Gan Liu
Papers
1
Total Citations
5
H-Index
1
About
Gan Liu is a researcher advancing the field of affective computing and human-robot interaction (HRI) through innovative electroencephalogram (EEG)-based emotion recognition. His key research areas include transfer learning, domain adaptation, and multi-source EEG signal processing. Liu’s most notable contribution is the development of the Joint Distribution Adaptation Network, a framework that addresses the critical challenge of cross-subject and cross-session EEG data variability. By aligning both marginal and conditional distributions across multiple source domains, his work enables more robust and generalizable emotion recognition systems—a breakthrough for real-world HRI applications where data from different users or time points often fail to transfer. His 2021 paper on this method has garnered 5 citations, reflecting its growing influence in the community. Liu’s research directly tackles the practical limitations that hinder widespread HRI deployment, offering a pathway toward more adaptive and personalized affective interfaces. His work stands at the intersection of machine learning and neuroscience, promising to make machines more responsive to human emotional states.
Research Focus
Key Achievements
Top Papers
- 1