Crime Hot Spots Research Articles

Spatial distribution of crimes in urban areas: An insight from Sri Lanka

Similar to other Asian countries, it is forecasted that the urban population in Sri Lanka will continue to increase at an accelerating rate and the majority will be living in urban areas by 2022. Urban crime which is a major challenge that cities face is assumed to spread with the increasing population. They are clustered geographically generating a substantial economic struggle. The related theories argue that criminal opportunity is the root cause of crime and physical environmental design makes an influence on the criminal opportunity. Therefore, a need of identifying how the built environment and different land uses become an opportunity and make an impact on the spatial distribution of urban crimes is evident. This study aims to do a hotspot analysis within the Colombo Municipal Council Area, Sri Lanka to identify the spatial relationship of urban crimes with different land uses. The data on 627 crime incidents occurred in 2018 were obtained from crime records of police stations in Colombo North, South and Central police divisions and were analyzed using Kernel Density Estimation in Geographical Information Systems (GIS) software. As per study findings, seven wards were identified as crime hotspots. Further, findings reveal that robbery and drug arrest incidents are common around low-income residential housing areas while property theft records are common around hospitals, cinemas and concentrated commercial areas. Vehicle thefts are often recorded near lakes, offices and playgrounds whereas housebreakings are recorded near housing schemes. Finally, implications to mitigate these impacts were also presented. Keywords: crime types, GIS, land use, spatial distribution, Sri Lanka, urban crime

Crime hotspot prediction based on dynamic spatial analysis

Crime is not a completely random event but rather shows a pattern in space and time. Capturing the dynamic nature of crime patterns is a challenging task. Crime prediction models that rely only on neighborhood influence and demographic features might not be able to capture the dynamics of crime patterns, as demographic data collection does not occur frequently and is static. This work proposes a novel approach for crime count and hotspot prediction to capture the dynamic nature of crime patterns using taxi data along with historical crime and demographic data. The proposed approach predicts crime events in spatial units and classifies each of them into a hotspot category based on the number of crime events. Four models are proposed, which consider different covariates to select a set of independent variables. The experimental results show that the proposed combined subset model (CSM), in which static and dynamic aspects of crime are combined by employing the taxi dataset, is more accurate than the other models presented in this study.

SAFE

Kernel density visualization (KDV) has been the de facto method in many spatial analysis tasks, including ecological modeling, crime hotspot detection, traffic accident hotspot detection, and disease outbreak detection. In these tasks, domain experts usually generate multiple KDVs with different bandwidth values. However, generating a single KDV, let alone multiple KDVs, is time-consuming. In this paper, we develop a share-and-aggregate framework, namely SAFE, to reduce the time complexity of generating multiple KDVs given a set of bandwidth values. On the other hand, domain experts can specify bandwidth values on the fly. To tackle this issue, we further extend SAFE and develop the exact method SAFE all and the 2-approximation method SAFE exp which reduce the time complexity under this setting. Experimental results on four large-scale datasets (up to 4.33M data points) show that these three methods achieve at least one-order-of-magnitude speedup for generating multiple KDVs in most of the cases without degrading the visualization quality.

Checkpoint urbanism: Violent infrastructures and border stigmas in the Juárez border region

As Popitz (2017) argues, violence is one component of the great economy of world history, an option permanently open to human activity. In Ciudad Juárez, right at the border between the United States and Mexico, this notion explains the fundamental incongruity that characterises the region: a booming industrial productive model operating in parallel with an international crime and violence hotspot that is also a coveted criminal passageway. This paper will argue that official and criminal checkpoints designed for border-crossing, have had a transformative spatial role when considered across the dimensions of infrastructure and stigma, triggering a material/symbolic tension. We argue that their location and accessibility determine the exposure of nearby communities to economic growth but also violent entrepreneurship – the illegal crossing of goods and people still remains a constant characteristic of the region, not only as part of a criminal enterprise but as a viable livelihood. The ways in which the region of Juárez develops and grows also determines how trafficking and illegal practices are established; rules and regulations that provide territorial parameters for what is open and transparent are equally referential to what is clandestine and devious. The tensions brought by the border’s geopolitical value have amplified the value of infrastructure and its practical ownership. The international border operates as a line that is barrier, social divider, landmark, policy-bridge, filtering mechanism and trafficking obstacle. Under this permanent state of tension, the checkpoints provide a physical structure to the transit flows and a sovereign interruption. Across this urbanism, the checkpoint surroundings acquire a magnetic significance, due to the resulting transit dynamics and the surveillance deterrents at the core of their function. Furthermore, their dual nature – official and criminal – has branded the region as a criminal outpost, stigmatising the people inhabiting it, and perpetuating the idea that Juárez is defined by its violent infrastructures.

