Fenqi Rong
Papers
2
Total Citations
61
H-Index
2
About
Fenqi Rong is a rising leader in brain-computer interface (BCI) research, specializing in motor imagery (MI) decoding and EEG signal processing. Their work directly tackles two of the field’s most persistent challenges: extracting meaningful neural features from noisy, limited data and ensuring reliable performance across multiple recording sessions. Rong’s flagship contribution, the M-FANet (Multi-Feature Attention Convolutional Neural Network), introduces a novel architecture that simultaneously captures spectral, spatial, and temporal features from EEG signals, achieving state-of-the-art MI decoding accuracy. This work has already garnered 44 citations, reflecting its immediate impact on rehabilitation robotics and motor control systems. Complementing this algorithmic advance, Rong led the creation of a multi-day, high-quality EEG dataset for MI-BCI (17 citations), directly addressing the critical issue of cross-session variability that has long hindered real-world BCI deployment. By providing a standardized benchmark for robust, day-to-day classification, this dataset is poised to accelerate progress toward practical, wearable BCIs. Rong’s dual focus—pushing algorithmic boundaries while building foundational resources—marks them as a key architect of next-generation, clinically viable neural interfaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2