
Applied Sciences, Год журнала: 2025, Номер 15(11), С. 6237 - 6237
Опубликована: Июнь 1, 2025
Understanding how people spend time on daily activities is key to modeling travel behavior. However, accurately estimating the duration of these remains a significant challenge, especially when generating synthetic activity-travel data. This article introduces an activity-based approach that addresses this issue by applying statistical and machine learning models improve precision activity estimates. The method utilizes real-world Origin-Destination (OD) datasets generate additional data can support transportation planning processes. Unlike conventional approaches rely solely OD matrices, framework incorporates Cox Cox-based hazard more precisely estimate durations, as well arrival departure times across trip segments. Statistical tests comparative evaluations show proposed produces accurate than existing open-source tools do not employ hazard-based modeling. A case study using from Athens, Greece, demonstrates effectiveness approach.
Язык: Английский