Abstract
We study high-resolution crime prediction and introduce a new generative model applicable to any spatiotemporal data with graph convolutional gated recurrent units (Graph-ConvGRU) and multivariate Gaussian distributions. We introduce a subdivision algorithm and create a graph representation to tackle the sparsity and complexity problem in high-resolution spatiotemporal data. By leveraging the flexible structure of graph representation, we model the spatial, temporal, and categorical relations of crime events and produce state vectors for each region. We create a multivariate probability distribution from the state vectors and train the distributions by minimizing the KL divergence between the generated and the actual distribution of the crime events. After creating the distributions, crime can be predicted in any resolution as the first time in the literature. In our experiments on real-life and synthetic datasets, our model obtains the best score with respect to the state-of-the-art models with statistically significant improvements. Hence, our model is not only generative but also precise. We also provide the source code of our algorithm for reproducibility.
Similar content being viewed by others
Notes
You can find all of our codes to perform analysis and experiments at https://github.com/sftekin/high-res-crime-forecasting.
References
Wang, H., et al.: Crime rate inference with big data. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 13–17-Aug, pp. 635–644 (2016). https://doi.org/10.1145/2939672.2939736
Khan, M.H., et al.: Spatiotemporal features of human motion for gait recognition. Signal Image Video Process. 13(2), 369–377 (2019). https://doi.org/10.1007/s11760-018-1365-y
Patil, A.R., et al.: A spatiotemporal approach for vision-based hand gesture recognition using Hough transform and neural network. Signal Image Video Process. 13(2), 413–421 (2019). https://doi.org/10.1007/s11760-018-1370-1
Huang, Q., et al.: View transform graph attention recurrent networks for skeleton-based action recognition. Signal Image Video Process. 15(3), 599–606 (2021). https://doi.org/10.1007/s11760-020-01781-6
Deepak, K., et al.: Residual spatiotemporal autoencoder for unsupervised video anomaly detection. Signal Image Video Process. 15(1), 215–222 (2021). https://doi.org/10.1007/s11760-020-01740-1
Zhang, J., et al.: Dnn-based prediction model for spatio-temporal data. SIGSPACIAL ’16. Association for Computing Machinery, New York (2016). https://doi.org/10.1145/2996913.2997016
Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: 31st AAAI Conference on Artificial Intelligence, AAAI 2017, pp. 1655–1661 (2017). arXiv:1610.00081
Wang, B., et al.: Deep Learning for Real Time Crime Forecasting, pp. 33–36 (2017). arXiv:1707.03340
Huang, C., et al.: MIST: a multiview and multimodal spatial-temporal learning framework for citywide abnormal event forecasting. WWW 2019, 717–728 (2019). https://doi.org/10.1145/3308558.3313730
Wang, B., Luo, X., Zhang, F., et al.: Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data (2018). arXiv:1804.00684
Sun, J., et al.: CrimeForecaster: Crime Prediction by Exploiting the Geographical Neighborhoods’ Spatiotemporal Dependencies. Lecture Notes in Computer Science 12461 LNAI, pp. 52–67 (2021). https://doi.org/10.1007/978-3-030-67670-4_4
Wang, C., Lin, Z., Yang, X., Sun, J., Yue, M., Shahabi, C.: HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting. arXiv:2109.12846 (2021)
Wu, Z., et al.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Jain, A., et al.: Structural-RNN: deep learning on spatio-temporal graphs. CVPR 2016-December, pp. 5308–5317 (2016). https://doi.org/10.1109/CVPR.2016.573
Salinas, D., et al.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36(3), 1181–1191 (2020). https://doi.org/10.1016/j.ijforecast.2019.07.001
Kullback, S.: Information Theory and Statistics. Dover Publications Inc., Mineola (1968)
Seo, Y., et al.: Structured Sequence Modeling with Graph Convolutional Recurrent Networks. Lecture Notes in Computer Science 11301 LNCS (2013), pp. 362–373 (2018). https://doi.org/10.1007/978-3-030-04167-0_33
Shi, X., et al.: Convolutional lstm Network: A Machine Learning Approach for Precipitation Nowcasting. NIPS’15, pp. 802–810. MIT Press, Cambridge (2015)
Department, C.I.P.: Chicago crimes, 2001–2018. Technical Report ICPSR37256-v1, Inter-university Consortium for Political and Social Research, Ann Arbor (2019). https://doi.org/10.3886/ICPSR37256.v1
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tekin, S.F., Kozat, S.S. Crime prediction with graph neural networks and multivariate normal distributions. SIViP 17, 1053–1059 (2023). https://doi.org/10.1007/s11760-022-02311-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-022-02311-2