Deep Learning for Real-Time Crime Forecasting and its Ternarization

November 23, 2017 ยท Declared Dead ยท ๐Ÿ› Chinese Annals of Mathematics. Series B

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Bao Wang, Penghang Yin, Andrea L. Bertozzi, P. Jeffrey Brantingham, Stanley J. Osher, Jack Xin arXiv ID 1711.08833 Category cs.LG: Machine Learning Cross-listed math.NA, stat.ML Citations 89 Venue Chinese Annals of Mathematics. Series B Last Checked 3 months ago
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].
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted