A review on transfer learning in EEG signal analysis

Addressing data limitations in seizure prediction through transfer learning

According to the literature, seizure prediction models should be developed following a patient-specific approach. However, seizures are usually very rare events, meaning the number of events that may be used to optimise seizure prediction approaches is limited. To overcome such constraint, we analysed the possibility of using data from patients from an external database to improve patient-specific seizure prediction models. We present seizure prediction models trained using a transfer learning procedure. We trained a deep convolutional autoencoder using electroencephalogram data from 41 patients collected from the EPILEPSIAE database. Then, a bidirectional long short-term memory and a classifier layers were added on the top of the encoder part and were optimised for 24 patients from the Universitätsklinikum Freiburg individually. The encoder was used as a feature extraction module. Therefore, its weights were not changed during the patient-specific training. Experimental results showed that seizure prediction models optimised using pretrained weights present about four times fewer false alarms while maintaining the same ability to predict seizures and achieved more 13% validated patients. Therefore, results evidenced that the optimisation using transfer learning was more stable and faster, saving computational resources. In summary, adopting transfer learning for seizure prediction models represents a significant advancement. It addresses the data limitation seen in the seizure prediction field and offers more efficient and stable training, conserving computational resources. Additionally, despite the compact size, transfer learning allows to easily share data knowledge due to fewer ethical restrictions and lower storage requirements. The convolutional autoencoder developed in this study will be shared with the scientific community, promoting further research.

A systematic evaluation of Euclidean alignment with deep learning for EEG decoding

Objective:Electroencephalography signals are frequently used for various Brain-Computer interface (BCI) tasks. While deep learning (DL) techniques have shown promising results, they are hindered by the substantial data requirements. By leveraging data from multiple subjects, transfer learning enables more effective training of DL models. A technique that is gaining popularity is Euclidean alignment (EA) due to its ease of use, low computational complexity, and compatibility with DL models. However, few studies evaluate its impact on the training performance of shared and individual DL models. In this work, we systematically evaluate the effect of EA combined with DL for decoding BCI signals.Approach:We used EA as a pre-processing step to train shared DL models with data from multiple subjects and evaluated their transferability to new subjects.Main results:Our experimental results show that it improves decoding in the target subject by 4.33% and decreases convergence time by more than 70%. We also trained individual models for each subject to use as a majority-voting ensemble classifier. In this scenario, using EA improved the 3-model ensemble accuracy by 3.71%. However, when compared to the shared model with EA, the ensemble accuracy was 3.62% lower.Significance:EA succeeds in the task of improving transfer learning performance with DL models and, could be used as a standard pre-processing technique.

Exploring the frontier: Transformer-based models in EEG signal analysis for brain-computer interfaces

This review systematically explores the application of transformer-based models in EEG signal processing and brain-computer interface (BCI) development, with a distinct focus on ensuring methodological rigour and adhering to empirical validations within the existing literature. By examining various transformer architectures, such as the Temporal Spatial Transformer Network (TSTN) and EEG Conformer, this review delineates their capabilities in mitigating challenges intrinsic to EEG data, such as noise and artifacts, and their subsequent implications on decoding and classification accuracies across disparate mental tasks. The analytical scope extends to a meticulous examination of attention mechanisms within transformer models, delineating their role in illuminating critical temporal and spatial EEG features and facilitating interpretability in model decision-making processes. The discourse additionally encapsulates emerging works that substantiate the efficacy of transformer models in noise reduction of EEG signals and diversifying applications beyond the conventional motor imagery paradigm. Furthermore, this review elucidates evident gaps and propounds exploratory avenues in the applications of pre-trained transformers in EEG analysis and the potential expansion into real-time and multi-task BCI applications. Collectively, this review distils extant knowledge, navigates through the empirical findings, and puts forward a structured synthesis, thereby serving as a conduit for informed future research endeavours in transformer-enhanced, EEG-based BCI systems.

A 3D ray traced biological neural network learning model

Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current choices of transfer learning algorithms are limited because the transferred models always have to adhere to the dimensions of the base model and can not easily modify the neural architecture to solve other datasets. On the other hand, biological neural networks (BNNs) are adept at rearranging themselves to tackle completely different problems using transfer learning. Taking advantage of BNNs, we design a dynamic neural network that is transferable to any other network architecture and can accommodate many datasets. Our approach uses raytracing to connect neurons in a three-dimensional space, allowing the network to grow into any shape or size. In the Alcala dataset, our transfer learning algorithm trains the fastest across changing environments and input sizes. In addition, we show that our algorithm also outperformance the state of the art in EEG dataset. In the future, this network may be considered for implementation on real biological neural networks to decrease power consumption.

Three-stage transfer learning for motor imagery EEG recognition

Motor imagery (MI) paradigms have been widely used in neural rehabilitation and drowsiness state assessment. The progress in brain-computer interface (BCI) technology has emphasized the importance of accurately and efficiently detecting motor imagery intentions from electroencephalogram (EEG). Despite the recent breakthroughs made in developing EEG-based algorithms for decoding MI, the accuracy and efficiency of these models remain limited by technical challenges posed by cross-subject heterogeneity in EEG data processing and the scarcity of EEG data for training. Inspired by the optimal transport theory, this study aims to develop a novel three-stage transfer learning (TSTL) method, which uses the existing labeled data from a source domain to improve classification performance on an unlabeled target domain. Notably, the proposed method comprises three components, namely, the Riemannian tangent space mapping (RTSM), source domain transformer (SDT), and optimal subspace mapping (OSM). The RTSM maps a symmetric positive definite matrix from the Riemannian space to the tangent space to minimize the marginal probability distribution drift. The SDT transforms the source domain to a target domain by finding the optimal transport mapping matrix to reduce the joint probability distribution differences. The OSM finally maps the transformed source domain and original target domain to the same subspace to further mitigate the distribution discrepancy. The performance of the proposed method was validated on two public BCI datasets, and the average accuracy of the algorithm on two datasets was 72.24% and 69.29%. Our results demonstrated the improved performance of EEG-based MI detection in comparison with state-of-the-art algorithms.

Increasing accessibility to a large brain-computer interface dataset: Curation of physionet EEG motor movement/imagery dataset for decoding and classification

A reliable motor imagery (MI) brain-computer interface (BCI) requires accurate decoding, which in turn requires model calibration using electroencephalography (EEG) signals from subjects executing or imagining the execution of movements. Although the PhysioNet EEG Motor Movement/Imagery Dataset is currently the largest EEG dataset in the literature, relatively few studies have used it to decode MI trials. In the present study, we curated and cleaned this dataset to store it in an accessible format that is convenient for quick exploitation, decoding, and classification using recent integrated development environments. We dropped six subjects owing to anomalies in EEG recordings and pre-possessed the rest, resulting in 103 subjects spanning four MI and four motor execution tasks. The annotations were coded to correspond to different tasks using numerical values. The resulting dataset is stored in both MATLAB structure and CSV files to ensure ease of access and organization. We believe that improving the accessibility of this dataset will help EEG-based MI-BCI decoding and classification, enabling more reliable real-life applications. The convenience and ease of access of this dataset may therefore lead to improvements in cross-subject classification and transfer learning.

