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

The mind-machine connection: adaptive information processing and new technologies promoting mental health in older adults

The human brain demonstrates an exceptional adaptability, which encompasses the ability to regulate emotions, exhibit cognitive flexibility, and generate behavioral responses, all supported by neuroplasticity. Brain-computer interfaces (BCIs) employ adaptive algorithms and machine learning techniques to adapt to variations in the user's brain activity, allowing for customized interactions with external devices. Older adults may experience cognitive decline, which could affect the ability to learn and adapt to new technologies such as BCIs, but both (human brain and BCI) demonstrate adaptability in their responses. The human brain is skilled at quickly switching between tasks and regulating emotions, while BCIs can modify signal-processing algorithms to accommodate changes in brain activity. Furthermore, the human brain and BCI participate in knowledge acquisition; the first one strengthens cognitive abilities through exposure to new experiences, and the second one improves performance through ongoing adjustment and improvement. Current research seeks to incorporate emotional states into BCI systems to improve the user experience, despite the exceptional emotional regulation abilities of the human brain. The implementation of BCIs for older adults could be more effective, inclusive, and beneficial in improving their quality of life. This review aims to improve the understanding of brain-machine interfaces and their implications for mental health in older adults.

Multiclass Classification Framework of Motor Imagery EEG by Riemannian Geometry Networks

In motor imagery (MI) tasks for brain computer interfaces (BCIs), the spatial covariance matrix (SCM) of electroencephalogram (EEG) signals plays a critical role in accurate classification. Given that SCMs are symmetric positive definite (SPD), Riemannian geometry is widely utilized to extract classification features. However, calculating distances between SCMs is computationally intensive due to operations like eigenvalue decomposition, and classical optimization techniques, such as gradient descent, cannot be directly applied to Riemannian manifolds, making the computation of the Riemannian mean more complex and reliant on iterative methods or approximations. In this paper, we propose a novel multiclass classification framework that integrates Riemannian geometry and neural networks to mitigate these challenges. The framework comprises two modules: a Riemannian module with multiple branches and a classification module. During training, a fusion loss function is introduced to update the branch corresponding to the true label, while other branches are updated using different loss functions along with the classification module. Comprehensive experiments on four sets of MI EEG data demonstrate the efficiency and effectiveness of the proposed model.

Improving inter-session performance via relevant session-transfer for multi-session motor imagery classification

Motor imagery (MI)-based brain-computer interfaces (BCIs) using electroencephalography (EEG) have found practical applications in external device control. However, the non-stationary nature of EEG signals remains to obstruct BCI performance across multiple sessions, even for the same user. In this study, we aim to address the impact of non-stationarity, also known as inter-session variability, on multi-session MI classification performance by introducing a novel approach, the relevant session-transfer (RST) method. Leveraging the cosine similarity as a benchmark, the RST method transfers relevant EEG data from the previous session to the current one. The effectiveness of the proposed RST method was investigated through performance comparisons with the self-calibrating method, which uses only the data from the current session, and the whole-session transfer method, which utilizes data from all prior sessions. We validated the effectiveness of these methods using two datasets: a large MI public dataset (Shu Dataset) and our own dataset of gait-related MI, which includes both healthy participants and individuals with spinal cord injuries. Our experimental results revealed that the proposed RST method leads to a 2.29 % improvement (p < 0.001) in the Shu Dataset and up to a 6.37 % improvement in our dataset when compared to the self-calibrating method. Moreover, our method surpassed the performance of the recent highest-performing method that utilized the Shu Dataset, providing further support for the efficacy of the RST method in improving multi-session MI classification performance. Consequently, our findings confirm that the proposed RST method can improve classification performance across multiple sessions in practical MI-BCIs.

Subject-Invariant Deep Neural Networks Based on Baseline Correction for EEG Motor Imagery BCI

Electroencephalography (EEG)-based brain-computer interface (BCI) systems have been extensively used in various applications, such as communication, control, and rehabilitation. However, individual anatomical and physiological differences cause subject-specific variability of EEG signals for the same task, and BCI systems thus require a calibration procedure that adjusts system parameters to each subject. To overcome this problem, we propose a subject-invariant deep neural network (DNN) using baseline-EEG signals that can be recorded from subjects resting in comfortable states. We first modeled the deep features of EEG signals as a decomposition of subject-invariant and subject-variant features corrupted by anatomical/physiological characteristics. Subject-variant features were then removed from the deep features by learning the network with a baseline correction module (BCM) using the underlying individual information in baseline-EEG signals. The subject-invariant loss forces the BCM to assemble subject-invariant features that have the same class, irrespective of the subject. Using 1-min baseline-EEG signals of the new subject, our algorithm can eliminate subject-variant components from test data without the calibration process. The experimental results show that our subject-invariant DNN framework significantly increases decoding accuracies of the conventional DNN methods for BCI systems. Furthermore, feature visualizations illustrate that the proposed BCM extracts subject-invariant features that are close to each other in the same class.

