Xiaorong Gao's research while affiliated with Tsinghua University and other places

Publications (11)

Article
Objective. Computerized classification of sleep stages based on single-lead electroencephalography (EEG) signals is important, but still challenging. In this paper, we proposed a deep neural network called MRASleepNet for automatic sleep stage classification using single-channel EEG signals. Approach. The proposed MRASleepNet model consisted of a f...
Article
Full-text available
Standard cognitive assessment tools often involve motor or verbal responses, making them impossible for severely motor-disabled individuals. Brain-computer interfaces (BCIs) are expected to help severely motor-impaired individuals to perform cognitive assessment because BCIs can circumvent motor and verbal requirements. Currently, the field of rese...
Article
Full-text available
In order to evaluate refractive amblyopia suppression and understand the neural mechanism of amblyopia suppression and push-pull perception training, we recorded the EEG of refractive amblyopia children before, during, and after push-pull perception training. We compared the brain activity in different states through the steady-state visual evoked...
Article
Full-text available
Electroencephalogram (EEG) electrodes are critical devices for brain-computer interface and neurofeedback. A pre-gelled (PreG) electrode was developed in this paper for EEG signal acquisition with a short installation time and good comfort. A hydrogel probe was placed in advance on the Ag/AgCl electrode before wearing the EEG headband instead of a...
Article
Full-text available
Brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP) has been widely studied due to the high information transfer rate (ITR), little user training, and wide subject applicability. However, there are also disadvantages such as visual discomfort and “BCI illiteracy.” To address these problems, this study proposes to us...
Article
Objective: The steady-state visual evoked potential based brain-computer interface (SSVEP-BCI) implemented in dry electrodes is a promising paradigm for alternative and augmentative communication in real-world applications. To improve its performance and reduce the calibration effort for dry-electrode systems, we utilize cross-device transfer lear...
Article
Full-text available
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. Specifi...
Article
Objective. Steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) has the characteristics of fast communication speed, high stability, and wide applicability, thus it has been widely studied. With the rapid development in paradigm, algorithm, and system design, SSVEP-BCI is gradually applied in clinical and real-life scen...
Article
Full-text available
Brain-computer interfaces (BCIs) provide humans a new communication channel by encoding and decoding brain activities. Steady-state visual evoked potential (SSVEP)-based BCI stands out among many BCI paradigms because of its non-invasiveness, little user training, and high information transfer rate (ITR). However, the use of conductive gel and bulk...
Chapter
In this study, we developed a high-speed steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system to address two long-standing challenges in BCIs: tedious user training and low applicability for target users. We designed a training-free method with low computational complexity called the spatio-temporal equalization...
Conference Paper
In order to explore the effect of low frequency stimulation on pupil size and electroencephalogram (EEG), we presented subjects with 1-6Hz black-and-white-alternating flickering stimulus, and compared the differences of signal-to-noise ratio (SNR) and classification performance between pupil size and visual evoked potentials (VEPs). The results sho...

Citations

... Frequency tagging is widely used to test the integrity of sensory processing, especially in the visual domain (Steady-State Visually Evoked Potentials-SSVEP [3]) and in the auditory domain (Auditory Steady-State Responses-ASSR [2]). Typical presentation rates depend on the frequency ranges in which these sensory systems are most responsive: [8][9][10][11][12][13][14][15][16][17][18][19][20] Hz for SSVEP and around 40 Hz for ASSR. In these frequency ranges, it is possible to obtain very high SNR because the amplitude of both ongoing EEG activity and biological EEG artifacts is low. ...
... The performance of gel-based and dry EEG solutions has been compared by either sequential or simultaneous acquisition with both systems within application-specific paradigms. However, most comparative studies thus far comprise low numbers of volunteers and have been conducted in optimally controlled environments, such as shielded acquisition chambers [23] or focused on low-density EEG with dedicated electrode layouts and applications [3][4][5][24][25][26], including manual electrode placement and preparation [27,28]. Moreover, an important limitation of the majority of previous studies is the single-center and single-operator approach. ...
... Thus, a CCA-based spatial filter can be obtained and then the 8-channel data were processed by the CCA-based spatial filter. Lastly, the amplitude spectrum y(f) was calculated by fast Fourier Transform (FFT), and the SNR in decibels (dB) was defined as the ratio of y(f) to the mean value of the eight neighboring frequencies [40]. The flow chart of the calculation process is shown in Figure 3. One-way repeated-measures analysis of variance (ANOVA) was also used to test the difference of amplitude and SNR between the PreG electrode and the wet electrode at different frequencies. ...
... The analysis of human visual imagination and understanding of the surroundings using brain signals is an interesting field of research in brain signal analysis. It includes the study of Steady-State Visual-Evoked Potentials (SSVEP) ( [85], [86], [87], [88], [89], [90], [91]) and visual recognition ( [92], [93], [94], [95], [96]). ...
... Brain computer interface (BCI) technology provides a new cognitive channel for human beings by encoding and decoding brain activity. SSVEP-based BCI stands out from other BCI paradigms because of its advantages of being noninvasive, requiring little user training, and yielding a high information transfer rate (13). SSVEP are widely used in electroencephalogram (EEG) responses elicited by periodic visual stimuli. ...
... This study intends to use low-frequency visual stimulations that can simultaneously elicit VEP and PR (Jiang et al., 2020) to implement a 12-target h-BCI speller. Compared with the existing HCI and BCI work related to PR, this system aims to achieve a shorter detection time and higher classification accuracy by adopting efficient coding and decoding methods. ...