Synthesizing affective neurophysiological signals using generative models: A review paper

The integration of emotional intelligence in machines is an important step in advancing human-computer interaction. This demands the development of reliable end-to-end emotion recognition systems. However, the scarcity of public affective datasets presents a challenge. In this literature review, we emphasize the use of generative models to address this issue in neurophysiological signals, particularly Electroencephalogram (EEG) and Functional Near-Infrared Spectroscopy (fNIRS). We provide a comprehensive analysis of different generative models used in the field, examining their input formulation, deployment strategies, and methodologies for evaluating the quality of synthesized data. This review serves as a comprehensive overview, offering insights into the advantages, challenges, and promising future directions in the application of generative models in emotion recognition systems. Through this review, we aim to facilitate the progression of neurophysiological data augmentation, thereby supporting the development of more efficient and reliable emotion recognition systems.

EEG-based emotion recognition systems; comprehensive study

Emotion recognition technology through EEG signal analysis is currently a fundamental concept in artificial intelligence. This recognition has major practical implications in emotional health care, human-computer interaction, and so on. This paper provides a comprehensive study of different methods for extracting electroencephalography (EEG) features for emotion recognition from four different perspectives, including time domain features, frequency domain features, time-frequency features, and nonlinear features. We summarize the current pattern recognition methods adopted in most related works, and with the rapid development of deep learning (DL) attracting the attention of researchers in this field, we pay more attention to deep learning-based studies and analyse the characteristics, advantages, disadvantages, and applicable scenarios. Finally, the current challenges and future development directions in this field were summarized. This paper can help novice researchers in this field gain a systematic understanding of the current status of emotion recognition research based on EEG signals and provide ideas for subsequent related research.

SSVEP-DAN: Cross-Domain Data Alignment for SSVEP-Based Brain-Computer Interfaces

Steady-state visual-evoked potential (SSVEP)-based brain-computer interfaces (BCIs) offer a non-invasive means of communication through high-speed speller systems. However, their efficiency is highly dependent on individual training data acquired during time-consuming calibration sessions. To address the challenge of data insufficiency in SSVEP-based BCIs, we introduce SSVEP-DAN, the first dedicated neural network model designed to align SSVEP data across different domains, encompassing various sessions, subjects, or devices. Our experimental results demonstrate the ability of SSVEP-DAN to transform existing source SSVEP data into supplementary calibration data. This results in a significant improvement in SSVEP decoding accuracy while reducing the calibration time. We envision SSVEP-DAN playing a crucial role in future applications of high-performance SSVEP-based BCIs. The source code for this work is available at: https://github.com/CECNL/SSVEP-DAN.

FetchEEG: a hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification

Objective. Electroencephalogram (EEG) analysis has always been an important tool in neural engineering, and the recognition and classification of human emotions are one of the important tasks in neural engineering. EEG data, obtained from electrodes placed on the scalp, represent a valuable resource of information for brain activity analysis and emotion recognition. Feature extraction methods have shown promising results, but recent trends have shifted toward end-to-end methods based on deep learning. However, these approaches often overlook channel representations, and their complex structures pose certain challenges to model fitting.Approach. To address these challenges, this paper proposes a hybrid approach named FetchEEG that combines feature extraction and temporal-channel joint attention. Leveraging the advantages of both traditional feature extraction and deep learning, the FetchEEG adopts a multi-head self-attention mechanism to extract representations between different time moments and channels simultaneously. The joint representations are then concatenated and classified using fully-connected layers for emotion recognition. The performance of the FetchEEG is verified by comparison experiments on a self-developed dataset and two public datasets.Main results. In both subject-dependent and subject-independent experiments, the FetchEEG demonstrates better performance and stronger generalization ability than the state-of-the-art methods on all datasets. Moreover, the performance of the FetchEEG is analyzed for different sliding window sizes and overlap rates in the feature extraction module. The sensitivity of emotion recognition is investigated for three- and five-frequency-band scenarios.Significance. FetchEEG is a novel hybrid method based on EEG for emotion classification, which combines EEG feature extraction with Transformer neural networks. It has achieved state-of-the-art performance on both self-developed datasets and multiple public datasets, with significantly higher training efficiency compared to end-to-end methods, demonstrating its effectiveness and feasibility.

A comparison of visual and auditory EEG interfaces for robot multi-stage task control

Shared autonomy holds promise for assistive robotics, whereby physically-impaired people can direct robots to perform various tasks for them. However, a robot that is capable of many tasks also introduces many choices for the user, such as which object or location should be the target of interaction. In the context of non-invasive brain-computer interfaces for shared autonomy-most commonly electroencephalography-based-the two most common choices are to provide either auditory or visual stimuli to the user-each with their respective pros and cons. Using the oddball paradigm, we designed comparable auditory and visual interfaces to speak/display the choices to the user, and had users complete a multi-stage robotic manipulation task involving location and object selection. Users displayed differing competencies-and preferences-for the different interfaces, highlighting the importance of considering modalities outside of vision when constructing human-robot interfaces.

Signal alignment for cross-datasets in P300 brain-computer interfaces

Objective.Transfer learning has become an important issue in the brain-computer interface (BCI) field, and studies on subject-to-subject transfer within the same dataset have been performed. However, few studies have been performed on dataset-to-dataset transfer, including paradigm-to-paradigm transfer. In this study, we propose a signal alignment (SA) for P300 event-related potential (ERP) signals that is intuitive, simple, computationally less expensive, and can be used for cross-dataset transfer learning.Approach.We proposed a linear SA that uses the P300's latency, amplitude scale, and reverse factor to transform signals. For evaluation, four datasets were introduced (two from conventional P300 Speller BCIs, one from a P300 Speller with face stimuli, and the last from a standard auditory oddball paradigm).Results.Although the standard approach without SA had an average precision (AP) score of 25.5%, the approach demonstrated a 35.8% AP score, and we observed that the number of subjects showing improvement was 36.0% on average. Particularly, we confirmed that the Speller dataset with face stimuli was more comparable with other datasets.Significance.We proposed a simple and intuitive way to align ERP signals that uses the characteristics of ERP signals. The results demonstrated the feasibility of cross-dataset transfer learning even between datasets with different paradigms.