NeuroGrasp: Real-Time EEG Classification of High-Level Motor Imagery Tasks Using a Dual-Stage Deep Learning Framework

Brain-computer interfaces (BCIs) have been widely employed to identify and estimate a user's intention to trigger a robotic device by decoding motor imagery (MI) from an electroencephalogram (EEG). However, developing a BCI system driven by MI related to natural hand-grasp tasks is challenging due to its high complexity. Although numerous BCI studies have successfully decoded large body parts, such as the movement intention of both hands, arms, or legs, research on MI decoding of high-level behaviors such as hand grasping is essential to further expand the versatility of MI-based BCIs. In this study, we propose NeuroGrasp, a dual-stage deep learning framework that decodes multiple hand grasping from EEG signals under the MI paradigm. The proposed method effectively uses an EEG and electromyography (EMG)-based learning, such that EEG-based inference at test phase becomes possible. The EMG guidance during model training allows BCIs to predict hand grasp types from EEG signals accurately. Consequently, NeuroGrasp improved classification performance offline, and demonstrated a stable classification performance online. Across 12 subjects, we obtained an average offline classification accuracy of 0.68 (±0.09) in four-grasp-type classifications and 0.86 (±0.04) in two-grasp category classifications. In addition, we obtained an average online classification accuracy of 0.65 (±0.09) and 0.79 (±0.09) across six high-performance subjects. Because the proposed method has demonstrated a stable classification performance when evaluated either online or offline, in the future, we expect that the proposed method could contribute to different BCI applications, including robotic hands or neuroprosthetics for handling everyday objects.

Multi-Source Decentralized Transfer for Privacy-Preserving BCIs

Transfer learning, which utilizes labeled source domains to facilitate the learning in a target model, is effective in alleviating high intra- and inter-subject variations in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Existing transfer learning approaches usually use the source subjects' EEG data directly, leading to privacy concerns. This paper considers a decentralized privacy-preserving transfer learning scenario: there are multiple source subjects, whose data and computations are kept local, and only the parameters or predictions of their pre-trained models can be accessed for privacy-protection; then, how to perform effective cross-subject transfer for a new subject with unlabeled EEG trials? We propose an offline unsupervised multi-source decentralized transfer (MSDT) approach, which first generates a pre-trained model from each source subject, and then performs decentralized transfer using the source model parameters (in gray-box settings) or predictions (in black-box settings). Experiments on two datasets from two BCI paradigms, motor imagery and affective BCI, demonstrated that MSDT outperformed several existing approaches, which do not consider privacy-protection at all. In other words, MSDT achieved both high privacy-protection and better classification performance.

Multi-Armed Bandits in Brain-Computer Interfaces

The multi-armed bandit (MAB) problem models a decision-maker that optimizes its actions based on current and acquired new knowledge to maximize its reward. This type of online decision is prominent in many procedures of Brain-Computer Interfaces (BCIs) and MAB has previously been used to investigate, e.g., what mental commands to use to optimize BCI performance. However, MAB optimization in the context of BCI is still relatively unexplored, even though it has the potential to improve BCI performance during both calibration and real-time implementation. Therefore, this review aims to further describe the fruitful area of MABs to the BCI community. The review includes a background on MAB problems and standard solution methods, and interpretations related to BCI systems. Moreover, it includes state-of-the-art concepts of MAB in BCI and suggestions for future research.

Classification of motor imagery using multisource joint transfer learning

As an important way for human-computer interaction, the motor imagery brain-computer interface (MI-BCI) can decode personal motor intention directly by analyzing electroencephalogram (EEG) signals. However, a large amount of labeled data has to be collected for each new subject since EEG patterns vary between individuals. The long calibration phase severely limits the further development of MI-BCI. To tackle this problem, multi-source joint domain adaption (MJDA) and multi-source joint Riemannian adaption (MJRA) algorithms are proposed in this paper. Both methods aim to transfer knowledge from other subjects to the current subject who has only a small amount of labeled data. First, the common spatial pattern with Euclidean alignment is used to select source subjects who have similar spatial patterns to the target subject. Second, the covariance matrices of EEG trials are aligned in Riemannian space by removing subject-specific baselines. These two steps are shared by MJDA and MJRA. In the last step, MJDA attempts to minimize the feature distribution mismatch in the Riemannian tangent space, while MJRA attempts to find an adaptive Riemannian classifier. Finally, the proposed methods are validated on two datasets: BCI Competition IV 2a and online event-related desynchronization (ERD)-BCI. The experimental results demonstrate that both MJDA and MJRA outperform the state-of-the-art approaches. The MJDA provides a new idea for the offline analysis of MI-BCI, while MJRA could make a big difference to the online calibration of MI-BCI.