Abstract
There is relentless effort in combating the issue of crime in South Africa and many parts of the world. This challenge is heightened in under-resourced settings, where there is limited knowledge support, thus resulting in increasing negative perceptions of public safety. This work presents a predictive policing model as an addition to a burglar alarm system deployed in a community policing project to improve crime prevention performance. The proposed model uses feature-oriented data fusion method based on a deep learning crime prediction mechanism. Feed-Forward Neural Network (FFNN) and Recurrent Neural Network (RNN) models are employed to predict the amount of calls made to police stations on a monthly basis. Device installation and census data are used in the feature selection process to predict monthly calls to a police station. Coefficient of correlation function is used to isolate the relevant features for the analysis. To provide a viable way of achieving crime reduction targets, the models are implemented and tested on a real-life community policing network system called MeMeZa, which is currently deployed in low-income areas of South Africa. Furthermore, the model is evaluated using coefficient of determination function and the accuracy of the predictions assessed using an independent dataset that was not used in the models’ development. The proposed solution falls under the Machine Learning and AI applications in networks paradigm, and promises to promote smart policing in under-resourced settings.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
South African Government: Crime report. In South African police service annual crime report 2017/2018. https://www.gov.za/sites/default/files/gcis_document/201809/crime-stats201718.pdf. Accessed June 2020
Isafiade, O., Bagula, A.: Fostering smart city development in developing nations: a crime series data analytics approach. In: Proceedings of the ITU-Kaleidoscope: Challenges for a Data-Driven Society, pp. 89–95. IEEE, Nanjing, China (2017)
Du Plessis, A., Louw, A.: Crime prevention in South Africa: 10 Years After. Can. J. Criminol. Crim. Justice/La Revue canadienne de criminologie et de justice pénale 47(2), 1–20 (2005). https://doi.org/10.3138/cjccj.47.2.427
South African Police Service: Together squeezing crime to zero. J. Strateg. Plan 3(1), 3–21 (2014)
Isafiade, O., Bagula, A.: CitiSafe: adaptive spatial pattern knowledge using Fp-growth algorithm for crime situation recognition. In: Proceedings of the IEEE International Conference on Ubiquitous Intelligence and Computing (UIC-ATC), pp. 551–556, December 2013
National Development Plan 2030: Our Future - make it work, pp. 1–70. https://www.gov.za/sites/default/files/Executive%20Summary-NDP%202030%20-%20Our%20future%20-%20make%20it%20work.pdf. Accessed June 2020
Mohler, G.O., et al.: Randomized controlled field trials of predictive policing. J. Am. Stat. Assoc. 110(512) (2015)
MeMeZa crime prevention and community mobilisation project: Memeza shout crime prevention Diepsloot pilot results summary. http://memeza.co.za/wp-content/uploads/2016/05/Memeza-Diepsloot-Pilot-Report-2015.pdf. Accessed September 2018
Wilson, J.M., Weis, A.: Police staffing allocation and managing workload demand: a critical assessment of existing practices. J. Policing 8, 1–13 (2014). https://doi.org/10.1093/police/pau00. Advance Access-Oxford University Press
Isafiade, O., Bagula, A.: Data mining trends and applications in criminal science and investigations, pp. 1–386. IGI Global, USA (2016)
Kang, H.W., Kang, H.B.: Prediction of crime occurrence from multi-modal data using deep learning. J. PLOS-ONE 12(4), 1–19 (2017)
Mookiah, L., Eberle, W., Siraj, A.: Survey of crime analysis and prediction. In: The Twenty-Eighth International Flairs Conference, pp. 440–443 (2015)
Mohd Shamsuddin, N.H., Ali, N.A., Alwee, R.: An overview on crime prediction methods. In: Proceedings of the 6th ICT International Student Project Conference (ICT-ISPC), pp. 1–5, Malaysia (2017)
Wang, H., Kifer, D., Graif, C., Li, Z.: Crime rate inference with big data. In: Proceedings of the International Conference on Knowledge Discovery in Database, pp. 635–644. ACM (2016)
Isafiade, O., Bagula, A.: Series mining for public safety advancement in emerging smart cities. Future Gener. Comput. Syst. 108, 777–802 (2020)
Almanie, T., Mirza, R., Lor, E.: Crime prediction based on crime types and using spatial and temporal criminal hotspots. Int. J. Data Min. Knowl. Manage. Process (IJDKP) 54, 1–19 (2015)
Isafiade, O., Bagula, A., Berman, S.: A revised frequent pattern model for crime situation recognition based on floor-ceil quartile function. Procedia Comput. Sci. 15, 251–260 (2015)
Isafiade, O., Bagula, A., Berman, S.: On the use of Bayesian network in crime suspect modelling and legal decision support. In: Data Mining Trends and Applications in Criminal Science and Investigations, pp. 143–168, USA (2016)
Greenberg, D.: Time series analysis of crime rates. J. Quant. Criminol. 17(4), 291–327 (2001)
Flaxman, S., Chirico, M., Pereira, P., Loeffler, C.: Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ Real-Time Crime Forecasting Challenge. Mach. Learn. 13, 1–30 (2018). https://arxiv.org/abs/1801.02858
Isafiade, O., Bagula A: Efficient frequent pattern knowledge for crime situation recognition in developing countries. In: Proceedings of the 4th Annual Symposious on Computing for Development, pp. 1–2, ACM (2013)
Mcclendon, L., Meghanathan, N.: Using machine learning algorithms to analyze crime data. Mach. Learn. Appl. Int. J. (MLAIJ) 2(1), 1–12 (2015)
Almanie, T., Mirza, R., Lor, E.: Crime prediction based on crime types and using spatial and temporal criminal hotspots. Int. J. Data Min. Knowl. Manage. Process 5(4), 1–9 (2015)
Lin, Y.-L., Yen, M.-F., Yu, L.-C.: Grid-based crime prediction using geographical features. ISPRS Int. J. Geo Inf. 7(8), 298 (2018). https://doi.org/10.3390/ijgi7080298
Azeez, J., Aravindhar, D.J.: Hybrid approach to crime prediction using deep learning. In: Proceedings of the International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1701–1710. IEEE, Kochi (2015)
Stec, A., Klabjan, D.: Forecasting crime with deep learning. arXiv preprint arXiv:1806.01486l, pp. 1–20 (2018)
Zhang, Q., Yang, L.T., Chen, Z., Li, P.: A survey on deep learning for big data. J. Inf. Fusion 42, 146–157 (2018)
Acknowledgment
Authors gratefully appreciate resources made available by the MeMeZa foundation, South Africa.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Isafiade, O., Ndingindwayo, B., Bagula, A. (2021). Predictive Policing Using Deep Learning: A Community Policing Practical Case Study. In: Zitouni, R., Phokeer, A., Chavula, J., Elmokashfi, A., Gueye, A., Benamar, N. (eds) Towards new e-Infrastructure and e-Services for Developing Countries. AFRICOMM 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 361. Springer, Cham. https://doi.org/10.1007/978-3-030-70572-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-70572-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70571-8
Online ISBN: 978-3-030-70572-5
eBook Packages: Computer ScienceComputer Science (R0)