The purpose of this study was to develop a computer-assisted inference model for determining age based on dental development by orthopantomographs (OPT). Five experienced examiners (2 forensic pathology and 3 orthodontists) defined the degree of maturation of each of the permanent dental elements (superior and inferior hemi-arch) by 66 digitised OPT. Data set obtained was used as data base for un expert system designed on self learning that, by fuzzy reasoning, developed a set of complex algorithms in order to determine the age. The standard deviation (SD) of the age in such a way estimated compared to real ones was ±/10 months with 70% of reliability in rnales and +/- 8 months with 75% of reliability in females.
Fuzzy reasoning in an expert system for age determination by dental maturity from orthopantomographs / DI LORENZO, Pierpaolo; Policino, Fabio; Quaremba, Giuseppe; Laino, Alberto; Niola, Massimo; Buccelli, Claudio. - STAMPA. - (2002), pp. 161-172. (Intervento presentato al convegno The 10th Biennial Scientific Meeting of the International Association for Craniofacial Identification: A head on the new millenium: the latest in craniofacial identification tenutosi a Bari nel 11-14 settembre 2002).
Fuzzy reasoning in an expert system for age determination by dental maturity from orthopantomographs
DI LORENZO, PIERPAOLO;POLICINO, FABIO;QUAREMBA, GIUSEPPE;LAINO, ALBERTO;NIOLA, MASSIMO;BUCCELLI, CLAUDIO
2002
Abstract
The purpose of this study was to develop a computer-assisted inference model for determining age based on dental development by orthopantomographs (OPT). Five experienced examiners (2 forensic pathology and 3 orthodontists) defined the degree of maturation of each of the permanent dental elements (superior and inferior hemi-arch) by 66 digitised OPT. Data set obtained was used as data base for un expert system designed on self learning that, by fuzzy reasoning, developed a set of complex algorithms in order to determine the age. The standard deviation (SD) of the age in such a way estimated compared to real ones was ±/10 months with 70% of reliability in rnales and +/- 8 months with 75% of reliability in females.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.