Due to the limited perceptual field, convolutional neural networks (CNN) only extract local temporal features and may fail to capture long-term dependencies for EEG decoding. In this paper, we propose a compact Convolutional Transformer, named EEG Conformer, to encapsulate local and global features in a unified EEG classification framework. Specifically, the convolution module learns the low-level local features throughout the one-dimensional temporal and spatial convolution layers. The self-attention module is straightforwardly connected to extract the global correlation within the local temporal features. Subsequently, the simple classifier module based on fully-connected layers is followed to predict the categories for EEG signals. To enhance interpretability, we also devise a visualization strategy to project the class activation mapping onto the brain topography. Finally, we have conducted extensive experiments to evaluate our method on three public datasets in EEG-based motor imagery and emotion recognition paradigms. The experimental results show that our method achieves state-of-the-art performance and has great potential to be a new baseline for general EEG decoding. The code has been released in https://github.com/eeyhsong/EEG-Conformer.

Significance: Brain–computer interface (BCI) technology provides a new communication channel. However, current applications have been severely limited by low communication speed. This study reports a noninvasive brain speller that achieved a multifold increase in information transfer rate compared with other existing systems. Based on extremely precise coding of frequency and phase in single-trial steady-state visual evoked potentials, this study developed a new joint frequency-phase modulation method and a user-specific decoding algorithm to implement synchronous modulation and demodulation of electroencephalograms. The resulting speller obtained high spelling rates up to 60 characters (∼12 words) per minute. The proposed methodological framework of high-speed BCI can lead to numerous applications in both patients with motor disabilities and healthy people.

Objective. Recently, canonical correlation analysis (CCA) has been widely used in steady-state visual evoked potential (SSVEP)-based brain–computer interfaces (BCIs) due to its high efficiency, robustness, and simple implementation. However, a method with which to make use of harmonic SSVEP components to enhance the CCA-based frequency detection has not been well established. Approach. This study proposed a filter bank canonical correlation analysis (FBCCA) method to incorporate fundamental and harmonic frequency components to improve the detection of SSVEPs. A 40-target BCI speller based on frequency coding (frequency range: 8–15.8 Hz, frequency interval: 0.2 Hz) was used for performance evaluation. To optimize the filter bank design, three methods (M1: sub-bands with equally spaced bandwidths; M2: sub-bands corresponding to individual harmonic frequency bands; M3: sub-bands covering multiple harmonic frequency bands) were proposed for comparison. Classification accuracy and information transfer rate (ITR) of the three FBCCA methods and the standard CCA method were estimated using an offline dataset from 12 subjects. Furthermore, an online BCI speller adopting the optimal FBCCA method was tested with a group of 10 subjects. Main results. The FBCCA methods significantly outperformed the standard CCA method. The method M3 achieved the highest classification performance. At a spelling rate of ∼33.3 characters/min, the online BCI speller obtained an average ITR of 151.18 ± 20.34 bits min−1. Significance. By incorporating the fundamental and harmonic SSVEP components in target identification, the proposed FBCCA method significantly improves the performance of the SSVEP-based BCI, and thereby facilitates its practical applications such as high-speed spelling.

With the development of brain-computer interface (BCI) technology, researchers are now attempting to put current BCI techniques into practical application. This paper presents an environmental controller using a BCI technique based on steady-state visual evoked potential. The system is composed of a stimulator, a digital signal processor, and a trainable infrared remote-controller. The attractive features of this system include noninvasive signal recording, little training requirement, and a high information transfer rate. Our test results have shown that this system can distinguish at least 48 targets and provide a transfer rate up to 68 b/min. The system has been applied to the control of an electric apparatus successfully.

Spelling is an important application of brain-computer interfaces (BCIs). Previous BCI spellers were not suited for widespread use due to their low information transfer rate (ITR). In this study, we constructed a high-ITR BCI speller based on the steady-state visual evoked potential (SSVEP). A 45-target BCI speller was implemented with a frequency resolution of 0.2 Hz. A sampled sinusoidal stimulation method was used to present visual stimuli on a conventional LCD screen. The online results revealed that the proposed BCI speller had a good performance, reaching a high average accuracy (84.1% for 2 s stimulation time; 90.2% for 3 s stimulation time) and the corresponding high ITR (105 bits/min for 2 s stimulation time, 82 bits/min for 3 s stimulation time) during the low-frequency stimuli, while 88.7% and 61 bits/min were achieved for a 4 s time window during the high-frequency stimuli.

The brain-computer interface (BCI) provides an alternative means to communicate and it has sparked growing interest in the past two decades. Specifically, for Steady-State Visual Evoked Potential (SSVEP) based BCI, marked improvement has been made in the frequency recognition method and data sharing. However, the number of pubic databases is still limited in this field. Therefore, we present a BEnchmark database Towards BCI Application (BETA) in the study. The BETA database is composed of 64-channel Electroencephalogram (EEG) data of 70 subjects performing a 40-target cued-spelling task. The design and the acquisition of the BETA are in pursuit of meeting the demand from real-world applications and it can be used as a test-bed for these scenarios. We validate the database by a series of analyses and conduct the classification analysis of eleven frequency recognition methods on BETA. We recommend using the metric of wide-band signal-to-noise ratio (SNR) and BCI quotient to characterize the SSVEP at the single-trial and population levels, respectively. The BETA database can be downloaded from the following link http://bci.med.tsinghua.edu.cn/download.html.