RESUMO

Objective.To propose novel SSVEP classification methodologies using deep neural networks (DNNs) and improve performances in single-channel and user-independent brain-computer interfaces (BCIs) with small data lengths.Approach.We propose the utilization of filter banks (creating sub-band components of the EEG signal) in conjunction with DNNs. In this context, we created three different models: a recurrent neural network (FBRNN) analyzing the time domain, a 2D convolutional neural network (FBCNN-2D) processing complex spectrum features and a 3D convolutional neural network (FBCNN-3D) analyzing complex spectrograms, which we introduce in this study as possible input for SSVEP classification. We tested our neural networks on three open datasets and conceived them so as not to require calibration from the final user, simulating a user-independent BCI.Results.The DNNs with the filter banks surpassed the accuracy of similar networks without this preprocessing step by considerable margins, and they outperformed common SSVEP classification methods (SVM and FBCCA) by even higher margins.Conclusion and significance.Filter banks allow different types of deep neural networks to more efficiently analyze the harmonic components of SSVEP. Complex spectrograms carry more information than complex spectrum features and the magnitude spectrum, allowing the FBCNN-3D to surpass the other CNNs. The performances obtained in the challenging classification problems indicates a strong potential for the construction of portable, economical, fast and low-latency BCIs.

Assuntos

Interfaces Cérebro-Computador , Algoritmos , Eletroencefalografia/métodos , Potenciais Evocados Visuais , Redes Neurais de Computação

RESUMO

Brain-Computer Interface (BCI) is a technology that uses electroencephalographic (EEG) signals to control external devices, such as Functional Electrical Stimulation (FES). Visual BCI paradigms based on P300 and Steady State Visually Evoked potentials (SSVEP) have shown high potential for clinical purposes. Numerous studies have been published on P300- and SSVEP-based non-invasive BCIs, but many of them present two shortcomings: (1) they are not aimed for motor rehabilitation applications, and (2) they do not report in detail the artificial intelligence (AI) methods used for classification, or their performance metrics. To address this gap, in this paper the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology was applied to prepare a systematic literature review (SLR). Papers older than 10 years, repeated or not related to a motor rehabilitation application, were excluded. Of all the studies, 51.02% referred to theoretical analysis of classification algorithms. Of the remaining, 28.48% were for spelling, 12.73% for diverse applications (control of wheelchair or home appliances), and only 7.77% were focused on motor rehabilitation. After the inclusion and exclusion criteria were applied and quality screening was performed, 34 articles were selected. Of them, 26.47% used the P300 and 55.8% the SSVEP signal. Five applications categories were established: Rehabilitation Systems (17.64%), Virtual Reality environments (23.52%), FES (17.64%), Orthosis (29.41%), and Prosthesis (11.76%). Of all the works, only four performed tests with patients. The most reported machine learning (ML) algorithms used for classification were linear discriminant analysis (LDA) (48.64%) and support vector machine (16.21%), while only one study used a deep learning algorithm: a Convolutional Neural Network (CNN). The reported accuracy ranged from 38.02 to 100%, and the Information Transfer Rate from 1.55 to 49.25 bits per minute. While LDA is still the most used AI algorithm, CNN has shown promising results, but due to their high technical implementation requirements, many researchers do not justify its implementation as worthwile. To achieve quick and accurate online BCIs for motor rehabilitation applications, future works on SSVEP-, P300-based and hybrid BCIs should focus on optimizing the visual stimulation module and the training stage of ML and DL algorithms.

RESUMO

Neural entrainment is the synchronization of neural activity to the frequency of repetitive external stimuli, which can be observed as an increase in the electroencephalogram (EEG) power spectrum at the driving frequency, -also known as the steady-state response. Although it has been systematically reported that the entrained EEG oscillation persists for approximately three cycles after stimulus offset, the neural mechanisms underpinning it remain unknown. Focusing on alpha oscillations, we adopt the dynamical excitation/inhibition framework, which suggests that phases of entrained EEG signals correspond to alternating excitatory/inhibitory states of the neural circuitry. We hypothesize that the duration of the persistence of entrainment is determined by the specific functional state of the entrained neural network at the time the stimulus ends. Steady-state visually evoked potentials (SSVEP) were elicited in 19 healthy volunteers at the participants' individual alpha peaks. Visual stimulation consisted of a sinusoidally-varying light terminating at one of four phases: 0, π/2, π, and 3π/2. The persistence duration of the oscillatory activity was analyzed as a function of the terminating phase of the stimulus. Phases of the SSVEP at the stimulus termination were distributed within a constant range of values relative to the phase of the stimulus. Longer persistence durations were obtained when visual stimulation terminated towards the troughs of the alpha oscillations, while shorter persistence durations occurred when stimuli terminated near the peaks. Source localization analysis suggests that the persistence of entrainment reflects the functioning of fronto-occipital neuronal circuits, which might prime the sensory representation of incoming visual stimuli based on predictions about stimulus rhythmicity. Consequently, different states of the network at the end of the stimulation, corresponding to different states of intrinsic neuronal coupling, may determine the time windows over which coding of incoming sensory stimulation is modulated by the preceding oscillatory activity.