More than the sum of its parts: investigating episodic memory as a multidimensional cognitive process

Why do we remember some events but forget others? Previous studies attempting to decode successful vs. unsuccessful brain states to investigate this question have met with limited success, potentially due, in part, to assessing episodic memory as a unidimensional process, despite evidence that multiple domains contribute to episodic encoding. Using a novel machine learning algorithm known as "transfer learning", we leveraged visual perception, sustained attention, and selective attention brain states to better predict episodic memory performance from trial-to-trial encoding electroencephalography (EEG) activity. We found that this multidimensional treatment of memory decoding improved prediction performance compared to traditional, unidimensional, methods, with each cognitive domain explaining unique variance in decoding of successful encoding-related neural activity. Importantly, this approach could be applied to cognitive domains outside of memory. Overall, this study provides critical insight into the underlying reasons why some events are remembered while others are not.

Self-supervised contrastive learning for EEG-based cross-subject motor imagery recognition

Objective. The extensive application of electroencephalography (EEG) in brain-computer interfaces (BCIs) can be attributed to its non-invasive nature and capability to offer high-resolution data. The acquisition of EEG signals is a straightforward process, but the datasets associated with these signals frequently exhibit data scarcity and require substantial resources for proper labeling. Furthermore, there is a significant limitation in the generalization performance of EEG models due to the substantial inter-individual variability observed in EEG signals.Approach. To address these issues, we propose a novel self-supervised contrastive learning framework for decoding motor imagery (MI) signals in cross-subject scenarios. Specifically, we design an encoder combining convolutional neural network and attention mechanism. In the contrastive learning training stage, the network undergoes training with the pretext task of data augmentation to minimize the distance between pairs of homologous transformations while simultaneously maximizing the distance between pairs of heterologous transformations. It enhances the amount of data utilized for training and improves the network's ability to extract deep features from original signals without relying on the true labels of the data.Main results. To evaluate our framework's efficacy, we conduct extensive experiments on three public MI datasets: BCI IV IIa, BCI IV IIb, and HGD datasets. The proposed method achieves cross-subject classification accuracies of 67.32%, 82.34%, and 81.13%on the three datasets, demonstrating superior performance compared to existing methods.Significance. Therefore, this method has great promise for improving the performance of cross-subject transfer learning in MI-based BCI systems.

Review of EEG Affective Recognition with a Neuroscience Perspective

Emotions are a series of subconscious, fleeting, and sometimes elusive manifestations of the human innate system. They play crucial roles in everyday life-influencing the way we evaluate ourselves, our surroundings, and how we interact with our world. To date, there has been an abundance of research on the domains of neuroscience and affective computing, with experimental evidence and neural network models, respectively, to elucidate the neural circuitry involved in and neural correlates for emotion recognition. Recent advances in affective computing neural network models often relate closely to evidence and perspectives gathered from neuroscience to explain the models. Specifically, there has been growing interest in the area of EEG-based emotion recognition to adopt models based on the neural underpinnings of the processing, generation, and subsequent collection of EEG data. In this respect, our review focuses on providing neuroscientific evidence and perspectives to discuss how emotions potentially come forth as the product of neural activities occurring at the level of subcortical structures within the brain's emotional circuitry and the association with current affective computing models in recognizing emotions. Furthermore, we discuss whether such biologically inspired modeling is the solution to advance the field in EEG-based emotion recognition and beyond.

Subject-independent meta-learning framework towards optimal training of EEG-based classifiers

Advances in deep learning have shown great promise towards the application of performing high-accuracy Electroencephalography (EEG) signal classification in a variety of tasks. However, many EEG-based datasets are often plagued by the issue of high inter-subject signal variability. Robust deep learning models are notoriously difficult to train under such scenarios, often leading to subpar or widely varying performance across subjects under the leave-one-subject-out paradigm. Recently, the model agnostic meta-learning framework was introduced as a way to increase the model's ability to generalize towards new tasks. While the original framework focused on task-based meta-learning, this research aims to show that the meta-learning methodology can be modified towards subject-based signal classification while maintaining the same task objectives and achieve state-of-the-art performance. Namely, we propose the novel implementation of a few/zero-shot subject-independent meta-learning framework towards multi-class inner speech and binary class motor imagery classification. Compared to current subject-adaptive methods which utilize large number of labels from the target, the proposed framework shows its effectiveness in training zero-calibration and few-shot models for subject-independent EEG classification. The proposed few/zero-shot subject-independent meta-learning mechanism performs well on both small and large datasets and achieves robust, generalized performance across subjects. The results obtained shows a significant improvement over the current state-of-the-art, with the binary class motor imagery achieving 88.70% and the accuracy of multi-class inner speech achieving an average of 31.15%. Codes will be made available to public upon publication.

Aggregating intrinsic information to enhance BCI performance through federated learning

Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed framework can boost classification performance up to 8.4% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge.

Enhancing SSVEP-BCI Performance Under Fatigue State Using Dynamic Stopping Strategy

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have emerged as a prominent technology due to their high information transfer rate, rapid calibration time, and robust signal-to-noise ratio. However, a critical challenge for practical applications is performance degradation caused by user fatigue during prolonged use. This work proposes novel methods to address this challenge by dynamically adjusting data acquisition length and updating detection models based on a fatigue-aware stopping strategy. Two 16-target SSVEP-BCIs were employed, one using low-frequency and the other using high-frequency stimulation. A self-recorded fatigue dataset from 24 subjects was utilized for extensive evaluation. A simulated online experiment demonstrated that the proposed methods outperform the conventional fixed stopping strategy in terms of classification accuracy, information transfer rate, and selection time, irrespective of stimulation frequency. These findings suggest that the proposed approach can significantly improve SSVEP-BCI performance under fatigue conditions, leading to superior performance during extended use.

A method to assess industrial paraffin contamination levels in rice and its transferability analysis based on transfer component analysis

Accurate assessment of industrial paraffin contamination levels (IPCLs) in rice is critical for food safety. However, time-consuming and labor-intensive experiments to produce labels for targeted adulterated rice have hindered the development of IPCL estimation methods. In this paper, a transfer learning method (TCA-LSSVR) has been developed. The algorithm integrates transfer component analysis (TCA) with domain adaptive capabilities to produce accurate estimates. Rice from 7 different regions and 3 industrial paraffins were used to generate 4,680 samples from 9 datasets for benchmarking. The test results showed that the established algorithm achieved good estimation performance in various modelling strategies, and only 20 % of off-site samples were needed to supplement the source dataset, the average determination coefficient R2 reached 0.7045, the average RMSE reached 0.140 %, and the average RPD reached 2.023. This work highlights the prospect of rapidly developing a new generation of adulteration detection algorithms using only previous trial data.

Personalized motor imagery prediction model based on individual difference of ERP

Objective. Motor imagery-based brain-computer interaction (MI-BCI) is a novel method of achieving human and external environment interaction that can assist individuals with motor disorders to rehabilitate. However, individual differences limit the utility of the MI-BCI. In this study, a personalized MI prediction model based on the individual difference of event-related potential (ERP) is proposed to solve the MI individual difference.Approach.A novel paradigm named action observation-based multi-delayed matching posture task evokes ERP during a delayed matching posture task phase by retrieving picture stimuli and videos, and generates MI electroencephalogram through action observation and autonomous imagery in an action observation-based motor imagery phase. Based on the correlation between the ERP and MI, a logistic regression-based personalized MI prediction model is built to predict each individual's suitable MI action. 32 subjects conducted the MI task with or without the help of the prediction model to select the MI action. Then classification accuracy of the MI task is used to evaluate the proposed model and three traditional MI methods.Main results.The personalized MI prediction model successfully predicts suitable action among 3 sets of daily actions. Under suitable MI action, the individual's ERP amplitude and event-related desynchronization (ERD) intensity are the largest, which helps to improve the accuracy by 14.25%.Significance.The personalized MI prediction model that uses the temporal ERP features to predict the classification accuracy of MI is feasible for improving the individual's MI-BCI performance, providing a new personalized solution for the individual difference and practical BCI application.

Multi-source domain adaptation based tempo-spatial convolution network for cross-subject EEG classification in RSVP task

Objective.Many subject-dependent methods were proposed for electroencephalogram (EEG) classification in rapid serial visual presentation (RSVP) task, which required a large amount of data from new subject and were time-consuming to calibrate system. Cross-subject classification can realize calibration reduction or zero calibration. However, cross-subject classification in RSVP task is still a challenge.Approach.This study proposed a multi-source domain adaptation based tempo-spatial convolution (MDA-TSC) network for cross-subject RSVP classification. The proposed network consisted of three modules. First, the common feature extraction with multi-scale tempo-spatial convolution was constructed to extract domain-invariant features across all subjects, which could improve generalization of the network. Second, the multi-branch domain-specific feature extraction and alignment was conducted to extract and align domain-specific feature distributions of source and target domains in pairs, which could consider feature distribution differences among source domains. Third, the domain-specific classifier was exploited to optimize the network through loss functions and obtain prediction for the target domain.Main results.The proposed network was evaluated on the benchmark RSVP dataset, and the cross-subject classification results showed that the proposed MDA-TSC network outperformed the reference methods. Moreover, the effectiveness of the MDA-TSC network was verified through both ablation studies and visualization.Significance.The proposed network could effectively improve cross-subject classification performance in RSVP task, and was helpful to reduce system calibration time.

Cross-Subject Motor Imagery Decoding by Transfer Learning of Tactile ERD

For Brain-Computer Interface (BCI) based on motor imagery (MI), the MI task is abstract and spontaneous, presenting challenges in measurement and control and resulting in a lower signal-to-noise ratio. The quality of the collected MI data significantly impacts the cross-subject calibration results. To address this challenge, we introduce a novel cross-subject calibration method based on passive tactile afferent stimulation, in which data induced by tactile stimulation is utilized to calibrate transfer learning models for cross-subject decoding. During the experiments, tactile stimulation was applied to either the left or right hand, with subjects only required to sense tactile stimulation. Data from these tactile tasks were used to train or fine-tune models and subsequently applied to decode pure MI data. We evaluated BCI performance using both the classical Common Spatial Pattern (CSP) combined with the Linear Discriminant Analysis (LDA) algorithm and a state-of-the-art deep transfer learning model. The results demonstrate that the proposed calibration method achieved decoding performance at an equivalent level to traditional MI calibration, with the added benefit of outperforming traditional MI calibration with fewer trials. The simplicity and effectiveness of the proposed cross-subject tactile calibration method make it valuable for practical applications of BCI, especially in clinical settings.

Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning

Pathology diagnosis based on EEG signals and decoding brain activity holds immense importance in understanding neurological disorders. With the advancement of artificial intelligence methods and machine learning techniques, the potential for accurate data-driven diagnoses and effective treatments has grown significantly. However, applying machine learning algorithms to real-world datasets presents diverse challenges at multiple levels. The scarcity of labeled data, especially in low regime scenarios with limited availability of real patient cohorts due to high costs of recruitment, underscores the vital deployment of scaling and transfer learning techniques. In this study, we explore a real-world pathology classification task to highlight the effectiveness of data and model scaling and cross-dataset knowledge transfer. As such, we observe varying performance improvements through data scaling, indicating the need for careful evaluation and labeling. Additionally, we identify the challenges of possible negative transfer and emphasize the significance of some key components to overcome distribution shifts and potential spurious correlations and achieve positive transfer. We see improvement in the performance of the target model on the target (NMT) datasets by using the knowledge from the source dataset (TUAB) when a low amount of labeled data was available. Our findings demonstrated that a small and generic model (e.g. ShallowNet) performs well on a single dataset, however, a larger model (e.g. TCN) performs better in transfer learning when leveraging a larger and more diverse dataset.

Boosting lower-limb motor imagery performance through an ensemble method for gait rehabilitation

Lower-limb exoskeletons have been used extensively in many rehabilitation applications to assist disabled people with their therapies. Brain-machine interfaces (BMIs) further provide effective and natural control schemes. However, the limited performance of brain signal decoding from lower-limb kinematics restricts the broad growth of both BMI and rehabilitation industry. To address these challenges, we propose an ensemble method for lower-limb motor imagery (MI) classification. The proposed model employs multiple techniques to boost performance, including deep and shallow parts. Traditional wavelet transformation followed by filter-bank common spatial pattern (CSP) employs neurophysiologically reasonable patterns, while multi-head self-attention (MSA) followed by temporal convolutional network (TCN) extracts deeper encoded generalized patterns. Experimental results in a customized lower-limb exoskeleton on 8 subjects in 3 consecutive sessions showed that the proposed method achieved 60.27% and 64.20% for three (MI of left leg, MI of right leg, and rest) and two classes (lower-limb MI vs. rest), respectively. Besides, the proposed model achieves improvements of up to 4% and 2% accuracy for the subject-specific and subject-independent modes compared to the current state-of-the-art (SOTA) techniques, respectively. Finally, feature analysis was conducted to show discriminative brain patterns in each MI task and sessions with different feedback modalities. The proposed models integrated in the brain-actuated lower-limb exoskeleton established a potential BMI for gait training and neuroprosthesis.

EEGProgress: A fast and lightweight progressive convolution architecture for EEG classification

Because of the intricate topological structure and connection of the human brain, extracting deep spatial features from electroencephalograph (EEG) signals is a challenging and time-consuming task. The extraction of topological spatial information plays a crucial role in EEG classification, and the architecture of the spatial convolution greatly affects the performance and complexity of convolutional neural network (CNN) based EEG classification models. In this study, a progressive convolution CNN architecture named EEGProgress is proposed, aiming to efficiently extract the topological spatial information of EEG signals from multi-scale levels (electrode, brain region, hemisphere, global) with superior speed. To achieve this, the raw EEG data is permuted using the empirical topological permutation rule, integrating the EEG data with numerous topological properties. Subsequently, the spatial features are extracted by a progressive feature extractor including prior, electrode, region, and hemisphere convolution blocks, progressively extracting the deep spatial features with reduced parameters and speed. Finally, the comparison and ablation experiments under both cross-subject and within-subject scenarios are conducted on a public dataset to verify the performance of the proposed EEGProgress and the effectiveness of the topological permutation. The results demonstrate the superior feature extraction ability of the proposed EEGProgress, with an average increase of 4.02% compared to other CNN-based EEG classification models under both cross-subject and within-subject scenarios. Furthermore, with the obtained average testing time, FLOPs, and parameters, the proposed EEGProgress outperforms other comparison models in terms of model complexity.

Self-Supervised Learning for Electroencephalography

Decades of research have shown machine learning superiority in discovering highly nonlinear patterns embedded in electroencephalography (EEG) records compared with conventional statistical techniques. However, even the most advanced machine learning techniques require relatively large, labeled EEG repositories. EEG data collection and labeling are costly. Moreover, combining available datasets to achieve a large data volume is usually infeasible due to inconsistent experimental paradigms across trials. Self-supervised learning (SSL) solves these challenges because it enables learning from EEG records across trials with variable experimental paradigms, even when the trials explore different phenomena. It aggregates multiple EEG repositories to increase accuracy, reduce bias, and mitigate overfitting in machine learning training. In addition, SSL could be employed in situations where there is limited labeled training data, and manual labeling is costly. This article: 1) provides a brief introduction to SSL; 2) describes some SSL techniques employed in recent studies, including EEG; 3) proposes current and potential SSL techniques for future investigations in EEG studies; 4) discusses the cons and pros of different SSL techniques; and 5) proposes holistic implementation tips and potential future directions for EEG SSL practices.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data

While deep learning methods are increasingly applied in research contexts for neuropsychiatric disorder diagnosis, small dataset size limits their potential for clinical translation. Data augmentation (DA) could address this limitation, but the utility of EEG DA methods remains relatively underexplored in neuropsychiatric disorder diagnosis. In this study, we train a model for major depressive disorder diagnosis. We then evaluate the utility of 6 EEG DA approaches. Importantly, to remove the bias that could be introduced by comparing performance for models trained on larger augmented training sets to models trained on smaller baseline sets, we also introduce a new baseline trained on duplicate training data to better. We lastly examine the effects of the DA approaches upon representations learned by the model with a pair of explainability analyses. We find that while most approaches boost model performance, they do not improve model performance beyond that of simply using a duplicate training set without DA. The exception to this is channel dropout augmentation, which does improve model performance. These findings suggest the importance of comparing EEG DA methods to a baseline with a duplicate training set of equal size to the augmented training set. We also found that some DA methods increased model robustness to frequency (Fourier transform surrogates) and channel (channel dropout) perturbation. While our findings on EEG DA efficacy are restricted to our dataset and model, we hope that future studies on deep learning for small EEG datasets and on new EEG DA methods will find our findings helpful.

Effectiveness of the Combined Use of a Brain-Machine Interface System and Virtual Reality as a Therapeutic Approach in Patients with Spinal Cord Injury: A Systematic Review

Spinal cord injury has a major impact on both the individual and society. This damage can cause permanent loss of sensorimotor functions, leading to structural and functional changes in somatotopic regions of the spinal cord. The combined use of a brain-machine interface and virtual reality offers a therapeutic alternative to be considered in the treatment of this pathology. This systematic review aimed to evaluate the effectiveness of the combined use of virtual reality and the brain-machine interface in the treatment of spinal cord injuries. A search was performed in PubMed, Web of Science, PEDro, Cochrane Central Register of Controlled Trials, CINAHL, Scopus, and Medline, including articles published from the beginning of each database until January 2023. Articles were selected based on strict inclusion and exclusion criteria. The Cochrane Collaboration's tool was used to assess the risk of bias and the PEDro scale and SCIRE systems were used to evaluate the methodological quality of the studies. Eleven articles were selected from a total of eighty-two. Statistically significant changes were found in the upper limb, involving improvements in shoulder and upper arm mobility, and weaker muscles were strengthened. In conclusion, most of the articles analyzed used the electroencephalogram as a measurement instrument for the assessment of various parameters, and most studies have shown improvements. Nonetheless, further research is needed with a larger sample size and long-term follow-up to establish conclusive results regarding the effect size of these interventions.

EEG decoding for datasets with heterogenous electrode configurations using transfer learning graph neural networks

Objective. Brain-machine interfacing (BMI) has greatly benefited from adopting machine learning methods for feature learning that require extensive data for training, which are often unavailable from a single dataset. Yet, it is difficult to combine data across labs or even data within the same lab collected over the years due to the variation in recording equipment and electrode layouts resulting in shifts in data distribution, changes in data dimensionality, and altered identity of data dimensions. Our objective is to overcome this limitation and learn from many different and diverse datasets across labs with different experimental protocols.Approach. To tackle the domain adaptation problem, we developed a novel machine learning framework combining graph neural networks (GNNs) and transfer learning methodologies for non-invasive motor imagery (MI) EEG decoding, as an example of BMI. Empirically, we focus on the challenges of learning from EEG data with different electrode layouts and varying numbers of electrodes. We utilize three MI EEG databases collected using very different numbers of EEG sensors (from 22 channels to 64) and layouts (from custom layouts to 10-20).Main results. Our model achieved the highest accuracy with lower standard deviations on the testing datasets. This indicates that the GNN-based transfer learning framework can effectively aggregate knowledge from multiple datasets with different electrode layouts, leading to improved generalization in subject-independent MI EEG classification.Significance. The findings of this study have important implications for brain-computer-interface research, as they highlight a promising method for overcoming the limitations posed by non-unified experimental setups. By enabling the integration of diverse datasets with varying electrode layouts, our proposed approach can help advance the development and application of BMI technologies.

