Improving EEG Decoding via Clustering-Based Multitask Feature Learning

Dynamic Hierarchical Convolutional Attention Network for Recognizing Motor Imagery Intention

The neural activity patterns of localized brain regions are crucial for recognizing brain intentions. However, existing electroencephalogram (EEG) decoding models, especially those based on deep learning, predominantly focus on global spatial features, neglecting valuable local information, potentially leading to suboptimal performance. Therefore, this study proposed a dynamic hierarchical convolutional attention network (DH-CAN) that comprehensively learned discriminative information from both global and local spatial domains, as well as from time-frequency domains in EEG signals. Specifically, a multiscale convolutional block was designed to dynamically capture time-frequency information. The channels of EEG signals were mapped to different brain regions based on motor imagery neural activity patterns. The spatial features, both global and local, were then hierarchically extracted to fully exploit the discriminative information. Furthermore, regional connectivity was established using a graph attention network, incorporating it into the local spatial features. Particularly, this study shared network parameters between symmetrical brain regions to better capture asymmetrical motor imagery patterns. Finally, the learned multilevel features were integrated through a high-level fusion layer. Extensive experimental results on two datasets demonstrated that the proposed model performed excellently across multiple evaluation metrics, exceeding existing benchmark methods. These findings suggested that the proposed model offered a novel perspective for EEG decoding research.

CapMatch: Semi-Supervised Contrastive Transformer Capsule With Feature-Based Knowledge Distillation for Human Activity Recognition

This article proposes a semi-supervised contrastive capsule transformer method with feature-based knowledge distillation (KD) that simplifies the existing semisupervised learning (SSL) techniques for wearable human activity recognition (HAR), called CapMatch. CapMatch gracefully hybridizes supervised learning and unsupervised learning to extract rich representations from input data. In unsupervised learning, CapMatch leverages the pseudolabeling, contrastive learning (CL), and feature-based KD techniques to construct similarity learning on lower and higher level semantic information extracted from two augmentation versions of the data, "weak" and "timecut," to recognize the relationships among the obtained features of classes in the unlabeled data. CapMatch combines the outputs of the weak- and timecut-augmented models to form pseudolabeling and thus CL. Meanwhile, CapMatch uses the feature-based KD to transfer knowledge from the intermediate layers of the weak-augmented model to those of the timecut-augmented model. To effectively capture both local and global patterns of HAR data, we design a capsule transformer network consisting of four capsule-based transformer blocks and one routing layer. Experimental results show that compared with a number of state-of-the-art semi-supervised and supervised algorithms, the proposed CapMatch achieves decent performance on three commonly used HAR datasets, namely, HAPT, WISDM, and UCI_HAR. With only 10% of data labeled, CapMatch achieves values of higher than 85.00% on these datasets, outperforming 14 semi-supervised algorithms. When the proportion of labeled data reaches 30%, CapMatch obtains values of no lower than 88.00% on the datasets above, which is better than several classical supervised algorithms, e.g., decision tree and -nearest neighbor (KNN).

An Empirical Model-Based Algorithm for Removing Motion-Caused Artifacts in Motor Imagery EEG Data for Classification Using an Optimized CNN Model

Electroencephalography (EEG) is a non-invasive technique with high temporal resolution and cost-effective, portable, and easy-to-use features. Motor imagery EEG (MI-EEG) data classification is one of the key applications within brain-computer interface (BCI) systems, utilizing EEG signals from motor imagery tasks. BCI is very useful for people with severe mobility issues like quadriplegics, spinal cord injury patients, stroke patients, etc., giving them the freedom to a certain extent to perform activities without the need for a caretaker, like driving a wheelchair. However, motion artifacts can significantly affect the quality of EEG recordings. The conventional EEG enhancement algorithms are effective in removing ocular and muscle artifacts for a stationary subject but not as effective when the subject is in motion, e.g., a wheelchair user. In this research study, we propose an empirical error model-based artifact removal approach for the cross-subject classification of motor imagery (MI) EEG data using a modified CNN-based deep learning algorithm, designed to assist wheelchair users with severe mobility issues. The classification method applies to real tasks with measured EEG data, focusing on accurately interpreting motor imagery signals for practical application. The empirical error model evolved from the inertial sensor-based acceleration data of the subject in motion, the weight of the wheelchair, the weight of the subject, and the surface friction of the terrain under the wheelchair. Three different wheelchairs and five different terrains, including road, brick, concrete, carpet, and marble, are used for artifact data recording. After evaluating and benchmarking the proposed CNN and empirical model, the classification accuracy achieved is 94.04% for distinguishing between four specific classes: left, right, front, and back. This accuracy demonstrates the model's effectiveness compared to other state-of-the-art techniques. The comparative results show that the proposed approach is a potentially effective way to raise the decoding efficiency of motor imagery BCI.

