Crime Hot Spot Forecasting: A Recurrent Model with Spatial and Temporal Information

Zhuang, Yun; Almeida, Matthew; Morabito, Melissa S.; Ding, Wei

doi:10.1109/icbk.2017.3

Cited by 48 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Percentages of all publications (n = 32) for describing basic information when reporting a spatial crime forecasting study. Blue: the item was properly defined; orange: the item was poorly defined or undefined the DeepCrime framework from Huang et al (2018), and the Long Short-Term Memory (LSTM) architecture proposed by Zhuang et al (2017). The paper by Huang et al (2018) even presents a neural architecture dedicated to a feature-independent approach, with a recurrent layer dedicated to encoding the temporal dependencies directly from the criminal occurrences.…”

Section: Algorithm Type Of Proposed Forecasting Methodsmentioning

confidence: 99%

“…An increasing body of forecasting techniques are based on DL, however, for this review, we include only three articles, with all of them for short-term prediction and coming from the computer science discipline (Huang et al 2018;Lin, Yen, and Yu 2018;Zhuang et al 2017). Two of the three articles consider geographic ancillary variables and apply the rolling-horizon validation strategy, while the third article deals only with crime lags following a 10-fold cross-validation approach.…”

Section: Algorithms and Validation Strategiesmentioning

confidence: 99%

“…All three articles consider a binary classification evaluated by metrics such as the PA and the F1-score. Zhuang et al (2017) propose a spatio-temporal neural network (STNN) for forecasting crime occurrences, while embedding spatial information. They then compare the STNN with three state-of-the-art methods, including the Recurrent Neural Network (RNN), the Long Short-Term Memory (LSTM), and the Gated Recurrent Unit (GRU).…”

Section: Algorithms and Validation Strategiesmentioning

confidence: 99%

See 2 more Smart Citations

A systematic review on spatial crime forecasting

et al. 2020

View full text Add to dashboard Cite

Background: Predictive policing and crime analytics with a spatiotemporal focus get increasing attention among a variety of scientific communities and are already being implemented as effective policing tools. The goal of this paper is to provide an overview and evaluation of the state of the art in spatial crime forecasting focusing on study design and technical aspects. Methods: We follow the PRISMA guidelines for reporting this systematic literature review and we analyse 32 papers from 2000 to 2018 that were selected from 786 papers that entered the screening phase and a total of 193 papers that went through the eligibility phase. The eligibility phase included several criteria that were grouped into: (a) the publication type, (b) relevance to research scope, and (c) study characteristics. Results: The most predominant type of forecasting inference is the hotspots (i.e. binary classification) method. Traditional machine learning methods were mostly used, but also kernel density estimation based approaches, and less frequently point process and deep learning approaches. The top measures of evaluation performance are the Prediction Accuracy, followed by the Prediction Accuracy Index, and the F1-Score. Finally, the most common validation approach was the train-test split while other approaches include the cross-validation, the leave one out, and the rolling horizon. Limitations: Current studies often lack a clear reporting of study experiments, feature engineering procedures, and are using inconsistent terminology to address similar problems. Conclusions: There is a remarkable growth in spatial crime forecasting studies as a result of interdisciplinary technical work done by scholars of various backgrounds. These studies address the societal need to understand and combat crime as well as the law enforcement interest in almost real-time prediction. Implications: Although we identified several opportunities and strengths there are also some weaknesses and threats for which we provide suggestions. Future studies should not neglect the juxtaposition of (existing) algorithms, of which the number is constantly increasing (we enlisted 66). To allow comparison and reproducibility of studies we outline the need for a protocol or standardization of spatial forecasting approaches and suggest the reporting of a study's key data items.

show abstract

Section: Algorithm Type Of Proposed Forecasting Methodsmentioning

confidence: 99%

Section: Algorithms and Validation Strategiesmentioning

confidence: 99%

Section: Algorithms and Validation Strategiesmentioning

confidence: 99%

See 1 more Smart Citation

A systematic review on spatial crime forecasting

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In ref. [ 80 ], the authors conducted research on forecasting crime hotspots. They used Google Tensor Flow to implement their model and evaluated three options for the recurrent neural network (RNN) architecture: accuracy, precision, and recall.…”

Section: Computer Vision Models Combined With Machine and Deep Learning Techniquesmentioning

confidence: 99%

Crime forecasting: a machine learning and computer vision approach to crime prediction and prevention

Shah¹,

Shah

2021

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

A crime is a deliberate act that can cause physical or psychological harm, as well as property damage or loss, and can lead to punishment by a state or other authority according to the severity of the crime. The number and forms of criminal activities are increasing at an alarming rate, forcing agencies to develop efficient methods to take preventive measures. In the current scenario of rapidly increasing crime, traditional crime-solving techniques are unable to deliver results, being slow paced and less efficient. Thus, if we can come up with ways to predict crime, in detail, before it occurs, or come up with a “machine” that can assist police officers, it would lift the burden of police and help in preventing crimes. To achieve this, we suggest including machine learning (ML) and computer vision algorithms and techniques. In this paper, we describe the results of certain cases where such approaches were used, and which motivated us to pursue further research in this field. The main reason for the change in crime detection and prevention lies in the before and after statistical observations of the authorities using such techniques. The sole purpose of this study is to determine how a combination of ML and computer vision can be used by law agencies or authorities to detect, prevent, and solve crimes at a much more accurate and faster rate. In summary, ML and computer vision techniques can bring about an evolution in law agencies.

show abstract

“…Mainly, cities with highly populated areas the risk of crime can increase. Over the last few years, several efforts have been made in the area of crime forecasting [91], [99], [116]. This question aims to present the most promising techniques reporting so far.…”

Section: ) Superior Spatio-temporal Crime Prediction Approaches (Rq2b)mentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

The primary objective of this study is to accumulate, summarize, and evaluate the state-ofthe-art for spatio-temporal crime hotspot detection and prediction techniques by conducting a systematic literature review (SLR). The authors were unable to find a comprehensive study on crime hotspot detection and prediction while conducting this SLR. Therefore, to the best of author's knowledge, this study is the premier attempt to critically analyze the existing literature along with presenting potential challenges faced by current crime hotspot detection and prediction systems. The SLR is conducted by thoroughly consulting top five scientific databases (such as IEEE, Science Direct, Springer, Scopus, and ACM), and synthesized 49 different studies on crime hotspot detection and prediction after critical review. 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 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 reliable; 4) the potential challenges faced by the state-of-the-art techniques and the future research directions. Moreover, the SLR aims to provide a core foundation for the research on spatio-temporal crime prediction applications while highlighting several challenges related to the accuracy of crime hotspot detection and prediction applications.

show abstract

Crime Hot Spot Forecasting: A Recurrent Model with Spatial and Temporal Information

Cited by 48 publications

References 10 publications

A systematic review on spatial crime forecasting

A systematic review on spatial crime forecasting

Crime forecasting: a machine learning and computer vision approach to crime prediction and prevention

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

Contact Info

Product

Resources

About