Location-Based Social Networks (LBSN) provides unprecedented opportunities to tackle various social problems. In this study, we identify a number of crime-prediction-specific dynamic features which, for the first time, explore crime risk factors implicitly associated with the visitors. The reliable correlations between the proposed dynamic features and crime event occurrences have been observed. The evaluations on large real world data sets verify that the crime prediction performance can be notably improved with the inclusion of proposed crime-prediction-specific dynamic features.
@inproceedings{DBLP:conf/gis/RumiDS18,
author = {Shakila Khan Rumi and
Ke Deng and
Flora D. Salim},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/conf/gis/RumiDS18.bib},
booktitle = {Proceedings of the 26th ACM SIGSPATIAL International Conference
on Advances in Geographic Information Systems, SIGSPATIAL 2018,
Seattle, WA, USA, November 06-09, 2018},
doi = {10.1145/3274895.3274994},
editor = {Farnoush Banaei Kashani and
Erik G. Hoel and
Ralf Hartmut Güting and
Roberto Tamassia and
Li Xiong},
pages = {552--555},
publisher = {ACM},
timestamp = {Wed, 25 Sep 2019 01:00:00 +0200},
title = {Theft prediction with individual risk factor of visitors},
url = {https://doi.org/10.1145/3274895.3274994},
year = {2018}
}
© 2021 Flora Salim - CRUISE Research Group.