An Intelligent Process-driven Knowledge Extraction Framework for Crime Analysis
description
Transcript of An Intelligent Process-driven Knowledge Extraction Framework for Crime Analysis
An Intelligent Process-driven Knowledge Extraction Framework for Crime
Analysis
PhD Thesis – Research PlanALBERTETTI Fabrizio
Thesis Director: Prof. STOFFEL KilianInformation Management Institute
University of NeuchatelSwitzerland
New Challenges in the European AreaYoung Scientist's 1st International Baku ForumMay 20-25
2
Context Objectives Research Challenges
Agenda
3Project context
» Interdisciplinary project:˃ Computational
+ Information Management Institute, University of Neuchatel
˃ Forensics+ Institut de Police Scientifique, University of Lausanne
» Supported by the Swiss National Science Foundation (SNSF)
» 5 years project (?) – Started in Sept. 2011
4
How do criminals think?Is crime rational?
5The Rationality of Crime
» E.g., the routine activity approach (Cohen & Felson, 1979)
Figure: Routine Activity (popcenter.org)
6
"Crime analysis is the systematic study of crime and disorder problems as well as other
police-related issues—including sociodemographic, spatial, and temporal
factors—to assist the police in criminal apprehension, crime and disorder reduction,
crime prevention, and evaluation." (Boba, 2005)
Crime Analysis
7
"Crime analysis is the systematic study of crime and disorder problems as well as other
police-related issues—including sociodemographic, spatial, and temporal
factors—to assist the police in criminal apprehension, crime and disorder reduction,
crime prevention, and evaluation." (Boba, 2005)
Crime Analysis
8
» The chain of events in crime prevention:
Prevention Proactivity Predictability Patterns
ComputationalForensics !
Discovering Forensic
Knowledge
How can we prevent crime?
From patterns to prevention (Ratcliffe, 2009)
9Objectives
» To develop a framework :
• For conducting analyses
• Driven by processes (using domain knowledge)
• Intelligent (assessing the results)
• Extracting knowledge from forensic data
10Key Questions
» What is the nature of forensic data?˃ Uncertain˃ Incomplete˃ Inaccurate
» Why?˃ Because it is based on hypotheses and conjectures˃ Because it stems mainly from latent marks˃ Because it reflects the effects and not the causes
(abduction)
11Key Questions
Challenges:» To conduct analyses and perform
deduction/reasoning with partial knowledge, uncertainties and conjectures
» To integrate domain intelligence for providing practical and consistent results
» To conduct analyses with a holistic view of the macro process, i.e. combining several mining outcomes based on crime analysis processes
DOMAIN-DRIVEN
DATA MINING
FORENSICSCIENCE
KNOWLEDGE REPRESENTATION
FUZZYLOGIC
COMPUTATIONAL
FORENSICFRAMEWORK
12Key Questions – Research Domains
13Conclusions
» Computational forensics is still an emerging research area
» Only a combination of several domains can answer crime analysis questions
Thank you
PhD Thesis – Research PlanALBERTETTI FabrizioThesis Director: Prof. STOFFEL KilianInformation Management InstituteUniversity of NeuchatelSwitzerland
* This project is supported by the Swiss National Science Foundation
An Intelligent Process-driven Knowledge Extraction Framework for Crime Analysis *