Publication Date
Spring 2025
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Engineering
Advisor
Wencen Wu; Bernardo Flores; Kaikai Liu
Abstract
Billions of people today rely on traffic predictions to optimize their travels. Digital mapping services deliver accurate predictions by learning from vast troves of historical data. Impressive as these systems are, their assumptions do not always apply. They depend on an endless flow of sensitive user data to a central authority, a stable Internet connection, and trustworthiness on both sides of the traditional client-server model. This thesis explores a novel architecture which bucks those assumptions. In the proposed model, traffic data remains on edge devices which individually train models via federated learning. Beyond the obvious privacy benefits, this architecture enables traffic prediction to occur in scenarios which the current paradigm struggles to support. In particular, in disaster scenarios such as earthquakes or hurricanes, evacuees may have no recourse in a dangerous environment without a system such as this.
Recommended Citation
Selvia, Andrew, "Sirilla: Predicting Traffic Flow via Stacked Decentralized Federated Learning" (2025). Master's Theses. 5667.
DOI: https://doi.org/10.31979/etd.96qt-wqec
https://scholarworks.sjsu.edu/etd_theses/5667
