Developing a fully applicable machine learning (ML) based sex classification model using linear cranial dimensions

Author:

Bašić Željana1,Jerković Ivan1,Anđelinović Šimun2,Krešić Elvira3,Jerković Nika1,Dolić Krešimir2,Čavka Mislav3,Bedalov Ana1,Kružić Ivana1

Affiliation:

1. University of Split

2. University Hospital Center Split

3. University Hospital Center Zagreb

Abstract

Abstract Recent advances in AI and ML applications have elevated accomplishments in various scientific fields, primarily those that benefit the economy and society. Contemporary threats, such as armed conflicts, natural and man-made disasters, and illegal migrations, often require fast and innovative but reliable identification aids, in which forensic anthropology has a significant role. However, forensic anthropology has not exploited new scientific advances yet but instead relies on traditionally used methods. The rare studies that employ AI and ML in developing standards for sex and age estimation did not go beyond the conceptual solutions and did not apply to real cases. In this study, on the example of Croatian populations’ cranial dimensions, we demonstrated the methodology of developing sex classification models using ML in conjunction with field knowledge, resulting in sex estimation accuracy of more than 95%. To illustrate the necessity of applying scientific results, we developed a web app, CroCrania, that can be used for sex estimation and method validation.

Publisher

Research Square Platform LLC

Reference68 articles.

1. New perspectives in forensic anthropology;Dirkmaat DC;Am J Phys Anthropol,2008

2. The role of forensic anthropology in disaster victim identification (DVI): recent developments and future prospects;Boer HH;Forensic Sci Res,2019

3. Guide DVI, Amendments P (2014) Disaster victim identification guide 1997. (1997)

4. Primorac D et al (2008) Analiza DNA u sudskoj medicini i pravosuđu. Medicinska naklada

5. Forensic age estimation of living individuals: a retrospective analysis;Santoro V;Forensic Sci Int,2009

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3