Prediction of crime rate in urban neighborhoods based on machine learning

As the impact of crime on the lives of residents has increased, there are a number of methods for predicting where crime will occur. They tend to explore only the association established between a single factor and the distribution of crime. In order to more accurately and quickly visualize and predict crime distribution in different neighborhoods, and to provide a basis for security planning and design by planning designers, this paper uses GAN neural networks to build a prediction model of city floor plans and corresponding crime distribution maps. We take Philadelphia as the research sample, use more than 2 million crime information of Philadelphia from 2006 to 2018 to draw the crime hotspot distribution map, and collect the corresponding map of Philadelphia, and train the model for predicting the crime rate of the city with more than two thousand sets of one-to-one corresponding images as the training set. When the training is complete, a floor plan can be fed directly to the model, and the model will immediately feed back a hotspot map reflecting the crime distribution. Using the untrained Philadelphia data as the test set, the model can accurately predict crime concentration areas and the predicted crime concentration areas are similar to the concentration areas considered in previous studies. With the feedback from the model, the city layout can be adjusted and the crime rate can be greatly reduced when the simulated city planner tunes into the city plan. In addition the ideas in this paper can be applied as a set of methodologies to predict other relevant urban characteristic parameters and visualize them.

Malignant mixes: The overlap of motor vehicle crashes and crime in Stockholm, Sweden

Places that concentrate both motor vehicle crashes and crime in Stockholm, Sweden were examined for common socio-economic, land use, and neighborhood characteristics. Using vehicle crash (N = 3,700) and non-traffic crime (N = 605,052) data from 2016 to 2018, hot spots of these two sets of events and their overlap were identified. Crash hot spots captured 14% of the crashes in only 0.5% of Stockholm’s area while crime hot spots captured 27% of the recorded offences in less than 1% of the area. There was overlap in these hot spots for 7% of the crashes and 10% of the crimes. To model predictors, the events were allocated to roadway segments (N = 5511) and tested using a Poisson-Gamma-CAR spatial regression model. Both crashes and crimes exhibit a clear center-periphery pattern that varies over time and by type of crashes and crimes.Crashes tended to occur on roadways with higher average daily traffic (ADT) while crimes tend to occur on roadways with lower ADT with around half occurring on residential streets. Both types of incidents tended to be higher in lower income neighborhoods. Land uses common to both types of harm were the location of underground stations, ATM machines, and alcohol-serving businesses. These are places where people and cars converge at particular times. The effect of these events on police, emergency, and medical services is discussed.

Improving the Creation of Hot Spot Policing Patrol Routes: Comparing Cognitive Heuristic Performance to an Automated Spatial Computation Approach

Hot spot policing involves the deployment of police patrols to places where high levels of crime have previously concentrated. The creation of patrol routes in these hot spots is mainly a manual process that involves using the results from an analysis of spatial patterns of crime to identify the areas and draw the routes that police officers are required to patrol. In this article we introduce a computational approach for automating the creation of hot spot policing patrol routes. The computational techniques we introduce created patrol routes that covered areas of higher levels of crime than an equivalent manual approach for creating hot spot policing patrol routes, and were more efficient in how they covered crime hot spots. Although the evidence on hot spot policing interventions shows they are effective in decreasing crime, the findings from the current research suggest that the impact of these interventions can potentially be greater when using the computational approaches that we introduce for creating hot spot policing patrol routes.