Spatial-Temporal EEG Fusion Based on Neural Network for Major Depressive Disorder Detection

In view of the major depressive disorder characteristics such as high mortality as well as high recurrence, it is important to explore an objective and effective detection method for major depressive disorder. Considering the advantages complementary of different machine learning algorithms in information mining process, as well as the fusion complementary of different information, in this study, the spatial-temporal electroencephalography fusion framework using neural network is proposed for major depressive disorder detection. Since electroencephalography is a typical time series signal, we introduce recurrent neural network embedded in long short-term memory unit for extract temporal domain features to solve the problem of long-distance information dependence. To reduce the volume conductor effect, the temporal electroencephalography data are mapping into a spatial brain functional network using phase lag index, then the spatial domain features were extracted from brain functional network using 2D convolutional neural networks. Considering the complementarity between different types of features, the spatial-temporal electroencephalography features are fused to achieve data diversity. The experimental results show that spatial-temporal features fusion can improve the detection accuracy of major depressive disorder with a highest of 96.33%. In addition, our research also found that theta, alpha, and full frequency band in brain regions of left frontal, left central, right temporal are closely related to MDD detection, especially theta frequency band in left frontal region. Only using single-dimension EEG data as decision basis, it is difficult to fully explore the valuable information hidden in the data, which affects the overall detection performance of MDD. Meanwhile, different algorithms have their own advantages for different application scenarios. Ideally, different algorithms should use their respective advantages to jointly address complex problems in engineering fields. To this end, we propose a computer-aided MDD detection framework based on spatial-temporal EEG fusion using neural network, as shown in Fig. 1. The simplified process is as follows: (1) Raw EEG data acquisition and preprocessing. (2) The time series EEG data of each channel are input as recurrent neural network (RNN), and RNN is used to process and extract temporal domain (TD) features. (3) The BFN among different EEG channels is constructed, and CNN is used to process and extract the spatial domain (SD) features of the BFN. (4) Based on the theory of information complementarity, the spatial-temporal information is fused to realize efficient MDD detection. Fig. 1 MDD detection framework based on spatial-temporal EEG fusion.

Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis

Transfer learning offers a route for developing robust deep learning models on small raw electroencephalography (EEG) datasets. Nevertheless, the utility of applying representations learned from large datasets with a lower sampling rate to smaller datasets with higher sampling rates remains relatively unexplored. In this study, we transfer representations learned by a convolutional neural network on a large, publicly available sleep dataset with a 100 Hertz sampling rate to a major depressive disorder (MDD) diagnosis task at a sampling rate of 200 Hertz. Importantly, we find that the early convolutional layers contain representations that are generalizable across tasks. Moreover, our approach significantly increases mean model accuracy from 82.33% to 86.99%, increases the model's use of lower frequencies, (θ-band), and increases its robustness to channel loss. We expect this analysis to provide useful guidance and enable more widespread use of transfer learning in EEG deep learning studies.

Biometric Recognition Based on Recurrence Plot and InceptionV3 Model Using Eye Movements

The ability to use eye movement signals as a feature in biometric recognition is a novel characteristic of biometric recognition technology. However, present technologies have not fully exploited the correlation features between eye movement signals. To address this, we propose an eye movement biometric recognition model that is based on recurrence plot encoding and the InceptionV3 model. We first encode the original eye movement signal using the recurrence plot to obtain a 2-D image that is then used as input for the InceptionV3 model to perform biometric recognition. Our experimental results using the GazeBaseV2.0 eye movement dataset demonstrate that our proposed model achieved a high biometric recognition accuracy of 96.58% ± 0.66% using the recurrence plot transformation of the horizontal gaze position signals and the InceptionV3 model, surpassing the accuracy achieved by other models. The use of horizontal gaze position eye movement signals for biometric recognition outperforms the use of vertical gaze position signals when using our proposed methods. Furthermore, the biometric recognition that is achieved through recurrent plot encoding is superior to that achieved using Markov transition fields and Gramian angular field transformations.

Transfer Learning for P300 Brain-Computer Interfaces by Joint Alignment of Feature Vectors

This article presents a new transfer learning method named group learning, that jointly aligns multiple domains (many-to-many) and an extension named fast alignment that aligns any further domain to previously aligned group of domains (many-to-one). The proposed group alignment algorithm (GALIA) is evaluated on brain-computer interface (BCI) data and optimal hyper-parameter values of the algorithm are studied for classification performance and computational cost. Six publicly available P300 databases comprising 333 sessions from 177 subjects are used. As compared to the conventional subject-specific train/test pipeline, both group learning and fast alignment significantly improve the classification accuracy except for the database with clinical subjects (average improvement: 2.12±1.88%). GALIA utilizes cyclic approximate joint diagonalization (AJD) to find a set of linear transformations, one for each domain, jointly aligning the feature vectors of all domains. Group learning achieves a many-to-many transfer learning without compromising the classification performance on non-clinical BCI data. Fast alignment further extends the group learning for any unseen domains, allowing a many-to-one transfer learning with the same properties. The former method creates a single machine learning model using data from previous subjects and/or sessions, whereas the latter exploits the trained model for an unseen domain requiring no further training of the classifier.

Epileptic EEG Signal Detection Using Variational Modal Decomposition and Improved Grey Wolf Algorithm

Epilepsy does great harm to the human body, and even threatens human life when it is serious. Therefore, research focused on the diagnosis and treatment of epilepsy holds paramount clinical significance. In this paper, we utilized variational modal decomposition (VMD) and an enhanced grey wolf algorithm to detect epileptic electroencephalogram (EEG) signals. Data were extracted from each patient's preseizure period and seizure period of 200 s each, with every 2 s as a segment, meaning 100 data points could be obtained for each patient's health period as well as 100 data points for each patient's epilepsy period. Variational modal decomposition (VMD) was used to obtain the corresponding intrinsic modal function (VMF) of the data. Then, the differential entropy (DE) and high frequency detection (HFD) of each VMF were extracted as features. The improved grey wolf algorithm is adopted for a selected channel to improve the maximum value of the channel. Finally, the EEG signal samples were classified using a support vector machine (SVM) classifier to achieve the accurate detection of epilepsy EEG signals. Experimental results show that the accuracy, sensitivity and specificity of the proposed method can reach 98.3%, 98.9% and 98.5%, respectively. The proposed algorithm in this paper can be used as an index to detect epileptic seizures and has certain guiding significance for the early diagnosis and effective treatment of epileptic patients.

