Crime prediction using patterns and context

Baloian, Nelson; Bassaletti, Col. Enrique; Fernández, Mario Rodríguez; Figueroa, Oscar; Fuentes, Paz Soto; Manásevich, Raúl; Orchard, Marcos E.; Peñafiel, Sergio; Pino, José A.; Vergara, Marcos

doi:10.1109/cscwd.2017.8066662

Cited by 17 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using data mining and statistical techniques, new algorithms and systems have been developed along with new types of data. For instance, classification and statistical models are applied for mining of crime patterns and crime prediction [17], [18], where transfer learning has been employed to exploit spatio-temporal patterns in New York city [19]. Wu et al [20] developed a system to automatically collect crime-logged data for mining of crime patterns, in order to achieve more effective crime prevention in/around a university campus.…”

Section: B Crime Data Mining Visualization and Trends Forecastingmentioning

confidence: 99%

Big Data Analytics and Mining for Effective Visualization and Trends Forecasting of Crime Data

et al. 2019

View full text Add to dashboard Cite

Big data analytics (BDA) is a systematic approach for analyzing and identifying different patterns, relations, and trends within a large volume of data. In this paper, we apply BDA to criminal data where exploratory data analysis is conducted for visualization and trends prediction. Several the state-of-theart data mining and deep learning techniques are used. Following statistical analysis and visualization, some interesting facts and patterns are discovered from criminal data in San Francisco, Chicago, and Philadelphia. The predictive results show that the Prophet model and Keras stateful LSTM perform better than neural network models, where the optimal size of the training data is found to be three years. These promising outcomes will benefit for police departments and law enforcement organizations to better understand crime issues and provide insights that will enable them to track activities, predict the likelihood of incidents, effectively deploy resources and optimize the decision making process. INDEX TERMS Big data analytics (BDA), data mining, data visualization, neural network, time series forecasting.

show abstract

Section: B Crime Data Mining Visualization and Trends Forecastingmentioning

confidence: 99%

Big Data Analytics and Mining for Effective Visualization and Trends Forecasting of Crime Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Similarly, output gate controls the extent to which the value in the cell is used to compute the outcome activation of the LSTM unit. The activation function is represented using the logistic sigmoid function [13,18].…”

Section: Methodsmentioning

confidence: 99%

Crime Data Analysis, Visualization and Prediction Using LSTM

Manengadan¹,

Nandanan²,

Subash³

2021

IJDSA

View full text Add to dashboard Cite

Crimes are common social problems that can even affect the quality of life, even the economic growth of a country. Big Data Analytics (BDA) is used for analyzing and identifying different crime patterns, their relations, and the trends within a large amount of crime data. Here, BDA is applied to criminal data in which, data analysis is conducted for the purpose of visualization. Big data analytics and visualization techniques were utilized to analyze crime big data within the different parts of India. Here, we have taken all the states of Indian for analysis, visualization and prediction. The series of operations performed are data collection, data pre-processing, visualization and trends prediction, in which LSTM model is used. The data includes different cases of crimes with in different years and the crimes such as crime against women and children in which, kidnap, murder, rape. The predictive results show that the LSTM perform better than neural network models. Hence, the generated outcomes will benefit for police and law enforcement organizations to clearly understand crime issues and that will help them to track activities, predict the similar incidents, and optimize the decision making process.

show abstract

“…For example, Game Theoretic approaches have been used to understand criminal behaviour ( [13], [43], [34], [1]); dynamical systems for the evolution of criminal behaviour ( [37], [46], [28]); and novel reaction-diffusion systems have explored the emergence of spatial heterogeneity in criminal activity ( [12], [42], [41], [30], [17], [33] ). There is also an extensive literature that uses statistical modelling approaches to understand crime data ( [44], [27], [4]) or agent based modelling to consider individuallevel behaviour and/or activity ( [10], [45], [31], [3]). In 2016, a special issue of the European Journal of Applied Mathematics was devoted to mathematical modelling of crime and security ( [6]), further identifying the potential for mathematics to help our understanding of the complexity of criminal activity and behaviours.…”

Section: Introductionmentioning

confidence: 99%

Towards understanding crime dynamics in a heterogeneous environment: A mathematical approach

White

Campillo-Funollet

Nyabadza

et al. 2021

Journal of Interdisciplinary Mathematics

View full text Add to dashboard Cite

Crime data provides information on the nature and location of the crime but, in general, does not include information on the number of criminals operating in a region. By contrast, many approaches to crime reduction necessarily involve working with criminals or individuals at risk of engaging in criminal activity and so the dynamics of the criminal population is important. With this in mind, we develop a mechanistic, mathematical model which combines the number of crimes and number of criminals to create a dynamical system. Analysis of the model highlights a threshold for criminal efficiency, below which criminal numbers will settle to an equilibrium level that can be exploited to reduce crime through prevention. This efficiency measure arises from the initiation of new criminals in response to observation of criminal activity; other initiation routes -via opportunism or peer pressure -do not exhibit such thresholds although they do impact on the level of criminal activity observed. We used data from Cape Town, South Africa, to obtain parameter estimates and predicted that the number of criminals in the region is tending towards an equilibrium point but in a heterogeneous manner -a drop in the number of criminals from low crime neighbourhoods is being offset by an increase from high crime neighbourhoods.

show abstract

Crime prediction using patterns and context

Cited by 17 publications

References 14 publications

Big Data Analytics and Mining for Effective Visualization and Trends Forecasting of Crime Data

Big Data Analytics and Mining for Effective Visualization and Trends Forecasting of Crime Data

Crime Data Analysis, Visualization and Prediction Using LSTM

Towards understanding crime dynamics in a heterogeneous environment: A mathematical approach

Contact Info

Product

Resources

About