Neural network analysis by using the Self-Organizing Maps (SOMs) applied to human fossil dental morphology: A new methodology

Abstract

Recent studies focusing on dental morphology of extinct and extant human populations have shown, on a global scale, the considerable potential of dental traits as a tool to understand the phenetic relations existing between populations. The aim of this paper is to analyze the dental morphologic relationships between archaic Homo and anatomically modern Homo sapiens by means of a new methodology derived from artificial neural networks called Self Organizing Maps (SOMs). The graph obtained by SOMs to some extent recalls a classical Multidimensional Scaling (MDS) or a Principal Component Analysis (PCA) plot. The most important advantages of SOMs is that they can handle vectors with missing components without interpolating missing data. The analyzed database consisted of 1055 Lower-Middle and (Early) Late Pleistocene specimens, which were scored by using dental morphological traits of the Arizona State University Dental Anthropology System (ASUDAS). The principal result indicates a close relationship between the Homo erectus s.l. and Middle Pleistocene specimens and the later Neandertal groups. Furthermore, the dental models of anatomically modern Homo sapiens are particularly different compared to the more archaic populations. Thus, SOMs can be considered a valuable tool in the field of dental morphological studies since they enable the analysis of samples at an individual level without any need i) to interpolate missing data or ii) place individuals in predetermined groups.