scholarly journals How Is the Confidentiality of Crime Locations Affected by Parameters in Kernel Density Estimation?

2019 ◽  
Vol 8 (12) ◽  
pp. 544 ◽  
Author(s):  
Zengli Wang ◽  
Lin Liu ◽  
Hanlin Zhou ◽  
Minxuan Lan

Kernel density estimation (KDE) is widely adopted to show the overall crime distribution and at the same time obscure exact crime locations due to the confidentiality of crime data in many countries. However, the confidential level of crime locational information in the KDE map has not been systematically investigated. This study aims to examine whether a kernel density map could be reverse-transformed to its original map with discrete crime locations. Using the Epanecknikov kernel function, a default setting in ArcGIS for density mapping, the transformation from a density map to a point map was conducted with various combinations of parameters to examine its impact on the deconvolution process (density to point location). Results indicate that if the bandwidth parameter (search radius) in the original convolution process (point to density) was known, the original point map could be fully recovered by a deconvolution process. Conversely, when the parameter was unknown, the deconvolution process would be unable to restore the original point map. Experiments on four different point maps—a random point distribution, a simulated monocentric point distribution, a simulated polycentric point distribution, and a real crime location map—show consistent results. Therefore, it can be concluded that the point location of crime events cannot be restored from crime density maps as long as parameters such as the search radius parameter in the density mapping process remain confidential.

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Wenzhong Shi ◽  
Chengzhuo Tong ◽  
Anshu Zhang ◽  
Bin Wang ◽  
Zhicheng Shi ◽  
...  

A Correction to this paper has been published: https://doi.org/10.1038/s42003-021-01924-6


2021 ◽  
Vol 13 (1) ◽  
pp. 796-806
Author(s):  
Zhen Shuo ◽  
Zhang Jingyu ◽  
Zhang Zhengxiang ◽  
Zhao Jianjun

Abstract Understanding the risk of grassland fire occurrence associated with historical fire point events is critical for implementing effective management of grasslands. This may require a model to convert the fire point records into continuous spatial distribution data. Kernel density estimation (KDE) can be used to represent the spatial distribution of grassland fire occurrences and decrease the influences historical records in point format with inaccurate positions. The bandwidth is the most important parameter because it dominates the amount of variation in the estimation of KDE. In this study, the spatial distribution characteristic of the points was considered to determine the bandwidth of KDE with the Ripley’s K function method. With high, medium, and low concentration scenes of grassland fire points, kernel density surfaces were produced by using the kernel function with four bandwidth parameter selection methods. For acquiring the best maps, the estimated density surfaces were compared by mean integrated squared error methods. The results show that Ripley’s K function method is the best bandwidth selection method for mapping and analyzing the risk of grassland fire occurrence with the dependent or inaccurate point variable, considering the spatial distribution characteristics.


Sign in / Sign up

Export Citation Format

Share Document