Artificial Neural Network System for Classification of Offenders in Murder and Rape Cases, Executive Summary

• NCJ Number: 190983
• Author(s): Lars Kangas
• Date Published: October 2000
• Length: 5 pages
• Grant Number(s): 97-IJ-CX-K007
• Sponsoring Agency: National Institute of Justice (NIJ)
• Corporate Author: Battelle Memorial Institute
• Sale Source: NCJRS Photocopy Services; Battelle Memorial Institute
• Publication Series: NIJ Research Report
• Publication Format: Document
• Publication Type: Report (Study/Research)
• Language: English
• Country: United States of America
• Note: For the complete report, see NCJ-190984.

Annotation

This is an Executive Summary of a report on an artificial neural network system for classifying offenders in murder and rape cases.

Abstract

The "Artificial Neural Network Systems for Classification of Offenders in Murder and Rape Cases" project developed two software prototypes that demonstrate developed algorithms for analyzing and comparing large databases of crime data. The CATCH (Computer Aided Tracking and Characterization of Homicides) and CATCHRAPE software applications analyze homicide data and sexual assault data, respectively. Development of CATCH was made possible with the HITS (Homicide Investigation Tracking System) database system. The HITS system provided the required historical crime data for CATCH to learn offender behavior so that new unsolved crimes can be characterized for analysis and comparison. CATCH characterizes an unknown offender by comparing his or her crime to known offenders of other crimes where the offenders' behavior was similar. The information includes level of education, type of work, physical appearance, misuse of alcohol and drugs, etc. The underlying assumption is that individuals who otherwise behave similarly, may also commit crimes with similar behavior. Bibliography