Sex Estimation Using Geometric Morphometrics

2021 ◽  
Author(s):  
Valda Black
Keyword(s):  
Geometric Morphometrics ◽  
Classification Accuracy ◽  
Function Analysis ◽  
Dorsal Surface ◽  
Two Dimensions ◽  
Pubic Bone ◽  
Biological Anthropology ◽  
Sex Estimation ◽  
Linear Discriminant ◽  
Shape Changes

Creating and testing efficient techniques for the sex estimation of modern human skeletal remains has been a significant focus in biological anthropology. It is well established that the innominate, particularly the pubic bone, is a sexually dimorphic part of the human skeleton, but prone to fragmentation. Using modern pubic bones of known age and sex, this study aims to capture shape differences using geometric morphometrics (GMM) to test classification accuracy of segments of the pubic bone. The sample consists of 70 left adult pubic bones from the William M. Bass Donated Skeletal Collection, with 35 males and 35 females of mixed age and population affinity. Landmarks were placed on the dorsal surface of the pubic body and ischiopubic ramus to capture their overall shape in two dimensions, so the study is easily replicable and applicable. The scans were separately run through a generalized Procrustes, principal components (PCA), and canonical linear discriminant function analysis (DFA). The DFA results show high classification accuracy for the pubic body (94% males, 100% females) and the ischiopubic ramus (100% females, 97% males), with the PCA DFA allowing a researcher to explore specific shape changes driving the differentiation between groups. GMM was able to quantify and successfully discriminant the shape changes between males and females for small elements of the pubis, which can be applied to fragmentary remains and future morphological methods.

scholarly journals Giant ants and their shape: revealing relationships in the genusTitanomyrmawith geometric morphometrics

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e4242 ◽  
Author(s):  
Julian Katzke ◽  
Phillip Barden ◽  
Manuel Dehon ◽  
Denis Michez ◽  
Torsten Wappler
Keyword(s):  
Geometric Morphometrics ◽  
Function Analysis ◽  
Principal Component ◽  
Canonical Variate ◽  
Natural Phenomenon ◽  
Evolutionary Patterns ◽  
Deep Time ◽  
Linear Discriminant ◽  
New Methods ◽  
Female Relative

Shape is a natural phenomenon inherent to many different lifeforms. A modern technique to analyse shape is geometric morphometrics (GM), which offers a whole range of methods concerning the pure shape of an object. The results from these methods have provided new insights into biological problems and have become especially useful in the fields of entomology and palaeontology. Despite the conspicuous successes in other hymenopteran groups, GM analysis of wings and fossil wings of Formicidae has been neglected. Here we tested if landmarks defining the wing shape of fossil ants that belong to the genusTitanomyrmaare reliable and if this technique is able to expose relationships among different groups of the largest Hymenoptera that ever lived. This study comprises 402 wings from 362 ants that were analysed and assigned with the GM methods linear discriminant function analysis, principal component analysis, canonical variate analysis, and regression. The giant ant genusTitanomyrmaand the parataxonFormiciumhave different representatives that are all very similar but these modern methods were able to distinguish giant ant types even to the level of the sex. Thirty-five giant ant specimens from the Eckfeld Maar were significantly differentiable from a collection of Messel specimens that consisted of 187Titanomyrma giganteafemales and 42T. giganteamales, and from 74Titanomyrma simillimafemales and 21T. simillimamales. Out of the 324 Messel ants, 127 are newly assigned to a species and 223 giant ants are newly assigned to sex with GM analysis. All specimens from Messel fit to the two species. Moreover, shape affinities of these groups and the speciesFormicium brodiei,Formicium mirabile, andFormicium berryi, which are known only from wings, were investigated.T. giganteastands out with a possible female relative in one of the Eckfeld specimens whereas the other groups show similar shape patterns that are possibly plesiomorphic. Formicidae are one of the most dominant taxa in the animal kingdom and new methods can aid in investigating their diversity in the present and in deep time. GM of the ant wing delivers significant results and this core of methods is able to enhance the toolset we have now to analyse the complex biology of the ants. It can prove as especially useful in the future when incorporated into better understanding aspects of evolutionary patterns and ant palaeontology.

scholarly journals A model for spectroscopic food sample analysis using data sonification

2021 ◽  
Author(s):  
Hsein Kew
Keyword(s):  
Dimensionality Reduction ◽  
Classification Accuracy ◽  
Reduction Method ◽  
Real Life ◽  
Principal Component ◽  
Relevant Information ◽  
Analysis Model ◽  
Linear Discriminant ◽  
Audio Output ◽  
Dimensionality Reduction Method

