Liyan Xiong

Title: Liyan Xiong: Innovator in Traffic Flow Forecasting

Introduction

Liyan Xiong is a notable inventor based in Nanchang, China. He has made significant contributions to the field of traffic management through his innovative patent. His work focuses on enhancing the accuracy of traffic flow forecasting, which is crucial for urban planning and traffic control.

Latest Patents

Liyan Xiong holds a patent for a "Traffic flow forecasting method based on multi-mode dynamic residual graph convolution network." This method involves constructing a relationship matrix and an adaptive matrix to learn the site dependence relationship for historical traffic data of traffic stations. It utilizes multi-mode dynamic graph convolution to extract traffic characteristics corresponding to different traffic modes. The method embeds graph convolution into a gated cyclic neural network to combine space dependence and time dependence of traffic flow. By connecting the network using dynamic residuals, it effectively combines input traffic data with decoding data to obtain the final forecasting value. This innovative approach captures traffic flow characteristics corresponding to different traffic modes and dynamically fuses these characteristics.

Career Highlights

Liyan Xiong is affiliated with East China Jiaotong University, where he contributes to research and development in traffic management technologies. His work is instrumental in advancing methodologies that improve traffic forecasting accuracy.

Collaborations

Liyan collaborates with several colleagues, including Xiaohui Huang and Yuming Ye, who contribute to his research efforts and innovations in the field.

Conclusion

Liyan Xiong's contributions to traffic flow forecasting through his innovative patent demonstrate his commitment to improving urban traffic management. His work is paving the way for more efficient traffic systems in the future.