Research Exchanges

Namwoo Kim


Summary

Dispatched as a visiting student researcher to UCB's Civil and Environmental Engineering for about 6 months, under the guidance of Professor Mark Hansen, he conducted research on social vulnerability prediction using mobility data and research and development of an expression learning model using time series data.

Research

Dispatched as a visiting student researcher to UCB's Civil and Environmental Engineering for about 6 months, under the guidance of Professor Mark Hansen, he conducted research on social vulnerability prediction using mobility data and research and development of an expression learning model using time series data.

Yuyol Shin


Summary

Yuyol Shin has been at Civil and Environmental Engineering at UC Berkeley for about 6 months, under the supervision of Professor Mark Hansen. During the visit, Yuyol has also been working with Dr. Jane Macfarlane and her team on developing a surrogate model for large-scale transportation networks. He conducted research on traffic forecasting using spatial-temporal graph neural networks with a focus on reflecting real-time dynamic changes of traffic data. More details of the research can be found in the link (site ), and paper (paper)

Research

The complex spatial-temporal correlations in transportation networks make the traffic forecasting problem challenging. Since transportation system inherently possesses graph structures, much research efforts have been put with graph neural networks. Recently, constructing adaptive graphs to the data has shown promising results over the models relying on a single static graph structure. However, the graph adaptations are applied during the training phases, and do not reflect the data used during the testing phases. Such shortcomings can be problematic especially in traffic forecasting since the traffic data often suffers from the unexpected changes and irregularities in the time series. In this study, we propose a novel traffic forecasting framework called Progressive Graph Convolutional Network (PGCN). PGCN constructs a set of graphs by progressively adapting to input data during the training and the testing phases. Specifically, we implemented the model to construct progressive adjacency matrices by learning trend similarities among graph nodes. Then, the model is combined with the dilated causal convolution and gated activation unit to extract temporal features. With residual and skip connections, PGCN performs the traffic prediction. When applied to four real-world traffic datasets of diverse geometric nature, the proposed model achieves state-of-the-art performance with consistency in all datasets. We conclude that the ability of PGCN to progressively adapt to input data enables the model to generalize in different study sites with robustness.