Enhancing Cross-Subject Motor Imagery Classification in EEG-Based Brain-Computer Interfaces by Using Multi-Branch CNN

A brain-computer interface (BCI) is a computer-based system that allows for communication between the brain and the outer world, enabling users to interact with computers using neural activity. This brain signal is obtained from electroencephalogram (EEG) signals. A significant obstacle to the development of BCIs based on EEG is the classification of subject-independent motor imagery data since EEG data are very individualized. Deep learning techniques such as the convolutional neural network (CNN) have illustrated their influence on feature extraction to increase classification accuracy. In this paper, we present a multi-branch (five branches) 2D convolutional neural network that employs several hyperparameters for every branch. The proposed model achieved promising results for cross-subject classification and outperformed EEGNet, ShallowConvNet, DeepConvNet, MMCNN, and EEGNet_Fusion on three public datasets. Our proposed model, EEGNet Fusion V2, achieves 89.6% and 87.8% accuracy for the actual and imagined motor activity of the eegmmidb dataset and scores of 74.3% and 84.1% for the BCI IV-2a and IV-2b datasets, respectively. However, the proposed model has a bit higher computational cost, i.e., it takes around 3.5 times more computational time per sample than EEGNet_Fusion.

Cross-Subject Transfer Method Based on Domain Generalization for Facilitating Calibration of SSVEP-Based BCIs

In steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs), various spatial filtering methods based on individual calibration data have been proposed to alleviate the interference of spontaneous activities in SSVEP signals for enhancing the SSVEP detection performance. However, the time-consuming calibration session would increase the visual fatigue of subjects and reduce the usability of the BCI system. The key idea of this study is to propose a cross-subject transfer method based on domain generalization, which transfers the domain-invariant spatial filters and templates learned from source subjects to the target subject with no access to the EEG data from the target subject. The transferred spatial filters and templates are obtained by maximizing the intra- and inter-subject correlations using the SSVEP data corresponding to the target and its neighboring stimuli. For SSVEP detection of the target subject, four types of correlation coefficients are calculated to construct the feature vector. Experimental results estimated with three SSVEP datasets show that the proposed cross-subject transfer method improves the SSVEP detection performance compared to state-of-art methods. The satisfactory results demonstrate that the proposed method provides an effective transfer learning strategy requiring no tedious data collection process for new users, holding the potential of promoting practical applications of SSVEP-based BCI.

An evaluation of transfer learning models in EEG-based authentication

Electroencephalogram(EEG)-based authentication has received increasing attention from researchers as they believe it could serve as an alternative to more conventional personal authentication methods. Unfortunately, EEG signals are non-stationary and could be easily contaminated by noise and artifacts. Therefore, further processing of data analysis is needed to retrieve useful information. Various machine learning approaches have been proposed and implemented in the EEG-based domain, with deep learning being the most current trend. However, retaining the performance of a deep learning model requires substantial computational effort and a vast amount of data, especially when the models go deeper to generate consistent results. Deep learning models trained with small data sets from scratch may experience an overfitting issue. Transfer learning becomes an alternative solution. It is a technique to recognize and apply the knowledge and skills learned from the previous tasks to a new domain with limited training data. This study attempts to explore the applicability of transferring various pre-trained models' knowledge to the EEG-based authentication domain. A self-collected database that consists of 30 subjects was utilized in the analysis. The database enrolment is divided into two sessions, with each session producing two sets of EEG recording data. The frequency spectrums of the preprocessed EEG signals are extracted and fed into the pre-trained models as the input data. Three experimental tests are carried out and the best performance is reported with accuracy in the range of 99.1-99.9%. The acquired results demonstrate the efficiency of transfer learning in authenticating an individual in this domain.

Electroencephalography Signal Processing: A Comprehensive Review and Analysis of Methods and Techniques

The electroencephalography (EEG) signal is a noninvasive and complex signal that has numerous applications in biomedical fields, including sleep and the brain-computer interface. Given its complexity, researchers have proposed several advanced preprocessing and feature extraction methods to analyze EEG signals. In this study, we analyze a comprehensive review of numerous articles related to EEG signal processing. We searched the major scientific and engineering databases and summarized the results of our findings. Our survey encompassed the entire process of EEG signal processing, from acquisition and pretreatment (denoising) to feature extraction, classification, and application. We present a detailed discussion and comparison of various methods and techniques used for EEG signal processing. Additionally, we identify the current limitations of these techniques and analyze their future development trends. We conclude by offering some suggestions for future research in the field of EEG signal processing.

Hedge transfer learning routing for dynamic searching and reconnoitering applications in 3D multimedia FANETs

With the fast development of unmanned aerial vehicles (UAVs) and the user increasing demand of UAV video transmission, UAV video service is widely used in dynamic searching and reconnoitering applications. Video transmissions not only consider the complexity and instability of 3D UAV network topology but also ensure reliable quality of service (QoS) in flying ad hoc networks (FANETs). We propose hedge transfer learning routing (HTLR) for dynamic searching and reconnoitering applications to address this problem. Compared with the previous transfer learning framework, HTRL has the following innovations. First, hedge principle is introduced into transfer learning. Online model is continuously trained on the basis of offline model, and their weight factors are adjusted in real-time by transfer learning, so as to adapt to the complex 3D FANETs. Secondly, distributed multi-hop link state scheme is used to estimate multi-hop link states in the whole network, thus enhancing the stability of transmission links. Among them, we propose the multiplication rule of multi-hop link states, which is a new idea to evaluate link states. Finally, we use packet delivery rate (PDR) and energy efficiency rate (EER) as two main evaluation metrics. In the same NS3 experimental scenario, the PDR of HTLR is at least 5.11% higher and the EER is at least 1.17 lower than compared protocols. Besides, we use Wilcoxon test to compare HTLR with the simplified version of HTLR without hedge transfer learning (N-HTLR). The results show that HTRL is superior to N-HTRL, effectively ensuring QoS.

Decoding Multi-Class Motor Imagery and Motor Execution Tasks Using Riemannian Geometry Algorithms on Large EEG Datasets

The use of Riemannian geometry decoding algorithms in classifying electroencephalography-based motor-imagery brain-computer interfaces (BCIs) trials is relatively new and promises to outperform the current state-of-the-art methods by overcoming the noise and nonstationarity of electroencephalography signals. However, the related literature shows high classification accuracy on only relatively small BCI datasets. The aim of this paper is to provide a study of the performance of a novel implementation of the Riemannian geometry decoding algorithm using large BCI datasets. In this study, we apply several Riemannian geometry decoding algorithms on a large offline dataset using four adaptation strategies: baseline, rebias, supervised, and unsupervised. Each of these adaptation strategies is applied in motor execution and motor imagery for both scenarios 64 electrodes and 29 electrodes. The dataset is composed of four-class bilateral and unilateral motor imagery and motor execution of 109 subjects. We run several classification experiments and the results show that the best classification accuracy is obtained for the scenario where the baseline minimum distance to Riemannian mean has been used. The mean accuracy values up to 81.5% for motor execution, and up to 76.4% for motor imagery. The accurate classification of EEG trials helps to realize successful BCI applications that allow effective control of devices.

Diagnosis of autism spectrum disorder based on functional brain networks and machine learning

Autism is a multifaceted neurodevelopmental condition whose accurate diagnosis may be challenging because the associated symptoms and severity vary considerably. The wrong diagnosis can affect families and the educational system, raising the risk of depression, eating disorders, and self-harm. Recently, many works have proposed new methods for the diagnosis of autism based on machine learning and brain data. However, these works focus on only one pairwise statistical metric, ignoring the brain network organization. In this paper, we propose a method for the automatic diagnosis of autism based on functional brain imaging data recorded from 500 subjects, where 242 present autism spectrum disorder considering the regions of interest throughout Bootstrap Analysis of Stable Cluster map. Our method can distinguish the control group from autism spectrum disorder patients with high accuracy. Indeed the best performance provides an AUC near 1.0, which is higher than that found in the literature. We verify that the left ventral posterior cingulate cortex region is less connected to an area in the cerebellum of patients with this neurodevelopment disorder, which agrees with previous studies. The functional brain networks of autism spectrum disorder patients show more segregation, less distribution of information across the network, and less connectivity compared to the control cases. Our workflow provides medical interpretability and can be used on other fMRI and EEG data, including small data sets.

Generative adversarial networks in EEG analysis: an overview

Electroencephalogram (EEG) signals have been utilized in a variety of medical as well as engineering applications. However, one of the challenges associated with recording EEG data is the difficulty of recording large amounts of data. Consequently, data augmentation is a potential solution to overcome this challenge in which the objective is to increase the amount of data. Inspired by the success of Generative Adversarial Networks (GANs) in image processing applications, generating artificial EEG data from the limited recorded data using GANs has seen recent success. This article provides an overview of various techniques and approaches of GANs for augmenting EEG signals. We focus on the utility of GANs in different applications including Brain-Computer Interface (BCI) paradigms such as motor imagery and P300-based systems, in addition to emotion recognition, epileptic seizures detection and prediction, and various other applications. We address in this article how GANs have been used in each study, the impact of using GANs on the model performance, the limitations of each algorithm, and future possibilities for developing new algorithms. We emphasize the utility of GANs in augmenting the limited EEG data typically available in the studied applications.

Survey of Movement Reproduction in Immersive Virtual Rehabilitation

Virtual reality (VR) has emerged as a powerful tool for rehabilitation. Many effective VR applications have been developed to support motor rehabilitation of people affected by motor issues. Movement reproduction, which transfers users' movements from the physical world to the virtual environment, is commonly used in VR rehabilitation applications. Three major components are required for movement reproduction in VR: (1) movement input, (2) movement representation, and (3) movement modulation. Until now, movement reproduction in virtual rehabilitation has not yet been systematically studied. This article aims to provide a state-of-the-art review on this subject by focusing on existing literature on immersive motor rehabilitation using VR. In this review, we provided in-depth discussions on the rehabilitation goals and outcomes, technology issues behind virtual rehabilitation, and user experience regarding movement reproduction. Similarly, we present good practices and highlight challenges and opportunities that can form constructive suggestions for the design and development of fit-for-purpose VR rehabilitation applications and can help frame future research directions for this emerging area that combines VR and health.

Cross-subject aesthetic preference recognition of Chinese dance posture using EEG

Due to the differences in knowledge, experience, background, and social influence, people have subjective characteristics in the process of dance aesthetic cognition. To explore the neural mechanism of the human brain in the process of dance aesthetic preference, and to find a more objective determining criterion for dance aesthetic preference, this paper constructs a cross-subject aesthetic preference recognition model of Chinese dance posture. Specifically, Dai nationality dance (a classic Chinese folk dance) was used to design dance posture materials, and an experimental paradigm for aesthetic preference of Chinese dance posture was built. Then, 91 subjects were recruited for the experiment, and their EEG signals were collected. Finally, the transfer learning method and convolutional neural networks were used to identify the aesthetic preference of the EEG signals. Experimental results have shown the feasibility of the proposed model, and the objective aesthetic measurement in dance appreciation has been implemented. Based on the classification model, the accuracy of aesthetic preference recognition is 79.74%. Moreover, the recognition accuracies of different brain regions, different hemispheres, and different model parameters were also verified by the ablation study. Additionally, the experimental results reflected the following two facts: (1) in the visual aesthetic processing of Chinese dance posture, the occipital and frontal lobes are more activated and participate in dance aesthetic preference; (2) the right brain is more involved in the visual aesthetic processing of Chinese dance posture, which is consistent with the common knowledge that the right brain is responsible for processing artistic activities.

An integrated perspective for the diagnosis and therapy of neurodevelopmental disorders - From an engineering point of view

Neurodevelopmental disorders (NDDs) are complex conditions with largely unknown pathophysiology. While many NDD symptoms are familiar, the cause of these disorders remains unclear and may involve a combination of genetic, biological, psychosocial, and environmental risk factors. Current diagnosis relies heavily on behaviorally defined criteria, which may be biased by the clinical team's professional and cultural expectations, thus a push for new biological-based biomarkers for NDDs diagnosis is underway. Emerging new research technologies offer an unprecedented view into the electrical, chemical, and physiological activity in the brain and with further development in humans may provide clinically relevant diagnoses. These could also be extended to new treatment options, which can start to address the underlying physiological issues. When combined with current speech, language, occupational therapy, and pharmacological treatment these could greatly improve patient outcomes. The current review will discuss the latest technologies that are being used or may be used for NDDs diagnosis and treatment. The aim is to provide an inspiring and forward-looking view for future research in the field.

Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models

Electroencephalography (EEG) is often used to evaluate several types of neurological brain disorders because of its noninvasive and high temporal resolution. In contrast to electrocardiography (ECG), EEG can be uncomfortable and inconvenient for patients. Moreover, deep-learning techniques require a large dataset and a long time for training from scratch. Therefore, in this study, EEG-EEG or EEG-ECG transfer learning strategies were applied to explore their effectiveness for the training of simple cross-domain convolutional neural networks (CNNs) used in seizure prediction and sleep staging systems, respectively. The seizure model detected interictal and preictal periods, whereas the sleep staging model classified signals into five stages. The patient-specific seizure prediction model with six frozen layers achieved 100% accuracy for seven out of nine patients and required only 40 s of training time for personalization. Moreover, the cross-signal transfer learning EEG-ECG model for sleep staging achieved an accuracy approximately 2.5% higher than that of the ECG model; additionally, the training time was reduced by >50%. In summary, transfer learning from an EEG model to produce personalized models for a more convenient signal can both reduce the training time and increase the accuracy; moreover, challenges such as data insufficiency, variability, and inefficiency can be effectively overcome.