A SURVEY OF CRIME PREDICTION USING MACHINE LEARNING AND RECURRENT NEURAL NETWORKS

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Machine learning is used in different areas, like finance and business and even farming and government. One new way it is being used is to try to figure out where crimes might happen. Studies have shown that special computer programs can look at things like where a crime happened and when and use that to predict what kind of crime might happen next. Some new computer tools like TensorFlow and Keras have made it possible to use something called learning to predict crimes and this method is often better at predicting crimes than older methods of machine learning. Machine learning and deep learning are really good, at helping us understand crime patterns and predict activity.Recurrent Neural Networks are really good at figuring out time-series problems. This is because they can see how past and present crime events are connected to each other. This paper looks at a lot of studies that use intelligence to predict crime. It talks about what's good and what is bad about different algorithms. Recurrent Neural Networks with Long Short-Term Memory units are especially good because they can deal with problems like vanishing gradients. This helps them make predictions about crime. Recurrent Neural Networks are very useful, for this kind of thing.

References

1. [1] Ying-Lung Lin, Liang-Chih Yu, Tenge-Yang Chen: Using Machine Learning to Assist Crime Prevention. 6th IIAI International Congress on Advanced Applied Informatics, 2017.
2. [3] Ashwini B. Bais, Rajesh Babu, Jayant Adhikari: An Intelligent Analysis of Crime through Newspaper Articles – Clustering and Classification. International Journal on Recent and Innovation Trends in Computing and Communication Volume: 5 Issue: 2, 2017.
3. [2] Nishat Shama and Dr. Mahbub Alam Majumdar: A Machine Learning Approach to Predict Crime Using Time and Location Data, 2015.
4. [4] Yong Zhuang, Matthew Almeida, Melissa Morabito, and Wei Ding: Crime Hot Spot Forecasting: A Recurrent Model with Spatial and Temporal Information. IEEE International Conference on Big Knowledge, 2017.
5. [5] Amit Gupta, Ali Syed, Azeem Mohammad, Malka N.Halgamuge: A Comparative Study of Classification Algorithms using Data Mining: Crime and Accidents in Denver City the USA. (IJACSA) International Journal of Advanced Computer Science and Applications, 2016.
6. [6] Trung T. Nguyen, Amartya Hatua, and Andrew H. Sung: Building a Learning Machine Classifier with Inadequate Data for Crime Prediction. Journal of Advances in Information Technology Vol. 8, No. 2, May 2017.
7. [7] Panagiotis Stalidis, Theodoros Semertzidis and Petros Daras: Examining Deep Learning Architectures for Crime Classification and Prediction. IEEE, 2018.
8. [8] Hyeon-Woo Kang, Hang-Bong Kang: Prediction of crime occurrence from multimodal data using deep learning. PLoS ONE 12(4):https://doi.org/10.1371/journal.pone.0176244, 2017.
9. [9]Ying-Lung Lin, Meng-Feng Yen and Liang-Chih Yu: Grid-Based Crime Prediction Using Geographical Features. International Journal of Geo-Information, 2018.
10. [10] Luiz G.A. Alves, Haroldo V. Ribeiro, Francisco and A. Rodrigues: Crime prediction through urban metrics and statistical learning. ELSEVIER, 2018.ce on Services Computing (SCC), San Francisco, CA, 2016, pp. 459-466.

 

Keywords

------