4.5 Article

Comparing discriminant analysis and neural network for the determination of sex using femur head measurements

期刊

FORENSIC SCIENCE INTERNATIONAL
卷 253, 期 -, 页码 81-87

出版社

ELSEVIER IRELAND LTD
DOI: 10.1016/j.forsciint.2015.05.023

关键词

Forensic medicine; Forensic anthropology; Sexual dimorphism; Artificial neural network; Discriminant analysis; Femoral head diameter

向作者/读者索取更多资源

The measurement of the femoral head is usually considered an interesting variable for the sex determination of skeletal remains. To date, there are few published reference measurements of the femoral head in a modern European population for the purpose of sex determination. In this study, 116 femurs from 58 individuals of the South of France (Nice Bone Collection, Nice, France) were studied. Three measurements of the femoral head were taken: the vertical head diameter (VHD), the transversal head diameter (THD) and the head circumference (HC). The results show that: (i) there is no statistical difference between the right and left femurs for each of the three measurements (VHD, THD and HC). Therefore we arbitrarily chose to use the measures from the right femurs (N = 58) to pursue our experiments; (ii) the measurements of the femoral head are similar to those of contemporary American populations; (iii) the dimensions of the femoral head place the measurements of the French population somewhere between Germany or Croatia, and Spain; (iv) there is no significant secular trend (in contrast with the femoral neck diameter); (v) the femoral head measurement as a single variable is useful for sex determination: a 96.5% rate of accuracy was obtained using THD and HC measurements with the artificial neural network; and a 94.8% rate of accuracy using VHD, both with the discriminant analysis and the neural network. (C) 2015 Elsevier Ireland Ltd. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Management

Bankruptcy prediction using terminal failure processes

Philippe du Jardin

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH (2015)

Article Computer Science, Artificial Intelligence

MD-ELM: Originally Mislabeled Samples Detection using OP-ELM Model

Anton Akusok, David Veganzones, Yoan Miche, Kaj-Mikael Bjork, Philippe du Jardin, Eric Severin, Amaury Lendasse

NEUROCOMPUTING (2015)

Article Computer Science, Artificial Intelligence

SOM-ELM Self-Organized Clustering using ELM

Yoan Miche, Anton Akusok, David Veganzones, Kaj-Mikael Bjork, Eric Severin, Philippe du Jardin, Maite Termenon, Amaury Lendasse

NEUROCOMPUTING (2015)

Article Management

A two-stage classification technique for bankruptcy prediction

Philippe du Jardin

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH (2016)

Article Computer Science, Artificial Intelligence

Dynamics of firm financial evolution and bankruptcy prediction

Philippe du Jardin

EXPERT SYSTEMS WITH APPLICATIONS (2017)

Article Medicine, Legal

Sex determination using the DSP (probabilistic sex diagnosis) method on the coxal bone: Efficiency of method according to number of available variables

Gerald Quatrehomme, Irina Radoman, Luisa Nogueira, Philippe du Jardin, Veronique Alunni

FORENSIC SCIENCE INTERNATIONAL (2017)

Article Medicine, Legal

Comparison of macroscopic and microscopic (stereomicroscopy and scanning electron microscopy) features of bone lesions due to hatchet hacking trauma

Luisa Nogueira, Gerald Quatrehomme, Marie-France Bertrand, Christophe Rallon, Romain Ceinos, Philippe du Jardin, Pascal Adalian, Veronique Alunni

INTERNATIONAL JOURNAL OF LEGAL MEDICINE (2017)

Article Computer Science, Artificial Intelligence

Failure pattern-based ensembles applied to bankruptcy forecasting

Philippe du Jardin

DECISION SUPPORT SYSTEMS (2018)

Article Medicine, Legal

Positive identification by X-rays bone trabeculae comparison

Gerald Quatrehomme, Elodie Biglia, Bernard Padovani, Philippe du Jardin, Veronique Alunni

FORENSIC SCIENCE INTERNATIONAL (2014)

Article Operations Research & Management Science

Forecasting bankruptcy using biclustering and neural network-based ensembles

Philippe du Jardin

Summary: Most bankruptcy prediction models do not fully capture the diversity of firm bankruptcy situations, often assuming that all symptoms of failure have the same origin or that financial situations leading to failure are the same for all firms. A proposed modeling method combines biclustering and ensemble techniques to overcome these limitations and improve forecast accuracy.

ANNALS OF OPERATIONS RESEARCH (2021)

Article Management

Forecasting corporate failure using ensemble of self-organizing neural networks

Philippe du Jardin

Summary: Research shows that by designing an ensemble method relying on self-organizing neural networks, it is possible to significantly reduce both type I and type II errors obtained with conventional methods.

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH (2021)

Article Computer Science, Artificial Intelligence

Dynamic self-organizing feature map-based models applied to bankruptcy prediction

Philippe du Jardin

Summary: Traditional bankruptcy prediction models rely on single-period data, while bankruptcy is actually a continuous process and time is an important explanatory variable for firm failure. Studies attempting to use multi-period data for forecasting have not significantly improved model accuracy.

DECISION SUPPORT SYSTEMS (2021)

Article Operations Research & Management Science

Designing topological data to forecast bankruptcy using convolutional neural networks

Philippe du Jardin

Summary: This article proposes a technique to transform data into a topological space in order to study the ability of CNN to forecast corporate bankruptcy and financial failure. The results show that CNN-based models designed with this technique are more accurate than traditional ones.

ANNALS OF OPERATIONS RESEARCH (2023)

Article Economics

Forecasting Corporate Bankruptcy Using Accrual-Based Models

Philippe du Jardin, David Veganzones, Eric Severing

COMPUTATIONAL ECONOMICS (2019)

Article Medicine, Legal

Assessing the usefulness of Raman spectroscopy and lipid analysis of decomposed human bones in forensic genetics and molecular taphonomy

Heitor S. D. Correa, Ivano Alessandri, Andrea Verzeletti

Summary: This research assessed the usefulness of Raman spectroscopy and gas chromatography-mass spectrometry in analyzing bones. The techniques were found to be useful in molecular taphonomy studies and forensic genetics.

FORENSIC SCIENCE INTERNATIONAL (2024)