Cross-Channel Specific-Mutual Feature Transfer Learning for Motor Imagery EEG Signals Decoding

In recent years, with the rapid development of deep learning, various deep learning frameworks have been widely used in brain-computer interface (BCI) research for decoding motor imagery (MI) electroencephalogram (EEG) signals to understand brain activity accurately. The electrodes, however, record the mixed activities of neurons. If different features are directly embedded in the same feature space, the specific and mutual features of different neuron regions are not considered, which will reduce the expression ability of the feature itself. We propose a cross-channel specific-mutual feature transfer learning (CCSM-FT) network model to solve this problem. The multibranch network extracts the specific and mutual features of brain's multiregion signals. Effective training tricks are used to maximize the distinction between the two kinds of features. Suitable training tricks can also improve the effectiveness of the algorithm compared with novel models. Finally, we transfer two kinds of features to explore the potential of mutual and specific features to enhance the expressive power of the feature and use the auxiliary set to improve identification performance. The experimental results show that the network has a better classification effect in the BCI Competition IV-2a and the HGD datasets.

Continual learning for seizure prediction via memory projection strategy

Despite extensive algorithms for epilepsy prediction via machine learning, most models are tailored for offline scenarios and cannot handle actual scenarios where data changes over time. Catastrophic forgetting(CF) for learned electroencephalogram(EEG) data occurs when EEG changes dynamically in the clinical setting. This paper implements a continual learning(CL) strategy Memory Projection(MP) for epilepsy prediction, which can be combined with other algorithms to avoid CF. Such a strategy enables the model to learn EEG data from each patient in dynamic subspaces with weak correlation layer by layer to minimize interference and promote knowledge transfer. Regularization Loss Reconstruction Algorithm and Matrix Dimensionality Reduction Algorithm are introduced into the core of MP. Experimental results show that MP exhibits excellent performance and low forgetting rates in sequential learning of seizure prediction. The forgetting rate of accuracy and sensitivity under multiple experiments are below 5%. When learning from multi-center datasets, the forgetting rates for accuracy and sensitivity decrease to 0.65% and 1.86%, making it comparable to state-of-the-art CL strategies. Through ablation experiments, we have analyzed that MP can operate with minimal storage and computational cost, which demonstrates practical potential for seizure prediction in clinical scenarios.

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification

In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.

Multi-Task Heterogeneous Ensemble Learning-Based Cross-Subject EEG Classification Under Stroke Patients

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

Analysis of brain activation and wave frequencies during a sentence completion task: a paradigm used with EEG in aphasic participants

Aphasia is a language disorder that occurs after brain injury and directly affects an individual's communication. The incidence of stroke increases with age, and one-third of people who have had a stroke develop aphasia. The severity of aphasia changes over time and some aspects of language may improve, while others remain compromised. Battery task training strategies are used in the rehabilitation of aphasics. The idea of this research is to use electroencephalography (EEG) as a non-invasive method, of electrophysiological monitoring, with a group of aphasic patients in rehabilitation process in a prevention and rehabilitation unit of the person with disabilities of the Unified Health System (SUS), of reference in the state of Bahia-Brazil. In this study, the goal is to analyze brain activation and wave frequencies of aphasic individuals during a sentence completion task, to possibly assist health professionals with the analysis of the aphasic subject's rehabilitation and task redefinition. We adopted the functional magnetic resonance imaging (fMRI) paradigm, proposed by the American Society for Functional Neuroradiology as a reference paradigm. We applied the paradigm in the group of aphasics with preserved comprehension, right hemiparesis, and left hemisphere injured or affected by stroke. We analyzed four electrodes (F3/F4 and F7/F8) corresponding to the left/right frontal cortex. Preliminary results of this study indicate a more robust activation in the right hemisphere (average of aphasics), with a difference of approximately 14% higher in Theta and Alpha frequencies, with 8% higher in low Beta (BetaL) and with approximately 1% higher in high Beta frequency (BetaH), Gamma frequency was higher by approximately 3% in the left hemisphere of the brain. The difference in electrical activation may be revealing to us a migration of language to the non-language dominant hemisphere. We point to possible evidence suggesting that EEG may be a promising tool for monitoring the rehabilitation of the aphasic subject.

Development of an Adaptive Artifact Subspace Reconstruction Based on Hebbian/Anti-Hebbian Learning Networks for Enhancing BCI Performance

