A Comparative Evaluation of Spatio Temporal Deep Learning Techniques for Crime Prediction

Matereke, Tawanda; Nyirenda, Clement N.; Ghaziasgar, Mehrdad

doi:10.1109/africon51333.2021.9570858

Cited by 11 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental showed the effectiveness of the deep learning algorithm. Matereke et al [66] compared three deep learning methods on the performance of the crime prediction, and they were deep multi view spatio-temporal network, spatio-temporal residual network, and the spatio-temporal dynamic network. The evaluation criteria were Mean absolute error, and the root mean square error.…”

Section: ) Methods Based On Convolution Networkmentioning

confidence: 99%

Crime Prediction Methods Based on Machine Learning: A Survey

Yin¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The objective of crime prediction, one of the most important technologies in social computing, is to extract useful information from many existing criminal records to predict the next process-related crime. It can aid the police in obtaining criminal information and warn the public to be vigilant in certain areas. With the rapid growth of big data, the Internet of Things, and other technologies, as well as the increasing use of artificial intelligence in forecasting models, crime prediction models based on deep learning techniques are accelerating. Therefore, it is necessary to classify the existing crime prediction algorithms and compare in depth the attributes and conditions that play an essential role in the analysis of crime prediction algorithms. Existing crime prediction methods can be roughly divided into two categories: those based on conventional machine learning and those based on contemporary deep learning. This survey analyses the fundamental theories and procedures. The most frequently used data sets are then enumerated, and the fundamental procedures of various algorithms are also analyzed in this paper. In light of the insufficient scale of existing data in this field, the ambiguity of data types used to predict crimes, and the absence of public data sets that have a significant impact on the research of algorithm models, this survey proposes the construction of a machine learning-based big data research model to address these issues. Future researchers who will enter this field are provided with a guide to the direction of future research development.

show abstract

Section: ) Methods Based On Convolution Networkmentioning

confidence: 99%

Crime Prediction Methods Based on Machine Learning: A Survey

Yin¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…However, more attention is paid to finegrained temporal units rather than fine-grained spatial units. Three deep learning architectures, such as ST-ResNet, DMVST-Net and STD-Net, were compared for the prediction of Chicago crime (Matereke et al, 2021). Hetero-ConvLSTM framework performed the prediction of traffic accidents and solved the problem of spatial heterogeneity (Yuan et al, 2018).…”

Section: Deep Learning Approachesmentioning

confidence: 99%

A Deep Neural Network for Spatiotemporal Prediction of Theft Crimes

Jing²,

Wang³

et al. 2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Accurate crime prediction plays an important role in public safety, providing technical guidance and decision support for the police and government departments. Due to the dynamics and imbalance of crime distribution, it is difficult to build predictive models for it. Specifically, the fine-grained and non-linear spatiotemporal dependencies of crime data cannot be captured accurately. In this paper, a neural network model ST-ACLCrime based on ConvLSTM and SE block was proposed to predict the number of theft crimes in hotspot areas. By overlaying ConvLSTM layers, fine-grained spatiotemporal dependencies are captured while preserving spatial location information. To further enhance the global channel feature representation, SE block is used to recalibrate the channel features and enhance the channel inter-dependencies. In addition, the closeness and the period components are set to dynamically capture the dependence of different time trends. We choose the city of Chicago as the study case, and use a multi-level spatial grid to divide the whole city area. The experimental results show that the proposed model exceeds all baseline model, such as HA, CNN, LSTM, CNN-LSTM and ConvLSTM. It was effectively capturing spatiotemporal dependence and improving prediction accuracy.

show abstract

“…To reliably forecast crime trends in particular cities, these algorithms have been trained using crime data that includes both geographical and temporal components. To better understand where crimes are most likely to occur and when they will occur, DL algorithms may be used to a variety of crime data sets, such as time, location, and kind [20].…”

Section: Introductionmentioning

confidence: 99%

A Systematic Review on the use of Machine Learning and Deep Learning Techniques for Crime Prediction from Social Media

2024

ijarcs

View full text Add to dashboard Cite

The goal of crime prediction is to help law enforcement authorities to prevent crimes before they happen by identifying and reducing potential future crimes. In present days, crime cases are rapidly occur so it is a challenging task to accurately predict and classify the future crimes, as criminal patterns are adaptable and constantly evolve, making it a challenging task. Sentiment analysis is essential for deciphering the feelings conveyed in text since social media has grown into a popular venue for individuals to communicate their thoughts, feelings, views, and comments. This analysis is particularly valuable for making informed decisions in business, politics and government agencies especially to identify crimes. However, it faces the difficulties like lexical diversity and dataset imbalance. In order to make better decisions and maybe lower the risk of predicting the suspects in a crime, early crime prediction has lately made use of Artificial Intelligence (AI) models like Deep Learning (DL) and Machine Learning (ML). When applied to crime data, ML and DL models may assist pinpoint possible crime hotspots and foretell when crimes may occur. Crime prediction and categorization using social media posts is covered in depth in this paper, which offers a comprehensive overview of several ML and DL frameworks. Initially, different ML and DL based crime prediction models designed by many researchers are examined in brief. The next step is to do a comparison research to learn about the shortcomings of those frameworks and provide an alternative method for effectively predicting crimes based on social media postings.

show abstract

A Comparative Evaluation of Spatio Temporal Deep Learning Techniques for Crime Prediction

Cited by 11 publications

References 19 publications

Crime Prediction Methods Based on Machine Learning: A Survey

Crime Prediction Methods Based on Machine Learning: A Survey

A Deep Neural Network for Spatiotemporal Prediction of Theft Crimes

A Systematic Review on the use of Machine Learning and Deep Learning Techniques for Crime Prediction from Social Media

Contact Info

Product

Resources

About