Sex estimation from sacrum and coccyx with discriminant analyses and neural networks in an equally distributed population by age and sex
Loading...
Date
2019
Journal Title
Journal ISSN
Volume Title
Publisher
ELSEVIER IRELAND LTD
Access Rights
info:eu-repo/semantics/openAccess
Abstract
Sex estimation is an essential step in the process of the identification of the skeletal remains in forensic anthropology since it reduces the number of possible matches by half. In this study, sex estimation with 21 sacral and coccygeal metric parameters obtained from Computerized Tomography images of a Turkish population which consists of 480 patients that are equalized according to their sexes and ages, is performed. Univariate discriminant analysis, linear discriminant function analysis, stepwise discriminant function analysis, and multilayer perceptron neural networks are used in this study. A maximum of 67.1% accuracy for univariate discriminant analysis, 82.5% for linear discriminant function analysis, 78.8% for stepwise discriminant function analysis, and 86.3% for multilayer perceptron neural networks, were achieved. Although it does not reach an acceptable accuracy rate of 95% or more for sacrum and coccyx, sex estimation with neural networks is a promising field of research in corpses where identification is otherwise not possible, and further studies with other bones and with new techniques might give useful information. (C) 2019 Elsevier B.V. All rights reserved.
Description
Keywords
Sacrum, Coccyx, Sex estimation, Discriminant function analysis, Neural, Networks
Journal or Series
FORENSIC SCIENCE INTERNATIONAL
WoS Q Value
Q1
Scopus Q Value
Q1
Volume
303
Issue
Citation
Etli, Y., Asirdizer, M., Hekimoglu, Y., Keskin, S., Yavuz, A. (2019). Sex Estimation From Sacrum And Coccyx With Discriminant Analyses And Neural Networks İn An Equally Distributed Population By Age And Sex. Forensıc Scıence Internatıonal, 303, 1-9.
