U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

APPLICATION OF PATTERN RECOGNITION IN ARSON INVESTIGATION

NCJ Number
54192
Journal
Fire Technology Volume: 11 Issue: 1 Dated: (FEBRUARY 1975) Pages: 35-41
Author(s)
D J ICOVE; H J CRISMAN
Date Published
1975
Length
7 pages
Annotation
A DISCUSSION IS PRESENTED OF THE APPLICATION OF PATTERN RECOGNITION METHODS TO THE DEVELOPMENT OF TECHNIQUES FOR AIDING THE ARSON INVESTIGATOR IN DETERMINING TRENDS IN INCENDIARY AND SUSPICIOUS FIRES.
Abstract
IN AN EFFORT TO PROVIDE COMPREHENSIVE ENGINEERING ANALYSIS OF THESE INVESTIGATIONS, A SET OF ALGORITHMIC COMPUTER PROGRAMS HAS BEEN DEVELOPED USING PATTERN RECOGNITION METHODS. THE EMERGENCE OF THE FIRE ENGINEERING DATA ANALYSIS PROGRAM (FEDAP) PARALLELED THE IMPLEMENTATION IN PRINCE GEORGE'S COUNTY, MD., OF THE MODULAR INFORMATION REPORTING SYSTEM (MIRS). DESIGNED BY THE NATIONAL BUREAU OF STANDARDS, MIRS IS INTENDED TO BECOME A NATIONWIDE STANDARD FOR THE COMPUTERIZED ENCODING OF EMERGENCY INCIDENTS. SUCCESSFUL IMPLEMENTATION OF A SUPERVISED ARSON PATTERN RECOGNITION (APR) SYSTEM FOR THE PREDICTION AND PREVENTION OF INCENDIARY CRIMES REQUIRES A SET OF VALID DECISION RULES. USING LABELED PATTERN SAMPLES OF KNOWN ARSON TRENDS, HIGHLY RELIABLE DECISION RULES CAN BE DERIVED. EACH PATTERN SAMPLE CONSISTS OF AN INDIVIDUAL ARSON-RELATED FIRE NUMERICALLY ENCODED BY MIRS AND DEFINED BY FEDAP AS A PARTITIONED ROW MATRIX. A SEVEN-DIMENSION PATTERN SPACE DESCRIBES THE FIRE IN TERMS OF THE DATE OF THE INCIDENT, THE LOCATION, TYPE OF FIRE, ACT OR OMISSION, THE TIME THE ALARM WAS RECEIVED, THE DAY OF THE WEEK, AND THE NUMBER OF ALARMS. BY SO CODING INDIVIDUAL FIRES WITHIN A JURISDICTION, COMPUTER BATCHING OR CLUSTERING IS POSSIBLE FOR FIRES SHARING SELECTED FEATURES. FEATURE SELECTION IS AN ACCEPTABLE TECHNIQUE FOR REDUCING THE DIMENSIONALITY OF THE PATTERN SPACE ARSON DATA. THE COUNTY USES A MAP CONSISTING OF 185 MAJOR MAP GRIDS, EACH CONTAINING AN ADDITIONAL 24 GRIDS. USING FEATURE SELECTION, CLUSTER CLASSIFICATION, AND THE FEDAP ALGORITHMS, 11 ADJACENT MAJOR MAP GRIDS HAVE BEEN IDENTIFIED AS CONTAINING 37 PERCENT OF THE 361 TOTAL ARSON-RELATED FIRES. USING LOCATION AND TIME DATA, THE COUNTY HAS USED THE SYSTEM TO SOLVE A SERIES OF ARSON INCIDENTS PERPETRATED BY JUVENILE GANGS IN WHICH THE TIMES OF THE MULTIPLE FIRES CORRESPONDED REPEATEDLY TO BREAKS IN THE SCHOOL DAY. REFERENCES AND GRAPHIC DATA ARE INCLUDED. (KBL)

Downloads

No download available

Availability