In the previous decade, breakthroughs in the central nervous system bioinformatics and computational innovation have prompted significant developments in brain–computer interface (BCI), elevating it to the forefront of applied science and research. BCI revitalization enables neurorehabilitation strategies for physically disabled patients (e.g., disabled patients and hemiplegia) and patients with brain injury (e.g., patients with stroke). Different methods have been developed for electroencephalogram (EEG)-based BCI applications. Due to the lack of a large set of EEG data, methods using matrix factorization and machine learning were the most popular. However, things have changed recently because a number of large, high-quality EEG datasets are now being made public and used in deep learning-based BCI applications. On the other hand, deep learning is demonstrating great prospects for solving complex relevant tasks such as motor imagery classification, epileptic seizure detection, and driver attention recognition using EEG data. Researchers are doing a lot of work on deep learning-based approaches in the BCI field right now. Moreover, there is a great demand for a study that emphasizes only deep learning models for EEG-based BCI applications. Therefore, we introduce this study to the recent proposed deep learning-based approaches in BCI using EEG data (from 2017 to 2022). The main differences, such as merits, drawbacks, and applications are introduced. Furthermore, we point out current challenges and the directions for future studies. We argue that this review study will help the EEG research community in their future research.

Dynamic functional connectivity (dFC) analysis enables us to capture the time-varying interactions between brain regions and can lead to powerful biomarkers. Most dFC studies are focused on the study of temporal dynamics and require significant postprocessing to summarize the results of the dynamics analysis. In this paper, we introduce an effective framework that makes use of independent vector analysis (IVA) with fractional amplitude of low frequency fluctuation (fALFF) features extracted from task functional magnetic resonance imaging (fMRI) data. Our approach, which is based on IVA with fALLF features as input, (IVA-fALLF) produces an effective summary of the dynamics also greatly facilitating the study of both spatial and temporal dynamics in a more concise manner. IVA-fALLF captures the spatial and temporal dynamics of sensorimotor task data and identifies a component with significant difference in dynamic behavior between healthy controls (HC) and patients with schizophrenia (SZ). Finally, our post analysis using behavioral scores finds significant correlation between brain imaging data and the associated behavioral scores, increasing confidence on our results. Our results are consistent with the previous data-driven dFC analysis as we find similar brain networks showing abnormal behavior in patients with SZ. Moreover, our analysis identifies component behavior in task and rest windows separately and provides additional confirmation of results through correlation with behavioral scores.

Analysis of time-evolving data is crucial to understand the functioning of dynamic systems such as the brain. For instance, analysis of functional magnetic resonance imaging (fMRI) data collected during a task may reveal spatial regions of interest, and how they evolve during the task. However, capturing underlying spatial patterns as well as their change in time is challenging. The traditional approach in fMRI data analysis is to assume that underlying spatial regions of interest are static. In this article, using fractional amplitude of low-frequency fluctuations (fALFF) as an effective way to summarize the variability in fMRI data collected during a task, we arrange time-evolving fMRI data as a subjects by voxels by time windows tensor, and analyze the tensor using a tensor factorization-based approach called a PARAFAC2 model to reveal spatial dynamics. The PARAFAC2 model jointly analyzes data from multiple time windows revealing subject-mode patterns, evolving spatial regions (also referred to as networks) and temporal patterns. We compare the PARAFAC2 model with matrix factorization-based approaches relying on independent components, namely, joint independent component analysis (ICA) and independent vector analysis (IVA), commonly used in neuroimaging data analysis. We assess the performance of the methods in terms of capturing evolving networks through extensive numerical experiments demonstrating their modeling assumptions. In particular, we show that (i) PARAFAC2 provides a compact representation in all modes, i.e., subjects, time, and voxels, revealing temporal patterns as well as evolving spatial networks, (ii) joint ICA is as effective as PARAFAC2 in terms of revealing evolving networks but does not reveal temporal patterns, (iii) IVA's performance depends on sample size, data distribution and covariance structure of underlying networks. When these assumptions are satisfied, IVA is as accurate as the other methods, (iv) when subject-mode patterns differ from one time window to another, IVA is the most accurate. Furthermore, we analyze real fMRI data collected during a sensory motor task, and demonstrate that a component indicating statistically significant group difference between patients with schizophrenia and healthy controls is captured, which includes primary and secondary motor regions, cerebellum, and temporal lobe, revealing a meaningful spatial map and its temporal change.

No abstract