Brain-computer interface (BCI) actively translates the brain signals into executable actions by establishing direct communication between the human brain and external devices. Recording brain activity through electroencephalography (EEG) is generally contaminated with both physiological and nonphysiological artifacts, which significantly hinders the BCI performance. Artifact subspace reconstruction (ASR) is a well-known statistical technique that automatically removes artifact components by determining the rejection threshold based on the initial reference EEG segment in multichannel EEG recordings. In real-world applications, the fixed threshold may limit the efficacy of the artifact correction, especially when the quality of the reference data is poor. This study proposes an adaptive online ASR technique by integrating the Hebbian/anti-Hebbian neural networks into the ASR algorithm, namely, principle subspace projection ASR (PSP-ASR) and principal subspace whitening ASR (PSW-ASR) that segmentwise self-organize the artifact subspace by updating the synaptic weights according to the Hebbian and anti-Hebbian learning rules. The effectiveness of the proposed algorithm is compared to the conventional ASR approaches on benchmark EEG dataset and three BCI frameworks, including steady-state visual evoked potential (SSVEP), rapid serial visual presentation (RSVP), and motor imagery (MI) by evaluating the root-mean-square error (RMSE), the signal-to-noise ratio (SNR), the Pearson correlation, and classification accuracy. The results demonstrated that the PSW-ASR algorithm effectively removed the EEG artifacts and retained the activity-specific brain signals compared to the PSP-ASR, standard ASR (Init-ASR), and moving-window ASR (MW-ASR) methods, thereby enhancing the SSVEP, RSVP, and MI BCI performances. Finally, our empirical results from the PSW-ASR algorithm suggested the choice of an aggressive cutoff range of c = 1-10 for activity-specific BCI applications and a moderate range of for the benchmark dataset and general BCI applications.

Past, Present, and Future of EEG-Based BCI Applications

An electroencephalography (EEG)-based brain-computer interface (BCI) is a system that provides a pathway between the brain and external devices by interpreting EEG. EEG-based BCI applications have initially been developed for medical purposes, with the aim of facilitating the return of patients to normal life. In addition to the initial aim, EEG-based BCI applications have also gained increasing significance in the non-medical domain, improving the life of healthy people, for instance, by making it more efficient, collaborative and helping develop themselves. The objective of this review is to give a systematic overview of the literature on EEG-based BCI applications from the period of 2009 until 2019. The systematic literature review has been prepared based on three databases PubMed, Web of Science and Scopus. This review was conducted following the PRISMA model. In this review, 202 publications were selected based on specific eligibility criteria. The distribution of the research between the medical and non-medical domain has been analyzed and further categorized into fields of research within the reviewed domains. In this review, the equipment used for gathering EEG data and signal processing methods have also been reviewed. Additionally, current challenges in the field and possibilities for the future have been analyzed.

MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification

OBJECTIVE

Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subject-independent manner.

METHODS

To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously.

RESULTS

This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72 %, and 2.23 % on the SMR-BCI, and OpenBMI datasets, respectively.

CONCLUSION

We demonstrate that MIN2Net improves discriminative information in the latent representation.

SIGNIFICANCE

This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration.

An empirical comparison of machine learning algorithms for the classification of brain signals to assess the impact of combined yoga and Sudarshan Kriya

Today's fast paced life reports so much stress among people that it may lead to various psychological and physical illnesses. Yoga and meditation are the best strategies to reduce the effect of stress on physical and mental level without any side-effects. In this study, combined yoga and Sudarshan Kriya (SK) has been used as an alternative and complementary therapy for the management of stress. The aim of the study is to find a method to classify the meditator and non-meditator states with the best accuracy. The 50 subjects have been participating in this study and divided into two groups, i.e. study and control group. The subjects with regular practice of Yoga and SK are known as meditators and the ones without any practice of yoga and meditation were known as non-meditators. Electroencephalogram (EEG) signals were acquired from these both groups before and after 3 months. The statistical parameters were computed from these acquired EEG signals using Discrete Wavelet Transform (DWT). These extracted statistical parameters were given as input to the classifiers. The decision tree, discriminant analysis, logistic regression, Support Vector Machine (SVM), Weighted K- Nearest Neighbour (KNN) and ensemble classifiers were used for classification of meditator and non- meditator states from the acquired EEG signals. The results have demonstrated that the SVM method gives the highest classification accuracy as compared to other classifiers. The proposed method can be used as a diagnosis system in clinical practices.

A Novel Two-Stage Refine Filtering Method for EEG-Based Motor Imagery Classification

Cerebral stroke is a common disease across the world, and it is a promising method to recognize the intention of stroke patients with the help of brain-computer interface (BCI). In the field of motor imagery (MI) classification, appropriate filtering is vital for feature extracting of electroencephalogram (EEG) signals and consequently influences the accuracy of MI classification. In this case, a novel two-stage refine filtering method was proposed, inspired by Gradient-weighted Class Activation Mapping (Grad-CAM), which uses the gradients of any target concept flowing into the final convolutional layer to highlight the important part of training data for predicting the concept. In the first stage, MI classification was carried out and then the frequency band to be filtered was calculated according to the Grad-CAM of the MI classification results. In the second stage, EEG was filtered and classified for a higher classification accuracy. To evaluate the filtering effect, this method was applied to the multi-branch neural network proposed in our previous work. Experiment results revealed that the proposed method reached state-of-the-art classification kappa value levels and acquired at least 3% higher kappa values than other methods This study also proposed some promising application scenarios with this filtering method.