Visual Analytics Law Enforcement Tools

• US 20130057551A1
• Filed: 11/08/2011
• Published: 03/07/2013
• Est. Priority Date: 10/01/2007
• Status: Active Grant

• Current Assignee: Purdue Research Foundation (The Trustees of Purdue University (d/b/a Purdue University))
• Original Assignee: Purdue Research Foundation (The Trustees of Purdue University (d/b/a Purdue University))
• Inventors: Ebert, David S., Maciejewski, Ross, Collins, Timothy, Malik, Abish
• Granted Patent: US 8,849,728 B2
• Time in Patent Office: Days
• US Class Current: 345/440
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Abstract

A system and method for visually displaying and analyzing criminal and/or public health and safety data for geospatial and/or time variations, including the collection of incident data coupled with geographic and time data, filtering the symptom data based upon a selected time period and geographic range, and creating a visual result based upon statistical modeling including power transform and/or data normalization. According to at least one embodiment, the system for visually displaying and analyzing includes selecting and performing at least one aberration detection method and displaying the result to a user via a visual analytics arrangement.

Claims

1. A method comprising:

obtaining first data regarding criminal, traffic and/or civil incidents, the first data comprising reported criminal, traffic and/or civil incidents from a plurality of locations;

sorting the first data based upon incident categories;

applying seasonal trend decomposition with loess smoothing for the first data;

plotting incidents within the first data as points, density estimated heatmaps, or chloropleth maps for a defined geotemporal unit; and

displaying the plotted incidents to a user via a graphic user interface.

2. The method of claim 1, wherein plotting the incidents within the first data is performed as a density estimated heatmap, wherein the density estimated heatmap is performed by employing a variable kernel method which scales the parameter of an estimation by allowing a kernel width to vary according to the algorithm

3. The method of claim 2, further comprising generating display information based on the density estimated heatmap.

4. The method of claim 1, further comprising plotting spatial statistics of the first data utilizing a multidirectional optimum ectope-based algorithm to create a spatial weights matrix to identify hot and cold spots in mapped data.

5. The method of claim 1, further comprising:

generating quantile measures based on a select epicenter and time window;

displaying information representative of the quantile measures.

6. The method of claim 1, further comprising obtaining second data regarding demographic data, weather data, or special events data, the second data comprising data related to a plurality of locations.

7. The method of claim 6, further comprising:

filtering the first data based upon the correlation of the first data with the second data.

8. The method of claim 7, further comprising predicting the occurrence of additional incidents based upon the filtered data.

9. A method comprising:

obtaining first data regarding criminal, traffic and/or civil incidents, the first data comprising reported criminal, traffic and/or civil incidents from a plurality of locations;

sorting the first data based upon incident categories;

applying seasonal trend decomposition with loess smoothing for the first data;

plotting incidents within the first data as points, density estimated heatmaps, or chloropleth maps for a defined geotemporal unit;

obtaining second data regarding demographic data, weather data, or special events data, the second data comprising data related to a plurality of locations; and

displaying the plotted incidents and second data to a user via a graphic user interface.

10. The method of claim 9, further comprising:

generating quantile measures based on a select epicenter and time window;

displaying information representative of the quantile measures.

11. The method of claim 9, wherein plotting the incidents within the first data is performed as a density estimated heatmap, wherein the density estimated heatmap is performed by employing a variable kernel method which scales the parameter of an estimation by allowing a kernel width to vary according to the algorithm

12. The method of claim 11, wherein generating the heatmap includes displaying a color of the glyph based on the value for the site.

13. The method of claim 9, further comprising plotting spatial statistics of the first data utilizing a multidirectional optimum ectope-based algorithm to create a spatial weights matrix to identify hot and cold spots in mapped data.

14. The method of claim 13, wherein the spatial weights matrix is determined according to the value of G*_i, where G*_i is defined as:

15. The method of claim 14, further comprising:

displaying a color of a group based on the G*_i value.