Sara Haghbayan; Behnam Tashayo; Mehdi Momeni
Abstract
Extended Abstract
Introduction
Today, one of the most complex issues in most countries is the high crime rate and the increase in social anomalies in them. One of these anomalies is residential burglary, which is one of the most widespread crimes in most countries of the world. Because spatial and ...
Read More
Extended Abstract
Introduction
Today, one of the most complex issues in most countries is the high crime rate and the increase in social anomalies in them. One of these anomalies is residential burglary, which is one of the most widespread crimes in most countries of the world. Because spatial and time play a very important and undeniable role in the formation of hot crime spots such as residential burglary therefore, by identifying the spatial and temporal of hot crime spots can be largely prevented. Previous studies have focused more on identifying and analyzing spatial crime hotspots and performing temporal analysis of crimes independently of spatial crime hotspots. However, in order to prevent the occurrence of these crimes in the future, a combination of time and spatial hot crime spots is needed to provide a more complete and accurate analysis. The aim of this study is to provide a systematic method for combining spatial and temporal information of residential burglary. The proposed method is based on spatial analysis and allows investigating the temporal distribution of events in hot crime spots. For this purpose, GIS capabilities have been used to perform statistical and graphical tests to identify and display crime hotspots. The results showed that hotspots follow a spatially clustered and temporally focused pattern. The research findings showed that the highest frequency of burglary is in hot spot No.4 in 2016 August, on Wednesday at 8 am, and the lowest frequency of burglary is in hot spot No.1 in 2018 January, on Sunday at 4 am.
Materials & Methods
The statistical tests used in this study include mean center, standard deviation ellipse test for clustering. The first step in identifying crime hotspots is to use the tests for clustering. For this purpose, in this study, the method of the average nearest neighbor is used. The results of residential burglary test for clustering showed that this crime is a cluster pattern in the study area. After proving to be clustered, graphical methods including point map display and kernel density have been used to display the hot crime spots. The results of the kernel density test cause to the identification and display of four spatial the hot crime spots in the study area.
The data used in this research include information on the time, place and type of crimes in the years 2015, 2016, 2017, 2018. The total number of crimes is 319073, of which 5573 were related to residential burglary, which was used as a statistical population in this study.
Results & Discussion
Statistical analysis was performed over a period of four years, which is equivalent to 48 months and 35064 around the clock for each hot crime spot. The results show that the highest incidence of crime in hot spot No.4 is equivalent to 1172 cases of residential burglary, which of all these four hot spot has a smaller area equivalent to 1117 hectares. Temporal analyzes of hot crime spots were performed annually, monthly, weekly and hourly. The results of the annual analysis of all four hot spots show that the highest rate of residential burglary is in 2016 and the lowest rate is in 2018.
The findings of this study show that the combination of spatial and temporal of hot crime spots analysis lump-sum by temporal analysis regardless of the spatial hot spots in monthly, daily and hourly intervals is significantly different. The combination of spatial and temporal of hot crime spots in the monthly interval shows that the maximum and minimum rates of residential burglary per month are different in these four hot spots. The highest number of residential burglary respectively occurred in hot spot No. 1 in October, in hot spot No. 2 in August, in hot spot No. 3 in June and in hot spot No. 4 in August. However, the results of the statistical analysis of time without considering the spatial hot crime spots show that August is the highest and April is the lowest. Daily statistical analysis shows that the highest number of residential burglary occurs in hot spot No. 1 and hot spot No. 3 on Friday, while in hot spot No. 2 it is Thursday and in hot spot No. 4 it is Wednesday. This analysis is different with a general daily analysis that shows Friday as the highest number of occurrences. Hourly analysis also shows that the peak of residential burglary in all four centers is at different hours; Thus, the peak of residential burglary areas in the study area is in the hot spot No. 1 hour 22, in the hot spot No. 2 hours 17, in hot spot No. 3 hours 12, in the hot spot No. 4 hours 8. However, statistical analysis of the time without considering the spatial hot spot shows the peak of residential burglary at 12 noon.
Conclusion
In this study, a new framework for the simultaneously displaying the pattern of crimes in two dimensions of spatial and time was presented, which can be used to identify the pattern of distribution of spatial and temporal of hot crime spots. The results of kernel density estimation analysis are four spatial-temporal crime hotspots where the spatial hotspot distribution pattern is clustered and the temporal of hot crime spots distribution pattern is focused. The results show that 78% of burglaries occur in these four crime hotspot, which cover only 25% of the total area of the study area. Therefore, by identifying the spatial and temporal of hot spots, crime can be largely prevented. This method is used to identify and display any type of crime in each study area and allows the identification and display of the combination of spatial and temporal hot crime spots.