Are trees and shrubs unsafe hiding places? Impact of plant forms on the perception of danger in urban green spaces in crime hot spots

Urban parks and forests are important for wellbeing, but feelings of unsafety limited their usage. Removal of vegetation from hotspots of fear is sometimes recommended as a means of boosting safety. However such actions should be approached with caution. One explanation, based on prospect-refuge theory, is that plants increase perceptions of danger because of their contribution to a setting’s effectiveness in concealing criminals. It is also believed that people do not like urban green spaces parks containing trees and shrubs that can act as hiding places because of the sense of danger that this vegetation evokes. To test this explanation, participants rated 57 photos of urban parks and forest parks settings park settings on perceived danger, effectiveness of concealment, and landscape preference. In addition, the effectiveness of concealment in the photos was measured assuming that the value of this variable is expressed by the percentage of the pixels occupied by trees and shrubs offering concealment in a photograph. Results confirmed that concealment and danger are highly correlated mediation analysis confirmed that the impact of concealment on preferences can be explained by perceived danger. When the danger was controlled, the efficiency of concealment had no influence on preferences.

The impact of plants offering cover on female students’ perception of danger in urban green spaces in crime hot spots

Urban parks and forests are important for wellbeing, but feelings of unsafety limited their usage. Removal of vegetation from hotspots of fear is sometimes recommended as a means of boosting safety. However such actions should be approached with caution. One explanation, based on prospect-refuge theory, is that plants increase perceptions of danger because of their contribution to a setting’s effectiveness in concealing criminals. It is also believed that people do not like urban green spaces parks containing trees and shrubs that can act as hiding places because of the sense of danger that this vegetation evokes. To test this explanation, participants rated 57 photos of urban parks and forest parks settings park settings on perceived danger, effectiveness of concealment, and landscape preference. In addition, the effectiveness of concealment in the photos was measured assuming that the value of this variable is expressed by the percentage of the pixels occupied by trees and shrubs offering concealment in a photograph. Results confirmed that concealment and danger are highly correlated mediation analysis confirmed that the impact of concealment on preferences can be explained by perceived danger. When the danger was controlled, the efficiency of concealment had no influence on preferences.

Crime Risk Stations: Examining Spatiotemporal Influence of Urban Features through Distance-Aware Risk Signal Functions

Static indicators may fail to capture spatiotemporal differences in the spatial influence of urban features on different crime types. In this study, with a base station analogy, we introduced crime risk stations that conceptualize the spatial influence of urban features as crime risk signals broadcasted throughout a coverage area. We operationalized these risk signals with two novel risk scores, risk strength and risk intensity, obtained from novel distance-aware risk signal functions. With a crime-specific spatiotemporal approach, through a spatiotemporal influence analysis we examined and compared these risk scores for different crime types across various spatiotemporal models. Using a correlation analysis, we examined their relationships with concentrated disadvantage. The results showed that bus stops had relatively lower risk intensity, but higher risk strength, while fast-food restaurants had a higher risk intensity, but a lower risk strength. The correlation analysis identified elevated risk intensity and strength around gas stations in disadvantaged areas during late-night hours and weekends. The results provided empirical evidence for a dynamic spatial influence that changes across space, time, and crime type. The proposed risk functions and risk scores could help in the creation of spatiotemporal crime hotspot maps across cities by accurately quantifying crime risk around urban features.

Examining the Modeling Framework of Crime Hotspot Models in Predictive Policing

Predictive policing has its roots in crime hotspot modeling. In this paper we give an example of what goes into mathematical crime hotspot modeling and show that the modeling assumptions perpetuate systemic racism in policing. The goal of this paper is to raise objections to this field of research, not on its mathematical merit, but on the scope of the problem formation. We do not make any suggestions about how to incorporate race into predictive policing models in order to make them less biased.

KDV-explorer

Kernel density visualization (KDV) is a commonly used visualization tool for many spatial analysis tasks, including disease outbreak detection, crime hotspot detection, and traffic accident hotspot detection. Although the most popular geographical information systems, e.g., QGIS, and ArcGIS, can also support this operation, these solutions are not scalable to generate a single KDV for datasets with million-scale data points, let alone to support exploratory operations (e.g., zoom in, zoom out, and panning operations) with KDV in near real-time (< 5 sec). In this demonstration, we develop a near real-time visualization system, called KDV-Explorer, that is built on top of our prior study on the efficient kernel density computation. Participants will be invited to conduct some kernel density analysis on three large-scale datasets (up to 1.3 million data points), including the traffic accident dataset, crime dataset and COVID-19 dataset. We will also compare the performance of our solution and the solutions in QGIS and ArcGIS.