AbstractIn this paper, we propose a method to generate an audio output based on spectroscopy data in order to discriminate two classes of data, based on the features of our spectral dataset. To do this, we first perform spectral pre-processing, and then extract features, followed by machine learning, for dimensionality reduction. The features are then mapped to the parameters of a sound synthesiser, as part of the audio processing, so as to generate audio samples in order to compute statistical results and identify important descriptors for the classification of the dataset. To optimise the process, we compare Amplitude Modulation (AM) and Frequency Modulation (FM) synthesis, as applied to two real-life datasets to evaluate the performance of sonification as a method for discriminating data. FM synthesis provides a higher subjective classification accuracy as compared with to AM synthesis. We then further compare the dimensionality reduction method of Principal Component Analysis (PCA) and Linear Discriminant Analysis in order to optimise our sonification algorithm. The results of classification accuracy using FM synthesis as the sound synthesiser and PCA as the dimensionality reduction method yields a mean classification accuracies of 93.81% and 88.57% for the coffee dataset and the fruit puree dataset respectively, and indicate that this spectroscopic analysis model is able to provide relevant information on the spectral data, and most importantly, is able to discriminate accurately between the two spectra and thus provides a complementary tool to supplement current methods.

Description and Quantification of Sexual Dimorphism of Pubic Body Shape in Hispanic Populations Using Elliptic Fourier Analysis

2021 ◽  
Author(s):  
Erica Cantor ◽  
Krista Latham ◽  
Stephen Nawrocki
Keyword(s):  
Fourier Analysis ◽  
North American ◽  
Principal Component ◽  
Pubic Bone ◽  
Biological Traits ◽  
Sex Estimation ◽  
Age At Death ◽  
Elliptic Fourier Analysis ◽  
Hispanic Populations ◽  
Effective Principal

Sex estimation is important in the creation of a biological profile for unidentified human remains, as positive identification cannot occur until the decedent’s biological traits have been determined and the range of possible matches has been narrowed. The pubic bone is cited as one of the best indicators of sex due to the constraints of childbirth. Current methods that use the pubic bone for sex estimation, however, rely on poorly defined and subjective observations that are susceptible to inter-and intraobserver error. Additionally, many of the methods currently in use are based on North American populations and thus may not necessarily model the variation seen in other populations around the globe. The aim of this study is to gain a better understanding of variation in pubic bone shape in Hispanic populations by separating the influences of sex, ancestry, and age at death. A total of 164 pubic bones from North American Hispanic and Chilean individuals were compared to 287 pubic bones from individuals of Euro-American ancestry from North American collections, using Elliptic Fourier analysis (EFA) of photographs, principal component analysis, and ANCOVA. EFA generated five effective principal components that collectively describe approximately 95% of the variation in the shape of the pubic body. Sex, age at death, and ancestry were all found to significantly influence shape but explained only 25% of the overall variation. The remaining 75% is likely influenced by variables that cannot be controlled for in anthropological analysis, underscoring how little variance in skeletal morphology is actually explainable.

scholarly journals Use of machine learning to identify autism with natural social gaze behavior (Preprint)

2021 ◽  
Author(s):  
Zhong Zhao ◽  
Haiming Tang ◽  
Xiaobin Zhang ◽  
Xingda Qu ◽  
Jianping Lu
Keyword(s):  
Machine Learning ◽  
Eye Tracking ◽  
Classification Accuracy ◽  
Autism Spectrum ◽  
Support Vector ◽  
Gaze Behavior ◽  
Linear Discriminant ◽  
Face To Face ◽  
Area Of Interest ◽  
Social Gaze

BACKGROUND Abnormal gaze behavior is a prominent feature of the autism spectrum disorder (ASD). Previous eye tracking studies had participants watch images (i.e., picture, video and webpage), and the application of machine learning (ML) on these data showed promising results in identify ASD individuals. Given the fact that gaze behavior differs in face-to-face interaction from image viewing tasks, no study has investigated whether natural social gaze behavior could accurately identify ASD. OBJECTIVE The objective of this study was to examine whether and what area of interest (AOI)-based features extracted from the natural social gaze behavior could identify ASD. METHODS Both children with ASD and typical development (TD) were eye-tracked when they were engaged in a face-to-face conversation with an interviewer. Four ML classifiers (support vector machine, SVM; linear discriminant analysis, LDA; decision tree, DT; and random forest, RF) were used to determine the maximum classification accuracy and the corresponding features. RESULTS A maximum classification accuracy of 84.62% were achieved with three classifiers (LDA, DT and RF). Results showed that the mouth, but not the eyes AOI, was a powerful feature in detecting ASD. CONCLUSIONS Natural gaze behavior could be leveraged to identify ASD, suggesting that ASD might be objectively screened with eye tracking technology in everyday social interaction. In addition, the comparison between our and previous findings suggests that eye tracking features that could identify ASD might be culture dependent and context sensitive.

