Fang Fang

Papers

Total Citations

H-Index

About

Fang Fang is an emerging researcher at the intersection of neural engineering, brain-computer interfaces (BCI), and machine learning, with a particular focus on electroencephalography (EEG) signal processing and motor imagery classification. Their most notable contribution introduces a novel character encoding-based framework for motor imagery EEG classification using convolutional neural networks (CNNs), a method that elegantly addresses two persistent challenges in the field: the complexity of feature extraction and the curse of dimensionality inherent in raw EEG data. By first converting EEG signals into character sequences before feeding them into a CNN architecture, Fang Fang's approach simplifies the classification pipeline while maintaining — and potentially improving — classification accuracy. This creative bridge between symbolic representation and deep learning reflects a broader commitment to making BCI systems more computationally accessible and practically deployable. Though still early in their citation trajectory with 8 citations on this 2023 work, the novelty of the methodology positions Fang Fang as a promising voice in the BCI research community, with this work likely to attract growing attention as motor imagery-based BCIs continue to advance toward real-world clinical and assistive technology applications.