Deep Learning for Real-Time Crime Forecasting and Its Ternarization

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].

[1]  George E. Tita,et al.  Gang rivalry dynamics via coupled point process networks , 2014 .

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  Taku Komura,et al.  Phase-functioned neural networks for character control , 2017, ACM Trans. Graph..

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Lin Xu,et al.  Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights , 2017, ICLR.

[8]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[9]  George E. Tita,et al.  Self-Exciting Point Process Modeling of Crime , 2011 .

[10]  Hanan Samet,et al.  Training Quantized Nets: A Deeper Understanding , 2017, NIPS.

[11]  David Bommes,et al.  Boundary element octahedral fields in volumes , 2017, TOGS.

[12]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[13]  Song Han,et al.  Trained Ternary Quantization , 2016, ICLR.

[14]  Colin Raffel,et al.  Lasagne: First release. , 2015 .

[15]  Andrea L. Bertozzi,et al.  Nonlinear Patterns in Urban Crime: Hotspots, Bifurcations, and Suppression , 2010, SIAM J. Appl. Dyn. Syst..

[16]  P. Jeffrey Brantingham,et al.  The Concentration-Dynamics Tradeoff in Crime Hot Spotting , 2017 .

[17]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

[18]  Xinyu Chen,et al.  Crime prediction using Twitter sentiment and weather , 2015, 2015 Systems and Information Engineering Design Symposium.

[19]  Xiaofeng Wang,et al.  Automatic Crime Prediction Using Events Extracted from Twitter Posts , 2012, SBP.

[20]  Hang-Bong Kang,et al.  Prediction of crime occurrence from multi-modal data using deep learning , 2017, PloS one.

[21]  Stanley Osher,et al.  Laplacian smoothing gradient descent , 2018, Research in the Mathematical Sciences.

[22]  Igor Carron,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016 .

[23]  Peng Chen,et al.  Forecasting Crime Using the ARIMA Model , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[24]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[25]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[26]  Matthew S. Gerber,et al.  Predicting crime using Twitter and kernel density estimation , 2014, Decis. Support Syst..

[27]  A. Stomakhin,et al.  Reconstruction of missing data in social networks based on temporal patterns of interactions , 2011 .

[28]  Jack Xin,et al.  Training Ternary Neural Networks with Exact Proximal Operator , 2016, ArXiv.

[29]  Andrea L Bertozzi,et al.  Dissipation and displacement of hotspots in reaction-diffusion models of crime , 2010, Proceedings of the National Academy of Sciences.

[30]  Silvio Savarese,et al.  Structural-RNN: Deep Learning on Spatio-Temporal Graphs , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, NIPS.

[32]  Tamal K. Dey,et al.  Persistent Heat Signature for Pose‐oblivious Matching of Incomplete Models , 2010, Comput. Graph. Forum.

[33]  Jack Xin,et al.  Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection , 2016, Journal of Computational Mathematics.

[34]  Bin Liu,et al.  Ternary Weight Networks , 2016, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[35]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[36]  Duo Zhang,et al.  Deep Learning for Real Time Crime Forecasting , 2017, ArXiv.