Demand forecasting and activity-based mobility modeling from cell phone data
PI: Alexey Pozdnukov, UC Berkeley; Co-PI Paul Waddell, UC Berkeley
Abstract: This project develops machine learning algorithms and methods for processing of cell phone location logs to generate travel behavior data. The project initially focuses on bias correction and activity inference for generating activity-based travel demand models. Inferred activity chains are used to calibrate an agent-based traffic micro-simulation for the SF Bay Area, and validated on loop detector counts.
Quarterly Progress Reports
Click on the links below to download any of the quarterly progress reports already finished.