Do license plate readers enhance the initial and residual deterrent effects of police patrol? A quasi-randomized test

To determine whether the use and display of license plate readers (LPRs) enhance the crime prevention effects of police patrol, particularly by increasing initial and residual deterrence from patrol presence. Crime hot spots in a large suburban jurisdiction were randomly assigned to receive intermittent patrols (15–30 min each) by officers with or without LPRs on their vehicles for 4.5 months. Data on 785 patrols at 33 hot spots were used to compare initial and residual outcomes of LPR and non-LPR patrols. Outcomes analyzed for each patrol visit via chi-square tests, survival analyses, and/or logistic regression included the following: the likelihood of a vehicle recovery or arrest; the likelihood of a new crime or disorder call in the location while the officer was present (measuring initial deterrence); time until a new crime or disorder call following the officer’s departure (measuring residual deterrence); and first type of call (crime or disorder) following the officer’s departure (measuring residual deterrence). LPR use increased stolen vehicle recoveries but not arrests. LPR use did not reduce the likelihood of a new call in the hot spot while an officer was present, nor did it affect the timing or seriousness of the next call following a patrol. This study provides little clear evidence for the crime prevention efficacy of using LPRs in general patrol, which is a common practice in the USA. Police and researchers should give more attention to testing the relative benefits of different LPR uses and modes of deployment.

Resources Package Modelling Supporting Border Surveillance Operations

The purpose of this work is to propose a military planning tool capable of providing logistical bases and patrol packages to most effectively support border surveillance. Presently, military patrols are employed along geographical borders to combat transnational crimes; acts such as drug trafficking, smuggling of goods and illegal natural resources exploitation. The patrols make temporary stops within specific time windows at specific places characterised by a high incidence of crime (hotspots). These hotspots have different criticalities within given time windows. To optimise the results, the proposed model allows additional stops in more critical hotspots. It achieves this using a mathematical optimisation model. Considering that there are not adequate logistical-military capacities (logistical bases and patrols) at all needed locations, developing a border surveillance plan that optimises resource use is imperative. The model was run using black hole-based optimisation and a real patrol mission’s database to ensure timely solutions. The solutions were then evaluated in terms of quality (number of bases and patrols, coverage efforts, and travel time) and computational processing time. Next, they were compared with solutions using the traditional method, thereby demonstrating the model’s robustness in providing timely surveillance schemes that ensure high coverage with minimum resources.

Citizenguard: A Watchdog for Unsafe-Area Detection to Increase the Safety of Citizens

Increasing numbers of crime cases over the years in Mumbai have caused concerns on the safety of citizens living in Mumbai City. There are some areas which can be called as a crime hotspot and the citizens can be roaming in such areas with no idea about how much danger they are in. To curb this problem there should be a solution feasible and accessible to each person. The proposed system may serve as a crime deterrent to increase security that enables the user to be notified in various ways and may transform their mobile devices into smart personal emergency phones. The proposed system gives valuable information on crime prone areas in a densely populated city. The proposed project can be summarized as a safety app for citizens of Mumbai, or tourists travelling from other states or countries. The project can assist these users by providing Risk alert notification, Nearby police stations, Nearby Hospitals, Emergency panic button and Emergency helpline contact numbers. With the help of these features it makes it easy for the citizens and tourists to be aware of any danger they might be in.

The relationship between density of drug outlets, crime hot spots and family factors on the consumption of drugs and delinquent behaviour of male adolescent Mexican students

This study examined the relationship between community risk factors (drug outlets density and crime hot spots) and family factors on the risk behaviours (drugs consumption and delinquent behaviour) of male adolescent Mexican students. Results were obtained based on data bank analysis and direct collection of information regarding family factors and risk behaviours of adolescents attending school. Spatial and statistical analysis was performed. The final sample was composed of 1450 male adolescents, from 11 secondary and high schools located in marginal and violent areas of Mexico. Spatial analysis revealed that when considering only the prevalence of the risk behaviours of the adolescents, the area of highest risk was the northwestern area of the city. However, after performing conjunct analysis of all evaluated variables using density point risk (aside from confirming that the northwestern area is still the one with the greatest risk), results indicated that the southern area has a high-density point risk. All densities of the variables showed a statistically significant positive association (p < 0.05). However, the results of the structural equation model indicated than only the family factors influenced the risk behaviours of adolescents (p < 0.05). The spatial distribution of the risk behaviours in male adolescent students and community risk variables surrounding the area where schools are located allows for the description of patterns and hotspot detection that facilitate the prioritization of where interventions must be directed. Besides, the interventions should target family factors.