Mechanical evaluation of theories of neurulation using computer simulations

Development ◽  
1993 ◽  
Vol 118 (3) ◽  
pp. 1013-1023 ◽  
Author(s):  
D. A. Clausi ◽  
G. W. Brodland
Keyword(s):  
Computer Simulations ◽  
Driving Forces ◽  
Shape Change ◽  
Three Dimensional ◽  
Dorsal Surface ◽  
Neural Plate ◽  
Neural Tube Closure ◽  
Amphibian Embryo ◽  
Axial Elongation ◽  
Shape Changes

Current theories about the forces that drive neurulation shape changes are evaluated using computer simulations. Custom, three-dimensional, finite element-based computer software is used. The software draws on current engineering concepts and makes it possible to construct a ‘virtual’ embryo with any user-specified mechanical properties. To test a specific hypothesis about the forces that drive neurulation, the whole virtual embryo or any selected part of it is ascribed with the force generators specified in the hypothesis. The shape changes that are produced by these forces are then observed and compared with experimental data. The simulations demonstrate that, when uniform, isotropic circumferential microfilament bundle (CMB) constriction and cephalocaudal (axial) elongation act together on a circular virtual neural plate, it becomes keyhole shaped. When these forces act on a spherical (amphibian) embryo, dorsal surface flattening occurs. Simulations of transverse sections further show that CMB constriction, acting with or without axial elongation, can produce numerous salient transverse features of neurulation. These features include the sequential formation of distinct neural ridges, narrowing and thickening of the neural plate, skewing just medial to the ridges, ‘hinge’ formation and neural tube closure. No region-specific ‘programs’ or non-mechanical cell-cell communications are used. The increase in complexity results entirely from mechanical interactions. The transverse simulations show how changes to the driving forces would affect the patterns of shape change produced. Hypotheses regarding force generation by microtubules, intercellular adhesions and forces extrinsic to the neural plate are also evaluated. The simulations show that these force-generating mechanisms do not, by themselves, produce shape changes that are consistent with normal development. The simulations support the concept of cooperation of forces and suggest that neurulation is robust because redundant force generating mechanisms exist.

Bio-Inspired Optimization Algorithms for Arabic Handwritten Characters

2017 ◽  
pp. 897-914 ◽  
Author(s):  
Ahmed.T. Sahlol ◽  
Aboul Ella Hassanien
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Random Forests ◽  
Classification Accuracy ◽  
Processing Time ◽  
Optimization Algorithms ◽  
Nearest Neighbors ◽  
Benchmark Dataset ◽  
K Nearest Neighbors ◽  
Linear Discriminant

There are still many obstacles for achieving high recognition accuracy for Arabic handwritten optical character recognition system, each character has a different shape, as well as the similarities between characters. In this chapter, several feature selection-based bio-inspired optimization algorithms including Bat Algorithm, Grey Wolf Optimization, Whale optimization Algorithm, Particle Swarm Optimization and Genetic Algorithm have been presented and an application of Arabic handwritten characters recognition has been chosen to see their ability and accuracy to recognize Arabic characters. The experiments have been performed using a benchmark dataset, CENPARMI by k-Nearest neighbors, Linear Discriminant Analysis, and random forests. The achieved results show superior results for the selected features when comparing the classification accuracy for the selected features by the optimization algorithms with the whole feature set in terms of the classification accuracy and the processing time. The experiments have been performed using a benchmark dataset, CENPARMI by k-Nearest neighbors, Linear Discriminant Analysis, and random forests. The achieved results show superior results for the selected features when comparing the classification accuracy for the selected features by the optimization algorithms with the whole feature set in terms of the classification accuracy and the processing time.

Equivalence between LDA/QR and Direct LDA

2012 ◽  
pp. 338-353
Author(s):  
Rong-Hua Li ◽  
Shuang Liang ◽  
George Baciu ◽  
Eddie Chan
Keyword(s):  
Discriminant Analysis ◽  
Dimension Reduction ◽  
Linear Discriminant Analysis ◽  
Classification Accuracy ◽  
Qr Decomposition ◽  
Linear Discriminant ◽  
Qr Algorithm ◽  
Special Cases ◽  
Benchmark Datasets ◽  
Pseudo Inverse

Singularity problems of scatter matrices in Linear Discriminant Analysis (LDA) are challenging and have obtained attention during the last decade. Linear Discriminant Analysis via QR decomposition (LDA/QR) and Direct Linear Discriminant analysis (DLDA) are two popular algorithms to solve the singularity problem. This paper establishes the equivalent relationship between LDA/QR and DLDA. They can be regarded as special cases of pseudo-inverse LDA. Similar to LDA/QR algorithm, DLDA can also be considered as a two-stage LDA method. Interestingly, the first stage of DLDA can act as a dimension reduction algorithm. The experiment compares LDA/QR and DLDA algorithms in terms of classification accuracy, computational complexity on several benchmark datasets and compares their first stages. The results confirm the established equivalent relationship and verify their capabilities in dimension reduction.

Sign in / Sign up

Export Citation Format

Share Document