A subject-independent brain-computer interface based on smoothed, second-order baselining

SPD-CNN: A plain CNN-based model using the symmetric positive definite matrices for cross-subject EEG classification with meta-transfer-learning

The electroencephalography (EEG) signals are easily contaminated by various artifacts and noise, which induces a domain shift in each subject and significant pattern variability among different subjects. Therefore, it hinders the improvement of EEG classification accuracy in the cross-subject learning scenario. Convolutional neural networks (CNNs) have been extensively applied to EEG-based Brain-Computer Interfaces (BCIs) by virtue of the capability of performing automatic feature extraction and classification. However, they have been mainly applied to the within-subject classification which would consume lots of time for training and calibration. Thus, it limits the further applications of CNNs in BCIs. In order to build a robust classification algorithm for a calibration-less BCI system, we propose an end-to-end model that transforms the EEG signals into symmetric positive definite (SPD) matrices and captures the features of SPD matrices by using a CNN. To avoid the time-consuming calibration and ensure the application of the proposed model, we use the meta-transfer-learning (MTL) method to learn the essential features from different subjects. We validate our model by making extensive experiments on three public motor-imagery datasets. The experimental results demonstrate the effectiveness of our proposed method in the cross-subject learning scenario.

Enhancing transfer performance across datasets for brain-computer interfaces using a combination of alignment strategies and adaptive batch normalization

Objective. Recently, transfer learning (TL) and deep learning (DL) have been introduced to solve intra- and inter-subject variability problems in brain-computer interfaces (BCIs). However, current TL and DL algorithms are usually validated within a single dataset, assuming that data of the test subjects are acquired under the same condition as that of training (source) subjects. This assumption is generally violated in practice because of different acquisition systems and experimental settings across studies and datasets. Thus, the generalization ability of these algorithms needs further validations in a cross-dataset scenario, which is closer to the actual situation. This study compared the transfer performance of pre-trained deep-learning models with different preprocessing strategies in a cross-dataset scenario.Approach. This study used four publicly available motor imagery datasets, each was successively selected as a source dataset, and the others were used as target datasets. EEGNet and ShallowConvNet with four preprocessing strategies, namely channel normalization, trial normalization, Euclidean alignment, and Riemannian alignment, were trained with the source dataset. The transfer performance of pre-trained models was validated on the target datasets. This study also used adaptive batch normalization (AdaBN) for reducing interval covariate shift across datasets. This study compared the transfer performance of using the four preprocessing strategies and that of a baseline approach based on manifold embedded knowledge transfer (MEKT). This study also explored the possibility and performance of fusing MEKT and EEGNet.Main results. The results show that DL models with alignment strategies had significantly better transfer performance than the other two preprocessing strategies. As an unsupervised domain adaptation method, AdaBN could also significantly improve the transfer performance of DL models. The transfer performance of DL models that combined AdaBN and alignment strategies significantly outperformed MEKT. Moreover, the generalizability of EEGNet models that combined AdaBN and alignment strategies could be further improved via the domain adaptation step in MEKT, achieving the best generalization ability among multiple datasets (BNCI2014001: 0.788, PhysionetMI: 0.679, Weibo2014: 0.753, Cho2017: 0.650).Significance. The combination of alignment strategies and AdaBN could easily improve the generalizability of DL models without fine-tuning. This study may provide new insights into the design of transfer neural networks for BCIs by separating source and target batch normalization layers in the domain adaptation process.

Review of brain encoding and decoding mechanisms for EEG-based brain-computer interface

A brain-computer interface (BCI) can connect humans and machines directly and has achieved successful applications in the past few decades. Many new BCI paradigms and algorithms have been developed in recent years. Therefore, it is necessary to review new progress in BCIs. This paper summarizes progress for EEG-based BCIs from the perspective of encoding paradigms and decoding algorithms, which are two key elements of BCI systems. Encoding paradigms are grouped by their underlying neural meachanisms, namely sensory- and motor-related, vision-related, cognition-related and hybrid paradigms. Decoding algorithms are reviewed in four categories, namely decomposition algorithms, Riemannian geometry, deep learning and transfer learning. This review will provide a comprehensive overview of both modern primary paradigms and algorithms, making it helpful for those who are developing BCI systems.

