9,686 Hits in 5.2 sec

Deep Learning for Real Time Crime Forecasting [article]

Bao Wang, Duo Zhang, Duanhao Zhang, P.Jeffery Brantingham, Andrea L. Bertozzi
2017 arXiv   pre-print
Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors.  ...  In this work, we adapt the state-of-the-art deep learning spatio-temporal predictor, ST-ResNet [Zhang et al, AAAI, 2017], to collectively predict crime distribution over the Los Angeles area.  ...  The authors thank the Los Angeles Police Department for providing the crime data for this paper.  ... 
arXiv:1707.03340v1 fatcat:2vn7jp34fvhnzmddqfswuxwhku

Deep Learning for Real-Time Crime Forecasting and its Ternarization [article]

Bao Wang, Penghang Yin, Andrea L. Bertozzi, P. Jeffrey Brantingham, Stanley J. Osher, Jack Xin
2017 arXiv   pre-print
Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult.  ...  Finally, we present a ternarization technique to address the resource consumption issue for its deployment in real world.  ...  The authors thank the Los Angeles Police Department for providing the crime data for this paper.  ... 
arXiv:1711.08833v1 fatcat:zbps4gvod5ehrnzogfm2syvdhm

Automating Time Series Forecasting on Crime Data using RNN-LSTM

J Vimala Devi, K S Kavitha
2021 International Journal of Advanced Computer Science and Applications  
With the advent of advanced machine and deep learning algorithms, Time series analysis and building a forecasting model on crime data sets has become feasible.  ...  N-Beats Recurrent Neural Networks (RNN) are the proven ensemble models for time series forecasting.  ...  etc., So why not time series forecasting on crime data?  ... 
doi:10.14569/ijacsa.2021.0121051 fatcat:hghewbhm2vekzhyoidt3y5zdhy

Empirical Analysis for Crime Prediction and Forecasting Using Machine Learning and Deep Learning Techniques

Wajiha Safat, Soahail Asghar, Saira Andleeb Gillani
2021 IEEE Access  
This method illustrate a real-time crime model with an online k-mean type algorithm.  ...  Real-time crime forecasting is always critical; especially in unknown circumstances; when and where the next crime will happen remains difficult to predict accurately [42] .  ... 
doi:10.1109/access.2021.3078117 fatcat:lyn27akrjreprljivq6jqggy2a

A Survey on Societal Event Forecasting with Deep Learning [article]

Songgaojun Deng, Yue Ning
2021 arXiv   pre-print
Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems.  ...  This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions.  ...  The specially designed deep neural network takes advantage of the RNN's ability to learn time series patterns, capturing real-time interactions of each node to its connected neighbors.  ... 
arXiv:2112.06345v1 fatcat:jtdlo67bbbazhj6xea55h6bbqa

HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting [article]

Chenyu Wang, Zongyu Lin, Xiaochen Yang, Jiao Sun, Mingxuan Yue, Cyrus Shahabi
2021 arXiv   pre-print
Neural Network (GNN) techniques for crime forecasting, because the GNN techniques could effectively exploit the latent relationships between neighboring region nodes in the graph.  ...  The crime forecasting is an important problem as it greatly contributes to urban safety.  ...  The work was conducted while the author was intern at USC's IMSC. † This is the corresponding author. several spatiotemporal deep learning frameworks for crime forecasting, including MiST (Huang et al  ... 
arXiv:2109.12846v1 fatcat:2dhl3lhehnf5pki53wbtkbltk4

Crime Prediction and Analysis

Amshu S Gajendra, Aruna S, Malini R
2022 International Journal for Research in Applied Science and Engineering Technology  
Hence analyzing of crime helps in detecting the patterns and trends in crime. The real time crime predictions will be a helping hand to reduce crime rate.  ...  There arelaws that have been enforced to take preventive measures but there is a need for advanced approaches for protecting the society and the individuals in the society.  ...  The authors Wajiha Safat, Sohail Asghar, (Member, IEEE), and Saira Safat published Empirical Analysis for Crime Prediction and Forecasting Using Machine Learning and Deep Learning Techniques in 2021.  ... 
doi:10.22214/ijraset.2022.44218 fatcat:cvuwb37wpbcmfazajfdcrxxrl4

Spatio-Temporal Crime HotSpot Detection and Prediction: A Systematic Literature Review

Umair Muneer Butt, Sukumar Letchmunan, Fadratul Hafinaz Hassan, Mubashir Ali, Anees Baqir, Hafiz Husnain Raza Sherazi
2020 IEEE Access  
analysis techniques and deep learning techniques in crime trend prediction; 3) the inclusion of spatial and temporal information in crime datasets making the crime prediction systems more accurate and  ...  This study unfolds the following major aspects: 1) the impact of data mining and machine learning approaches, especially clustering techniques in crime hotspot detection; 2) the utility of time series  ...  Existing approaches for crime forecasting are divided into six different categories: Classical classification, deep learning-based, Clustering, Framework proposed, Regression techniques, and Time series  ... 
doi:10.1109/access.2020.3022808 fatcat:szzqvkh64fdypotz6xwnrmujhm

CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting [article]

Ali Mert Ertugrul, Yu-Ru Lin, Tugba Taskaya-Temizel
2020 arXiv   pre-print
To improve the overdose surveillance and to identify the areas in need of prevention effort, in this work, we focus on forecasting opioid overdose using real-time crime dynamics.  ...  Motivated by these observations, we propose a novel spatio-temporal predictive model for opioid overdose forecasting by leveraging the spatio-temporal patterns of crime incidents.  ...  opioid overdose using real-time crime data.  ... 
arXiv:1905.04714v4 fatcat:5zbmvexxfrgltjxnbvxzn5pcba

Crime Prediction with Graph Neural Networks and Multivariate Normal Distributions [article]

Selim Furkan Tekin, Suleyman Serdar Kozat
2021 arXiv   pre-print
Existing approaches to the crime prediction problem are unsuccessful in expressing the details since they assign the probability values to large regions.  ...  In each node of the graph, we learn a multivariate probability distribution from the extracted features of GCNs.  ...  We studied the problem of high-resolution crime forecasting with a new generative graph neural network architecture, HRCF.  ... 
arXiv:2111.14733v2 fatcat:nwyldtmfk5eczefp5s3qtahasi

Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data [article]

Bao Wang, Xiyang Luo, Fangbo Zhang, Baichuan Yuan, Andrea L. Bertozzi, P. Jeffrey Brantingham
2018 arXiv   pre-print
This novel deep neural network (DNN) incorporates the real time interactions of the graph nodes to enable more accurate real time forecasting.  ...  We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time.  ...  crime on a small spatial scale in real time.  ... 
arXiv:1804.00684v1 fatcat:fhfkdj423jgrdbteydh4o7mzbq

Theoretical and Empirical Analysis of Crime Data

Manisha Mudgal, Deepika Punj, Anuradha Pillai
2021 Journal of Web Engineering  
Most of the researches are currently working on forecasting the occurrence of future crime. There is a need for approaches that can work on real-time crime prediction at high speed and accuracy.  ...  In this paper, a model has been proposed that can work on real-time crime prediction by recognizing human actions.  ...  For solving these issues, there is a need of the auto-detection system. Many authors have proposed some real time crime activity detection systems.  ... 
doi:10.13052/jwe1540-9589.2016 fatcat:nqoxbqz5fvc3rlxpti6rkdnxfy

A Hybrid GCN and LSTM Structure Based on Attention Mechanism for Crime Prediction

Jinming Hu
2021 Converter  
A rolling forecast of crime data for about three years in the Boston of the United States shows that our model has good prediction performance.  ...  While at the same time, it has stimulated the development of crime method as frequent cross-border communication allowed.  ...  In 2017, Bao W et al. pioneered the use of deep learning for real time crime prediction, using a spatiotemporal deep learning model in their paper [15] .  ... 
doi:10.17762/converter.132 fatcat:nu2q3vviabcwdnihysy7zbtx7q

Deep Learning for Spatio-Temporal Data Mining: A Survey [article]

Senzhang Wang, Jiannong Cao, Philip S. Yu
2019 arXiv   pre-print
Then a framework is introduced to show a general pipeline of the utilization of deep learning models for STDM.  ...  In this paper, we provide a comprehensive survey on recent progress in applying deep learning techniques for STDM.  ...  A real-time crowd flow forecasting system called UrbanFlow is built, and the crowd flow spatial maps are as its input.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

Artificial Intelligence, Predictive Policing, and Risk Assessment for Law Enforcement

Richard A. Berk
2020 annual review of criminology  
Its use in predictive policing to forecast crimes in time and space is largely an exercise in spatial statistics that in principle can make policing more effective and more surgical.  ...  Its use in criminal justice risk assessment to forecast who will commit crimes is largely an exercise in adaptive, nonparametric regression.  ...  Tchetgen, Ed George, Linda Zhao, and Arun Kuchibhotla for hours of technical instruction.  ... 
doi:10.1146/annurev-criminol-051520-012342 fatcat:xkyi5i5wbzf5zmni3j57e2mol4
« Previous Showing results 1 — 15 out of 9,686 results