In this pap er we evaluate forensic identication hyp otheses conditionally to the characteristics observed b oth on a crime sample and on individ- uals contained in a database. First we solve the problem via a computational ecient Bayesian Network obtained by transforming some rec- ognized conditional sp ecic indep endencies into conditional indep endencies. Then we prop ose an Ob ject Oriented Bayesian Network represen- tation, rst considering a generic characteristic, then inheritable DNA traits. In this resp ect we show how to use the Ob ject Oriented Bayesian Network to evaluate hyp otheses concerning the p ossibility that some unobserved individuals, ge- netically related to the individuals proled in the database, are the donors of the crime sample.

OOBN for Forensic Identification through a searching in a database of DNA profiles’ / F. CORRADI; D. CAVALLINI. - ELETTRONICO. - (2005), pp. 41-48. (Intervento presentato al convegno UAI tenutosi a Barbados nel 5-8 January 2005).

OOBN for Forensic Identification through a searching in a database of DNA profiles’

CORRADI, FABIO
;
CAVALLINI, DAVID
2005

Abstract

In this pap er we evaluate forensic identication hyp otheses conditionally to the characteristics observed b oth on a crime sample and on individ- uals contained in a database. First we solve the problem via a computational ecient Bayesian Network obtained by transforming some rec- ognized conditional sp ecic indep endencies into conditional indep endencies. Then we prop ose an Ob ject Oriented Bayesian Network represen- tation, rst considering a generic characteristic, then inheritable DNA traits. In this resp ect we show how to use the Ob ject Oriented Bayesian Network to evaluate hyp otheses concerning the p ossibility that some unobserved individuals, ge- netically related to the individuals proled in the database, are the donors of the crime sample.
2005
AISTATS 2005 Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics
UAI
Barbados
5-8 January 2005
F. CORRADI; D. CAVALLINI
File in questo prodotto:
File Dimensione Formato  
OOBN.pdf

Accesso chiuso

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Tutti i diritti riservati
Dimensione 247.32 kB
Formato Adobe PDF
247.32 kB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/237651
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact