Portable Fourier-transform infrared spectroscopy and machine learning for sex determination in third instar Chrysomya rufifacies larvae.

Aidan P Holman, Davis N Pickett, Hunter West, Aaron M Tarone, Dmitry Kurouski
{"title":"Portable Fourier-transform infrared spectroscopy and machine learning for sex determination in third instar Chrysomya rufifacies larvae.","authors":"Aidan P Holman, Davis N Pickett, Hunter West, Aaron M Tarone, Dmitry Kurouski","doi":"10.1111/1556-4029.70054","DOIUrl":null,"url":null,"abstract":"<p><p>Forensic entomology is crucial in medicolegal investigations, utilizing insects-primarily flies-to estimate a supplemental post-mortem interval based on their development at the (death) scene. This estimation can be influenced by extrinsic factors like temperature and humidity, as well as intrinsic factors such as species and sex. Previously, benchtop Fourier-transform infrared (FTIR) spectroscopy coupled with machine learning demonstrated high accuracy in distinguishing the sex of third instar Cochliomyia macellaria larvae. This study leverages benchtop- and handheld-based FTIR spectroscopy combined with machine learning models-Partial Least Squares Discriminant Analysis (PLSDA), eXtreme Gradient Boosting trees Discriminant Analysis (XGBDA), and Artificial Neural Networks Discriminant Analysis (ANNDA)-to differentiate between male and female Chrysomya rufifacies larvae, commonly found on human remains. Significant vibrational differences were detected in the mid-infrared spectra of third instar Ch. rufifacies larvae, with a majority of peaks showing a higher abundance of proteins, lipids, and hydrocarbons in male larvae. PLSDA and ANNDA models developed using benchtop FTIR data achieved high external validation accuracies of approximately 90% and 94.5%, respectively, when tested with handheld FTIR data. This nondestructive approach offers the potential to refine supplemental post-mortem interval estimations significantly, enhancing the accuracy of forensic analyses of entomological evidence.</p>","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of forensic sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1111/1556-4029.70054","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Forensic entomology is crucial in medicolegal investigations, utilizing insects-primarily flies-to estimate a supplemental post-mortem interval based on their development at the (death) scene. This estimation can be influenced by extrinsic factors like temperature and humidity, as well as intrinsic factors such as species and sex. Previously, benchtop Fourier-transform infrared (FTIR) spectroscopy coupled with machine learning demonstrated high accuracy in distinguishing the sex of third instar Cochliomyia macellaria larvae. This study leverages benchtop- and handheld-based FTIR spectroscopy combined with machine learning models-Partial Least Squares Discriminant Analysis (PLSDA), eXtreme Gradient Boosting trees Discriminant Analysis (XGBDA), and Artificial Neural Networks Discriminant Analysis (ANNDA)-to differentiate between male and female Chrysomya rufifacies larvae, commonly found on human remains. Significant vibrational differences were detected in the mid-infrared spectra of third instar Ch. rufifacies larvae, with a majority of peaks showing a higher abundance of proteins, lipids, and hydrocarbons in male larvae. PLSDA and ANNDA models developed using benchtop FTIR data achieved high external validation accuracies of approximately 90% and 94.5%, respectively, when tested with handheld FTIR data. This nondestructive approach offers the potential to refine supplemental post-mortem interval estimations significantly, enhancing the accuracy of forensic analyses of entomological evidence.

便携式傅里叶变换红外光谱和机器学习在三龄金蝇幼虫性别鉴定中的应用。
法医昆虫学在法医调查中是至关重要的,它利用昆虫——主要是苍蝇——根据它们在(死亡)现场的发育来估计一个补充的死后间隔。这种估计可能受到温度和湿度等外在因素以及物种和性别等内在因素的影响。此前,台式傅里叶变换红外(FTIR)光谱与机器学习相结合,在区分三龄macellaria蜗蝇幼虫的性别方面表现出很高的准确性。本研究利用台式和手持FTIR光谱结合机器学习模型-偏最小二乘判别分析(PLSDA),极端梯度增强树判别分析(XGBDA)和人工神经网络判别分析(ANNDA)-来区分男性和女性金蝇rufifacies幼虫,通常在人类遗骸上发现。在三龄幼虫的中红外光谱中发现了显著的振动差异,雄性幼虫在大多数峰中显示出更高的蛋白质、脂质和碳氢化合物丰度。使用台式FTIR数据开发的PLSDA和ANNDA模型在使用手持FTIR数据进行测试时,分别获得了约90%和94.5%的高外部验证精度。这种非破坏性的方法提供了显著改进补充死后间隔估计的潜力,提高了昆虫学证据的法医分析的准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信