Deep learning for real-time crime forecasting and its ternarization

DOI10.1007/S11401-019-0168-YzbMATH Open1453.91085arXiv1711.08833OpenAlexW2983165041WikidataQ126784973 ScholiaQ126784973MaRDI QIDQ2286236FDOQ2286236

Authors: Bao Wang, Penghang Yin, P. Jeffrey Brantingham, Jack Xin, Andrea L. Bertozzi, Stanley Osher 

Publication date: 10 January 2020

Published in: Chinese Annals of Mathematics. Series B (Search for Journal in Brave)

Abstract: Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model provides a reasonable approximation to such a complex system. Historical crime data are sparse in both space and time and the signal of interests is weak. In this work, we first present a proper representation of crime data. We then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels. These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy. Finally, we present a ternarization technique to address the resource consumption issue for its deployment in real world. This work is an extension of our short conference proceeding paper [Wang et al, Arxiv 1707.03340].

Full work available at URL: https://arxiv.org/abs/1711.08833

Recommendations

• Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ ``Real-time crime forecasting challenge
• Predicting citywide crowd flows using deep spatio-temporal residual networks
• Personalized crime location prediction
• Spatio-temporal low count processes with application to violent crime events
• Sequential data assimilation for 1D self-exciting processes with application to urban crime data

zbMATH Keywords

real-time forecastingcrime representationspatial-temporal deep learningternarization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Mathematical modeling or simulation for problems pertaining to game theory, economics, and finance (91-10) Mathematical sociology (including anthropology) (91D99) Computational methods for problems pertaining to game theory, economics, and finance (91-08)

Cites Work

• Self-exciting point process modeling of crime
• A STATISTICAL MODEL OF CRIMINAL BEHAVIOR
• Nonlinear Patterns in Urban Crime: Hotspots, Bifurcations, and Suppression
• Gang rivalry dynamics via coupled point process networks

Uses Software

• Theano
• cuDNN
• Adam
• BinaryConnect
• BinaryNet
• XNOR-Net
• LaplacianSmoothing-GradientDescent

This page was built for publication: Deep learning for real-time crime forecasting and its ternarization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2286236)