Jiayun Hou

Papers

Total Citations

H-Index

About

Jiayun Hou has made significant contributions to the field of brain-computer interfaces (BCIs), with a primary focus on enhancing the practicality and efficiency of P300-based systems. Her key research addresses the critical challenge of inter-subject variability in P300 responses, which traditionally requires extensive, user-specific labeled data collection and leads to time-consuming calibration. Hou's most cited work, "Improving the P300-based brain-computer interface with transfer learning" (2017, 8 citations), pioneers the application of transfer learning techniques to mitigate this bottleneck. By leveraging knowledge from existing users, her approach dramatically reduces the need for new user training data, making BCI systems more accessible and deployable in real-world scenarios. This contribution is foundational for advancing non-invasive neural interfaces, with potential applications in assistive technology for individuals with motor disabilities. Hou's research represents a crucial step toward user-friendly, adaptive BCIs, demonstrating how machine learning can bridge the gap between laboratory prototypes and practical, everyday use. Her work continues to influence researchers seeking to improve BCI performance through cross-subject knowledge transfer.