Smart Police: A Hybrid Deep Learning Model for Crime Proactivity Assessment
Authors:
- 6 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Abstract
Conducting competent and precise investigations on criminal situations is necessary to establish peace, order, and justice in a community. With the increased use of modern sophisticated systems to track crime and violence, computer programmers may also significantly assist officials in law enforcement. Previous research was not successfully able to accomplish crime forecasting and precision of predictions made by learning models. This paper proposes CNN-LSTM hybrid approach for forecasting and predicting criminal behavior with improved accuracy. To understand the crimes data, the study uses different machine learning models such as Support Vector Machines, Naïve Bayes, k-Nearest Neighbors, Logistic Regression, Multilayer Perceptron’s (MLP), cloud gradient boosting (XGBoost), decision tree, random forests, time series analysis implementing a Convolutional Neural Network and (ARIMA) Autoregressive Integrated Moving Average and Long-Term Memory model and machine learning algorithm to improve error predictions. The demonstration of model was evaluated with various performance criteria. After extensive testing on real-time data, the CNN-LSTM model shows higher accuracy compared to existing models. Specifically, the model achieved 91% accuracy in the dataset of Denver and 90% in the Los Angeles dataset.Keywords
This publication has 25 references indexed in Scilit:
- Prediction of crime occurrence from multi-modal data using deep learningPLOS ONE, 2017
- Smart4Job: A Big Data Framework for Intelligent Job Offers Broadcasting Using Time Series Forecasting and Semantic ClassificationBig Data Research, 2017
- The Influence of Community Areas, Neighborhood Clusters, and Street Segments on the Spatial Variability of Violent Crime in ChicagoJournal of Quantitative Criminology, 2016
- Improving the Robustness and Accuracy of Crime Prediction with the Self-Exciting Point Process Through Isotropic TriggeringApplied Spatial Analysis and Policy, 2016
- Measurement of repeat effects in Chicago’s criminal social networkApplied Computing and Informatics, 2016
- Vulnerability and Exposure to Crime: Applying Risk Terrain Modeling to the Study of Assault in ChicagoApplied Spatial Analysis and Policy, 2015
- A Study on Performance Evaluation of Machine Learning Algorithms for Crime DatasetAdvanced Science and Technology Letters, 2014
- Predictive crime mappingPolice Practice and Research, 2014
- Self-Exciting Point Process Modeling of CrimeJournal of the American Statistical Association, 2011
- A Temporal Constraint Theory to Explain Opportunity-Based Spatial Offending PatternsJournal of Research in Crime and Delinquency, 2006