Low-Dimensional Subject Representation-Based Transfer Learning in EEG Decoding

Recently, the advances in passive brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have shed light on real-world neuromonitoring technologies. However, human variability in the EEG activities hinders the development of practical applications of EEG-based BCI. To tackle this problem, many transfer-learning techniques perform supervised calibration. This kind of calibration approach requires task-relevant data, which is impractical in real-life scenarios such as drowsiness during driving. This study presents a transfer-learning framework for EEG decoding based on the low-dimensional representations of subjects learned from the pre-trial EEG. Tensor decomposition was applied to the pre-trial EEG of subjects to extract the underlying characteristics in subject, spatial, and spectral domains. Then, the proposed framework assessed the characteristics to obtain the low-dimensional subject representations such that the subjects with similar brain dynamics can be identified. This method can leverage the existing data from other users, and a small number of data from a rapid, non-task, unsupervised calibration from a new user to build an accurate BCI. Our results demonstrated that, in terms of prediction accuracy, the proposed low-dimensional subject representation-based transfer learning (LDSR-TL) framework outperformed the random selection, and the Riemannian manifold approach in cognitive-state tracking, while requiring fewer training data. The results can greatly improve the practicability, and usability of EEG-based BCI in the real world.

MI3DNet: A Compact CNN for Motor Imagery EEG Classification with Visualizable Dense Layer Parameters

Electroencephalography (EEG) based Brain Computer Interface (BCI) attracts more and more attention. Motor Imagery (MI) is a popular one among all the EEG paradigms. Building a subject-independent MI EEG classification procedure is a main challenge in practical applications. Recently, Convolutional Neural Network (CNN) has been introduced and achieved state-of-the-art performance in related areas. To extract subject-independent features in MI EEG classification, we propose the MI3DNet, using a remapped signal cubic as the input. Experiments show that MI3DNet has a higher performance with fewer parameters and layers. We also give a method to plot the parameters of the dense layer, and explain its effect.

Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks

For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 min to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-free, or subject-independent, BCI. In this article, we construct a large motor imagery (MI)-based electroencephalography (EEG) database and propose a subject-independent framework based on deep convolutional neural networks (CNNs). The database is composed of 54 subjects performing the left- and right-hand MI on two different days, resulting in 21 600 trials for the MI task. In our framework, we formulated the discriminative feature representation as a combination of the spectral-spatial input embedding the diversity of the EEG signals, as well as a feature representation learned from the CNN through a fusion technique that integrates a variety of discriminative brain signal patterns. To generate spectral-spatial inputs, we first consider the discriminative frequency bands in an information-theoretic observation model that measures the power of the features in two classes. From discriminative frequency bands, spectral-spatial inputs that include the unique characteristics of brain signal patterns are generated and then transformed into a covariance matrix as the input to the CNN. In the process of feature representations, spectral-spatial inputs are individually trained through the CNN and then combined by a concatenation fusion technique. In this article, we demonstrate that the classification accuracy of our subject-independent (or calibration-free) model outperforms that of subject-dependent models using various methods [common spatial pattern (CSP), common spatiospectral pattern (CSSP), filter bank CSP (FBCSP), and Bayesian spatio-spectral filter optimization (BSSFO)].

Federated Transfer Learning for EEG Signal Classification

The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets. Privacy concerns associated with EEG signals limit the possibility of constructing a large EEG-BCI dataset by the conglomeration of multiple small ones for jointly training machine learning models. Hence, in this paper, we propose a novel privacy-preserving DL architecture named federated transfer learning (FTL) for EEG classification that is based on the federated learning framework. Working with the single-trial covariance matrix, the proposed architecture extracts common discriminative information from multi-subject EEG data with the help of domain adaptation techniques. We evaluate the performance of the proposed architecture on the PhysioNet dataset for 2-class motor imagery classification. While avoiding the actual data sharing, our FTL approach achieves 2% higher classification accuracy in a subject-adaptive analysis. Also, in the absence of multi-subject data, our architecture provides 6% better accuracy compared to other state-of-the-art DL architectures.

Cross-Dataset Variability Problem in EEG Decoding With Deep Learning

Cross-subject variability problems hinder practical usages of Brain-Computer Interfaces. Recently, deep learning has been introduced into the BCI community due to its better generalization and feature representation abilities. However, most studies currently only have validated deep learning models for single datasets, and the generalization ability for other datasets still needs to be further verified. In this paper, we validated deep learning models for eight MI datasets and demonstrated that the cross-dataset variability problem weakened the generalization ability of models. To alleviate the impact of cross-dataset variability, we proposed an online pre-alignment strategy for aligning the EEG distributions of different subjects before training and inference processes. The results of this study show that deep learning models with online pre-alignment strategies could significantly improve the generalization ability across datasets without any additional calibration data.

