Papers
2
Total Citations
183
H-Index
2
About
Xingchen Li is a leading researcher in brain–computer interfaces (BCIs), with a primary focus on motor imagery (MI) EEG signal processing and practical assistive technology. Li’s major contributions lie in developing advanced computational frameworks that bridge signal decomposition and deep learning. Their most influential work, “Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network,” has garnered 162 citations, establishing a robust method for extracting meaningful neural patterns from noisy EEG data. In a notable 2021 study (21 citations), Li introduced a transfer learning approach using rotation alignment with Riemannian mean, directly tackling the persistent challenge of cross-session and cross-subject variability in MI classification. This innovation has significant implications for real-world BCI applications, including wheelchair control, where reliable performance across different users and recording sessions is critical. By integrating optimization techniques with multi-scale neural networks, Li has advanced the accuracy and robustness of EEG-based recognition systems, making strides toward more intuitive and accessible BCI technologies for individuals with motor disabilities.
Research Focus
Key Achievements
Top Papers
- 1
- 2