrate the feasibility of machine learning to predict impaired behavior during SWDs based on EEG features. With additional validation and optimization in a larger data sample, applications may include EEG‐based prediction of driving safety, treatment adjustment, and insight into mechanisms of impaired consciousness in absence seizures.

High-Frequency Vibrating Stimuli Using the Low-Cost Coin-Type Motors for SSSEP-Based BCI.

Steady-state somatosensory-evoked potential- (SSSEP-) based brain-computer interfaces (BCIs) have been applied for assisting people with physical disabilities since it does not require gaze fixation or long-time training. Despite the advancement of various noninvasive electroencephalogram- (EEG-) based BCI paradigms, researches on SSSEP with the various frequency range and related classification algorithms are relatively unsettled. In this study, we investigated the feasibility of classifying the SSSEP within high-frequency vibration stimuli induced by a versatile coin-type eccentric rotating mass (ERM) motor. Seven healthy subjects performed selective attention (SA) tasks with vibration stimuli attached to the left and right index fingers. Three EEG feature extraction methods, followed by a support vector machine (SVM) classifier, have been tested: common spatial pattern (CSP), filter-bank CSP (FBCSP), and mutual information-based best individual feature (MIBIF) selection after the FBCSP. Consequently, the FBCSP showed the highest performance at 71.5 ± 2.5% for classifying the left and right-hand SA tasks than the other two methods (i.e., CSP and FBCSP-MIBIF). Based on our findings and approach, the high-frequency vibration stimuli using low-cost coin motors with the FBCSP-based feature selection can be potentially applied to developing practical SSSEP-based BCI systems.

A Power Spectrum Pattern Difference-Based Time-Frequency Sub-Band Selection Method for MI-EEG Classification

Motor imagery-based brain-computer interface (MI-BCI) is considered to be the most promising technology, which can help patients with muscle disorders to carry out rehabilitation training and assist in activities of daily living. However, the time window and frequency band of the ERD/ERS pattern activated by motor imagery vary from person to person. In this study, we propose a power spectrum pattern difference-based time-frequency sub-band selection (PSPD) method, which can further improve the classification performance of MI EEG. To better analyze the sensorimotor rhythm, we divide the EEG channels and extract the average and maximum pattern difference of the power spectrum according to the division. Then, the difference metric of the power spectrum pattern difference of inter-sample sets is calculated by dynamic time warping distance, and the consistency metric of the power spectrum pattern difference of intra-sample sets is calculated by mean pooling, and the optimal time-frequency sub-band is selected based on these two metrics. Finally, the optimal time-frequency sub-bands are respectively used for the common spatial pattern feature extraction and the linear kernel support vector machine classification. The proposed PSPD method achieves an average classification accuracy of 84.51%, 84.10% and 73.21% in BCI Competition IV Dataset IIa, Dataset IIb and OpenBMI dataset, respectively. Compared with the state-of-the-art methods, the PSPD method achieves the highest classification accuracy and good stability on three datasets. Excellent experimental results show that the PSPD method has great potential in MI-BCI’s motion intention decoding.

Design a Novel BCI for Neurorehabilitation Using Concurrent LFP and EEG Features: A Case Study.

Brain-computer interfaces (BCI) that enables people with severe motor disabilities to use their brain signals for direct control of objects have attracted increased interest in rehabilitation. To date, no study has investigated feasibility of the BCI framework incorporating both intracortical and scalp signals. Concurrent local field potential (LFP) from the hand-knob area and scalp EEG were recorded in a paraplegic patient undergoing a spike-based close-loop neurorehabilitation training. Based upon multimodal spatio-spectral feature extraction and Naïve Bayes classification, we developed, for the first time, a novel LFP-EEG-BCI for motor intention decoding. A transfer learning (TL) approach was employed to further improve the feasibility. The performance of the proposed LFP-EEG-BCI for four-class upper-limb motor intention decoding was assessed. Using a decision fusion strategy, we showed that the LFP-EEG-BCI significantly (p 0.05) outperformed single modal BCI (LFP-BCI and EEG-BCI) in terms of decoding accuracy with the best performance achieved using regularized common spatial pattern features. Interrogation of feature characteristics revealed discriminative spatial and spectral patterns, which may lead to new insights for better understanding of brain dynamics during different motor imagery tasks and promote development of efficient decoding algorithms. Moreover, we showed that similar classification performance could be obtained with few training trials, therefore highlighting the efficacy of TL. The present findings demonstrated the superiority of the novel LFP-EEG-BCI in motor intention decoding. This work introduced a novel LFP-EEG-BCI that may lead to new directions for developing practical neurorehabilitation systems with high detection accuracy and multi-paradigm feasibility in clinical applications.

