New Progress in Brain-Computer Interface Research from ECUST Published in IEEE Transactions on Image Processing

Recently, the team led by Professor Jin Jing of ECUST has achieved new progress in the interdisciplinary research on Brain-Computer Interface (BCI) and computer vision. The study was published online in IEEE Transactions on Image Processing under the title “Enhancing Target Recognition Performance in SSVEP-Based Brain-Computer Interfaces via Deep Neural Networks With Pyramid Squeeze Attention”. This is the first publication in this journal to take BCI as its core research subject, highlighting the growing integration of image processing and neural engineering.

Current mainstream steady-state visual evoked potential (SSVEP) decoding methods heavily rely on manually designed features and within-subject training, leading to subjective feature extraction, limited generalization ability, and performance degradation in cross-subject scenarios. 

Although existing deep learning methods possessed automatic feature learning capabilities, they do not fully integrate multi-dimensional information and overlooked the personalized neural response characteristics of new subjects. 

To explore common neural patterns across subjects and achieve rapid adaptation with small samples, the research team proposed a deep neural network based on pyramid squeeze attention. By combining joint feature extraction across frequency, spatial, and temporal domains with three-stage transfer learning, the method improved the cross-subject target recognition performance of SSVEP-based BCIs, providing an efficient solution for EEG signal decoding in low signal-to-noise ratio and small sample scenarios.

ECUST is the first and sole corresponding institution for this paper. Professor Jin Jing is the corresponding author, and PhD candidate Wu Xiao is the first author. This research was supported by the National Major Science and Technology Program on Brain Science and Brain Inspired Research, the National Natural Science Foundation of China, the Shanghai Municipal Science and Technology Major Project, the Jiangsu Provincial Science and Technology Plan Special Fund, the National Key Research and Development Program, and the Lingang Laboratory.