Fast augmentation algorithms for network kernel density visualization

Network kernel density visualization, or NKDV, has been extensively used to visualize spatial data points in various domains, including traffic accident hotspot detection, crime hotspot detection, disease outbreak detection, and business and urban planning. Due to a wide range of applications for NKDV, some geographical software, e.g., ArcGIS, can also support this operation. However, computing NKDV is very time-consuming. Although NKDV has been used for more than a decade in different domains, existing algorithms are not scalable to million-sized datasets. To address this issue, we propose three efficient methods in this paper, namely aggregate distance augmentation (ADA), interval augmentation (IA), and hybrid augmentation (HA), which can significantly reduce the time complexity for computing NKDV. In our experiments, ADA, IA and HA can achieve at least 5x to 10x speedup, compared with the state-of-the-art solutions.

The Indianapolis harmspot policing experiment

PurposeThis 100-day experiment explored the impact of a dynamic place-based policing strategy on social harm in Indianapolis. Scholars have recently called for place-based policing to consider the co-occurrence of substance abuse and mental health problems that correlate within crime hot spots. Moreover, severity is not ubiquitous across harmful events and should thus be weighted accordingly. MethodsHarmspots and hotspots were operationalized for this experiment and both received proactive police activities. Evaluation analyses includes multivariate point processes and hawkes processes to determine experimental effects. Survey data was collected via telephone surveys, was weighted for demographic representativeness, and analyzed using Poisson regression. ResultsResults indicate proactive policing in dynamic harmspots can reduce aggregated social harm. No statistical deterrence effect was observed in crime hotspots. Proactive police activity in harmspots was associated with higher arrest rates, though not disproportionate across race and ethnicity, nor was there an effect on incidents of use of force. A two-wave pre/post community survey indicated Indianapolis citizens believe data-driven policing to be useful, though perceptions vary across demographic groups with moderate trust around computer algorithms. ConclusionPlace-based policing strategies should consider social harm events as a method to operationalize proactive policing. Observed effects are consistent with those of hotspots policing while enabling cities to broaden the set of harms experienced by varying communities. Harmspot policing may also position municipalities to maximize social service delivery at places beyond policing.

Gang-related crime in Los Angeles remained stable following COVID-19 social distancing orders.

Research SummaryThe onset of extreme social distancing measures is expected to have a dramatic impact on crime. Here, we examine the impact of mandated, city‐wide social distancing orders aimed at limiting the spread of COVID‐19 on gang‐related crime in Los Angeles. We hypothesize that the unique subcultural processes surrounding gangs may supersede calls to shelter in place and allow gang‐related crime to persist. If the normal guardianship of people and property is also disrupted by social distancing, then we expect gang violence to increase. Using autoregressive time series models, we show that gang‐related crime remained stable and crime hot spots largely stationary following the onset of shelter in place.Policy ImplicationsIn responding to disruptions to social and economic life on the scale of the present pandemic, both police and civilian organizations need to anticipate continued demand, all while managing potential reductions to workforce. Police are faced with this challenge across a wide array of crime types. Civilian interventionists tasked with responding to gang‐related crime need to be prepared for continued peacekeeping and violence interruption activities, but also an expansion of responsibilities to deal with “frontline” or “street‐level” management of public health needs.

Measuring hot spots policing in non-research settings

Hot spots policing has become a robust evidence-based strategy to address the problem of crime in U.S. cities. Today, a growing number of police departments report that they use hot spots policing to some extent in their daily operations. However, to our knowledge, only one study has been conducted to determine whether police departments have implement the strategy effectively. In our study, we used crime and stop-question-and-frisk (SQF) data from the New York Police Department (NYPD) and an innovative analytical strategy to assess (1) whether the NYPD makes significant use of hot spots policing, and (2) if yes, how much hot spots policing the department performs. Our findings showed that the NYPD uses hot spots policing in about 40%–45% of its violent crime hot spots. The implications of the study are discussed.