Multimodal collaborative BCI system based on the improved CSP feature extraction algorithm

BackgroundAs a novel approach for people to directly communicate with an external device, the study of brain-computer interfaces (BCIs) has become well-rounded. However, similar to the real-world scenario, where individuals are expected to work in groups, the BCI systems should be able to replicate group attributes. MethodsWe proposed a 4-order cumulants feature extraction method (CUM4- CSP) based on the common spatial patterns (CSP) algorithm. Simulation experiments conducted using motion visual evoked potentials (mVEP) EEG data verified the robustness of the proposed algorithm. In addition, to freely choose paradigms, we adopted the mVEP and steady-state visual evoked potential (SSVEP) paradigms and designed a multimodal collaborative BCI system based on the proposed CUM4- CSP algorithm. The feasibility of the proposed multimodal collaborative system framework was demonstrated using a multiplayer game controlling system that simultaneously facilitates the coordination and competitive control of two users on external devices. To verify the robustness of the proposed scheme, we recruited 30 subjects to conduct online game control experiments, and the results were statistically analyzed. ResultsThe simulation results prove that the proposed CUM4-CSP algorithm has good noise immunity. The online experimental results indicate that the subjects could reliably perform the game confrontation operation with the selected BCI paradigm. ConclusionsThe proposed CUM4-CSP algorithm can effectively extract features from EEG data in a noisy environment. Additionally, the proposed scheme may provide a new solution for EEG-based group BCI research.

Real-Movement Classification for Hybrid Brain-Computer Interface Applications Using Neighborhood Component Analysis to Select Common Spatial Pattern Features from EMG and EEG Signals

Real-Movement Classification for Hybrid Brain-Computer Interface Applications Using Neighborhood Component Analysis to Select Common Spatial Pattern Features from EMG and EEG Signals

SincNet-Based Hybrid Neural Network for Motor Imagery EEG Decoding.

It is difficult to identify optimal cut-off frequencies for filters used with the common spatial pattern (CSP) method in motor imagery (MI)-based brain-computer interfaces (BCIs). Most current studies choose filter cut-frequencies based on experience or intuition, resulting in sub-optimal use of MI-related spectral information in the electroencephalography (EEG). To improve information utilization, we propose a SincNet-based hybrid neural network (SHNN) for MI-based BCIs. First, raw EEG is segmented into different time windows and mapped into the CSP feature space. Then, SincNets are used as filter bank band-pass filters to automatically filter the data. Next, we used squeeze-and-excitation modules to learn a sparse representation of the filtered data. The resulting sparse data were fed into convolutional neural networks to learn deep feature representations. Finally, these deep features were fed into a gated recurrent unit module to seek sequential relations, and a fully connected layer was used for classification. We used the BCI competition IV datasets 2a and 2b to verify the effectiveness of our SHNN method. The mean classification accuracies (kappa values) of our SHNN method are 0.7426 (0.6648) on dataset 2a and 0.8349 (0.6697) on dataset 2b, respectively. The statistical test results demonstrate that our SHNN can significantly outperform other state-of-the-art methods on these datasets.

A multi-feature fusion decoding study for unilateral upper-limb fine motor imagery.

To address the fact that the classical motor imagination paradigm has no noticeable effect on the rehabilitation training of upper limbs in patients after stroke and the corresponding feature extraction algorithm is limited to a single domain, this paper describes the design of a unilateral upper-limb fine motor imagination paradigm and the collection of data from 20 healthy people. It presents a feature extraction algorithm for multi-domain fusion and compares the common spatial pattern (CSP), improved multiscale permutation entropy (IMPE) and multi-domain fusion features of all participants through the use of decision tree, linear discriminant analysis, naive Bayes, a support vector machine, k-nearest neighbor and ensemble classification precision algorithms in the ensemble classifier. For the same subject, the average classification accuracy improvement of the same classifier for multi-domain feature extraction relative to CSP feature results went up by 1.52%. The average classification accuracy improvement of the same classifier went up by 32.87% relative to the IMPE feature classification results. This study's unilateral fine motor imagery paradigm and multi-domain feature fusion algorithm provide new ideas for upper limb rehabilitation after stroke.

Iterative Outlier Removal Clustering Based Time-Frequency-Spatial Feature Selection for Binary EEG Motor Imagery Decoding

Electroencephalography (EEG)-based motor imagery (MI) brain-computer interface (BCI) is a bridge in the instruments of rehabilitation and motor assistance field to control external assist devices without external stimulation. Feature extraction (FE) is a key to improving the performance of EEG MI decoding. Existing FE methods usually extract single-domain features such as spatial, frequency features, or dual-domain features such as time–frequency features. However, the multidomains features which describe the intent more comprehensively are not simultaneously extracted. Therefore, inspired by short-time Fourier transform (STFT) and common spatial pattern (CSP) FE methods, a frequency-spatial-temporal multidomain (FSTMD) FE method is proposed. To solve the problem of the high dimensions of the FSTMD features, a feature selection (FS) method is designed. In the proposed FSTMD FE process, the STFT is employed to extract the time–frequency domain features first. Then, the time–frequency features of each channel are cascaded. After that, the cascaded features are divided according to time segments. At last, the covariance transform is performed for each time segment. Since the proposed features have a one-to-one correspondence with frequency, channel, and time, the extracted features have good interpretability. The proposed FS method selects the features in the frequency-spatial domain of each time segment based on mutual information and correlation metrics first and then selects the key time segment based on clustering with outlier removal. The performance of the proposed feature is verified in BCI Competition IV Dataset IIa and IIb. Compared to the CSP feature in the only spatial domain, the proposed feature has significantly lower deviation and slightly higher accuracy. The average recognition accuracy of the proposed MI decoding framework is 85.1% on the dataset IIb session 3, which is competitive compared with the state-of-the-art methods.