How full will my next bus be? A Framework to Predict Bus Crowding Levels
DocUID: 2019-016 Full Text:
PDF Author: Tahereh Arabghalizi, Alexandros Labrinidis
Abstract: Public transit is one of the first things that come to mind when someone talks about “smart cities.” As a result, many technologies, applications, and infrastructure have been deployed already to bring the promise of the smart city to public transportation. Most of these have focused on answering the question “when will my bus arrive?”; little has been done to answer the question “how full will my next bus be?” which also greatly affects commuters’ quality of life. In this paper, we develop a framework to address the fullness question. We formulate the problem as a classification problem, develop a framework to enable predictions using Random Forests, and evaluate our proposed techniques using data from the Pittsburgh region.
Keywords: smart city, intelligent transportation, urban computing
Published In: 8th International Workshop on Urban Computing (ACM)
Year Published: 2019
Project: PittSmartLiving Subject Area: Data Mining, Machine Learning
Publication Type: Workshop Paper
Sponsor: NSF CNS-1739413