Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Record fields, open police data [42].

Crime types are listed in S2 Appendix.

More »

Table 1 Expand

Fig 1.

Histogram of distances from anonymised to true crime locations (Cardiff).

More »

Fig 1 Expand

Fig 2.

Hourly reported violence count by day of week (Cardiff).

More »

Fig 2 Expand

Fig 3.

Subset of point of interest hierarchy.

More »

Fig 3 Expand

Fig 4.

City centres used for evaluation.

Blue squares indicate 3 km × 3 evaluation areas. © OpenStreetMap [44] contributors.

More »

Fig 4 Expand

Table 2.

Cities in the study and their populations, 2011 UK Census.

Note that population counts refer to entire city, Nviolence and NPOI are the violence and POI counts in the central 9 km2 of these cities.

More »

Table 2 Expand

Fig 5.

Illustration of regression from POI densities to violent crime density.

More »

Fig 5 Expand

Fig 6.

Clustered correlation coefficients between subset of pairs of POIs (Cardiff).

More »

Fig 6 Expand

Fig 7.

Model performance and variable count by LASSOα value, all cities.

More »

Fig 7 Expand

Fig 8.

Model performance by kernel type, brackets show mean and standard deviation in performance.

More »

Fig 8 Expand

Fig 9.

The effect of varying the bandwidth in POI KDE, by city.

More »

Fig 9 Expand

Fig 10.

Ground truth, prediction, and residuals for Cardiff.

Units are crime incidents per square kilometer.

More »

Fig 10 Expand

Table 3.

Mean performance of the baseline alcohol-outlet only linear regression vs the proposed LASSO-based POI model across 100 random test/train splits.

More »

Table 3 Expand

Table 4.

Occurence count of POI classes occurring in top ten model coefficients.

More »

Table 4 Expand

Table 5.

Top 10 LASSO R2 coefficients, combined model.

More »

Table 5 Expand

Table 6.

Combined model performance.

More »

Table 6 Expand