Please use this identifier to cite or link to this item:
Utilizing Geospatial Information in Cellular Data Usage for Key Location Prediction
|Title:||Utilizing Geospatial Information in Cellular Data Usage for Key Location Prediction|
|Keywords:||Decision Support for Smart Cities|
cellular data usage, geospatial information, home and workplace, precision marketing, kernel density estimation
|Date Issued:||03 Jan 2018|
|Abstract:||Previous research on the identification of key locations (e.g., home and workplace) for a user largely relies on call detail records (CDRs). Recently, cellular data usage (i.e., mobile internet) is growing rapidly and offers fine-grained insights into various human behavior patterns. In this study, we introduce a novel dataset containing both voice and mobile data usage records of mobile users. We then construct a new feature based on the geospatial distribution of cell towers connected by mobile users and employ bivariate kernel density estimation to help predict users’ key locations. The evaluation results suggest that augmented features based on both voice and mobile data usage improve the prediction precision and recall.|
|Rights:||Attribution-NonCommercial-NoDerivatives 4.0 International|
|Appears in Collections:||
Decision Support for Smart Cities|
Please email firstname.lastname@example.org if you need this content in ADA-compliant format.
Items in ScholarSpace are protected by copyright, with all rights reserved, unless otherwise indicated.