Optimal Multitrial Prediction Combination and Subject-Specific Adaptation for Minimal Training Brain Switch Designs

Brain-Computer Interface (BCI) systems are traditionally designed by taking into account user-specific data to enable practical use. More recently, subject independent (SI) classification algorithms have been developed which bypass the subject specific adaptation and enable rapid use of the system. A brain switch is a particular BCI system where the system is required to distinguish from two separate mental tasks corresponding to the on-off commands of a switch. Such applications require a low false positive rate (FPR) while having an acceptable response time (RT) until the switch is activated. In this work, we develop a methodology that produces optimal brain switch behavior through subject specific (SS) adaptation of: a) a multitrial prediction combination model and b) an SI classification model. We propose a statistical model of combining classifier predictions that enables optimal FPR calibration through a short calibration session. We trained an SI classifier on a training synchronous dataset and tested our method on separate holdout synchronous and asynchronous brain switch experiments. Although our SI model obtained similar performance between training and holdout datasets, 86% and 85% for the synchronous and 69% and 66% for the asynchronous the between subject FPR and TPR variability was high (up to 62%). The short calibration session was then employed to alleviate that problem and provide decision thresholds that achieve when possible a target FPR=1% with good accuracy for both datasets.

Subject-to-subject transfer for CSP based BCIs: feature space transformation and decision-level fusion

Modern Brain Computer Interfaces (BCIs) usually require a calibration session to train a machine learning system before each usage. In general, such trained systems are highly specialized to the subject's characteristic activation patterns and cannot be used for other sessions or subjects. This paper presents a feature space transformation that transforms features generated using subject-specific spatial filters into a subject-independent feature space. The transformation can be estimated from little adaptation data of the subject. Furthermore, we combine three different Common Spatial Pattern based feature extraction approaches using decision-level fusion, which enables BCI use when little calibration data is available, but also outperformed the subject-dependent reference approaches for larger amounts of training data.

Detection of attempted movement from the EEG during neuromuscular block: proof of principle study in awake volunteers

Brain-Computer Interfaces (BCIs) have the potential to detect intraoperative awareness during general anaesthesia. Traditionally, BCI research is aimed at establishing or improving communication and control for patients with permanent paralysis. Patients experiencing intraoperative awareness also lack the means to communicate after administration of a neuromuscular blocker, but may attempt to move. This study evaluates the principle of detecting attempted movements from the electroencephalogram (EEG) during local temporary neuromuscular blockade. EEG was obtained from four healthy volunteers making 3-second hand movements, both before and after local administration of rocuronium in one isolated forearm. Using offline classification analysis we investigated whether the attempted movements the participants made during paralysis could be distinguished from the periods when they did not move or attempt to move. Attempted movement trials were correctly identified in 81 (68-94)% (mean (95% CI)) and 84 (74-93)% of the cases using 30 and 9 EEG channels, respectively. Similar accuracies were obtained when training the classifier on the participants' actual movements. These results provide proof of the principle that a BCI can detect movement attempts during neuromuscular blockade. Based on this, in the future a BCI may serve as a communication channel between a patient under general anaesthesia and the anaesthesiologist.

Quantitative analysis of task selection for brain-computer interfaces

OBJECTIVE

To assess quantitatively the impact of task selection in the performance of brain-computer interfaces (BCI).

APPROACH

We consider the task-pairs derived from multi-class BCI imagery movement tasks in three different datasets. We analyze for the first time the benefits of task selection on a large-scale basis (109 users) and evaluate the possibility of transferring task-pair information across days for a given subject.

MAIN RESULTS

Selecting the subject-dependent optimal task-pair among three different imagery movement tasks results in approximately 20% potential increase in the number of users that can be expected to control a binary BCI. The improvement is observed with respect to the best task-pair fixed across subjects. The best task-pair selected for each subject individually during a first day of recordings is generally a good task-pair in subsequent days. In general, task learning from the user side has a positive influence in the generalization of the optimal task-pair, but special attention should be given to inexperienced subjects.

SIGNIFICANCE

These results add significant evidence to existing literature that advocates task selection as a necessary step towards usable BCIs. This contribution motivates further research focused on deriving adaptive methods for task selection on larger sets of mental tasks in practical online scenarios.

Adaptive Classification on Brain-Computer Interfaces Using Reinforcement Signals

We introduce a probabilistic model that combines a classifier with an extra reinforcement signal (RS) encoding the probability of an erroneous feedback being delivered by the classifier. This representation computes the class probabilities given the task related features and the reinforcement signal. Using expectation maximization (EM) to estimate the parameter values under such a model shows that some existing adaptive classifiers are particular cases of such an EM algorithm. Further, we present a new algorithm for adaptive classification, which we call constrained means adaptive classifier, and show using EEG data and simulated RS that this classifier is able to significantly outperform state-of-the-art adaptive classifiers.