A Generative Model of Urban Activities from Cellular Data

author: Mogeng Yin, UC Berkeley
published: Oct. 12, 2016,   recorded: August 2016,   views: 1316

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


Activity based travel models are the main tools used to evaluate traffic conditions in the context of rapidly changing travel demand. However, data collection for activity based models is performed through travel surveys that are infrequent, expensive, and reflect the changes in transportation with significant delays. Thanks to the ubiquitous cell phone data, we see an opportunity to substantially complement these surveys with data extracted from network carrier mobile phone usage logs, such as call detail records (CDRs). Activity based travel demand models describe travel itineraries of individual users, namely (1) what activities users are participating in; (2) when users perform these activities; and (3) how users travel to the activity locales. In this paper, we first present a method of extracting user stay locations while not over-filtering short-term travel. Second, we apply Input-Output Hidden Markov Models (IO-HMMs) to reveal the activity patterns in real CDR data (with a focus on the San Francisco Bay Area regular commuters) collected by a major network carrier. No personally identifiable information (PII) was gathered or used in conducting this study. The mobility data that was analyzed was anonymous and aggregated in strict compliance with the carrier’s privacy policy. Our approach delivers actionable information to the practitioners in a form of a modular activity-based travel demand model, and captures the heterogeneous activity transition probabilities conditioned on spatial-temporal context.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: