Artificial neural networks and geometric morphometric methods as a means for classification: A case‐study using teeth from Carcharhinus sp. (Carcharhinidae)

Abstract

Over the past few decades, geometric morphometric methods have become increasingly popular and powerful tools to describe morphological data while over the same period artificial neural networks have had a similar rise in the classification of specimens to preconceived groups. However, there has been little research into how well these two systems operate together, particularly in comparison to preexisting techniques. In this study, geometric morphometric data and multilayer perceptrons, a style of artificial neural network, were used to classify shark teeth from the genus Carcharhinus to species. Three datasets of varying size and species differences were used. We compared the performance of this combination with geometric morphometric data in a linear discriminate function analysis, linear measurements in a linear discriminate function analysis, and a preexisting methodology from the literature that incorporates linear measurements and a two-layered discriminate function analysis. Across datasets, geometric morphometric data in a multilayer perceptron tended to yield modest accuracies but accuracies that varied less across species whereas other methods were able to achieve higher accuracies in some species at the expense of lower accuracies in others. Further, the performance of the two-layered discriminate function analysis illustrates that constraining what material is classified can increase the accuracy of a method. Based on this tradeoff, the best methodology will then depend on the scope of the study and the amount of material available. J. Morphol. 278:131-141, 2017. ©© 2016 Wiley Periodicals,Inc.

A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification

“…The present study additionally complements previous efforts to implement ML algorithms in Geometric Morphometric analyses, expanding the available toolbox for morphological studies [26,[61][62][63][64][65][66]. Courtenay et al [26]'s original attempts to implement neural network architectures for tooth mark classification performed poorly, attributed by the authors to the model's superficial nature.…”

“…These results thus confirm model configuration and tuning to be essential for efficient classification, requiring extensive experimentation to find the optimal model. This would also explain the mixed results obtained by similarly superficial models in applications for systematic biology [61][62][63][64][65][66].…”

Three-Dimensional Dental Analysis for Sex Estimation in the Italian Population: A Pilot Study Based on a Geometric Morphometric and Artificial Neural Network Approach

“…The use of ANNs combined with GMA has been compared with classical methods of classification (linear or quadratic discriminate analysis) by Soda and et al [ 26 ]. They demonstrated that ANNs yielded the most stable accuracy among the analyzed groups.…”

The intraspecific diversity of tooth morphology in the large‐spotted catshark Scyliorhinus stellaris: insights into the ontogenetic cues driving sexual dimorphism

“…These approaches mainly base the tooth shape analysis on main cusp dimensions, which do not capture complex heterodonty patterns (Whitenack and Gottfried, 2010). Recent publications, however, have focused on quantitative tooth traits in sharks by using geometric morphometrics (Marramà and Kriwet, 2017; Soda et al ., 2017; Cullen and Marshall, 2019), providing more subtle information on tooth size and shape quantitative variation. These comparative studies allow to infer developmental and phylogenetic hypotheses and refine our knowledge about the inter‐ and intraspecific tooth shape variation in several shark species.…”