Search for: All records

Abstract Objective analytical identification methods are still a minority in the praxis of paleobiological sciences. Subjective interpretation of fossils and their modifications remains a nonreplicable expert endeavor. Identification of African bovids is a crucial element in the reconstruction of paleo‐landscapes, ungulate paleoecology, and, eventually, hominin adaptation and ecosystemic reconstruction. Recent analytical efforts drawing on Fourier functional analysis and discrimination methods applied to occlusal surfaces of teeth have provided a highly accurate framework to correctly classify African bovid tribes and taxa. Artificial intelligence tools, like computer vision, have also shown their potential to be objectively more accurate in the identification of taphonomic agency than human experts. For this reason, here we implement some of the most successful computer vision methods, using transfer learning and ensemble analysis, to classify bidimensional images of African bovid teeth and show that 92% of the large testing set of images of African bovid tribes analyzed could be correctly classified. This brings an objective tool to paleoecological interpretation, where bovid identification and paleoecological interpretation can be more confidently carried out. 

Abstract Researchers typically rely on fossils from the Family Bovidae to generate African paleoenvironmental reconstructions due to their strict ecological tendencies. Bovids have dominated the southern African fauna for the past four million years and, therefore, dominate the fossil faunal assemblages, especially isolated teeth. Traditionally, researchers reference modern and fossil comparative collections to identify teeth. However, researchers are limited by the specific type and number of bovids at each institution. B.O.V.I.D. (Bovidae Occlusal Visual IDentification) is a repository of images of the occlusal surface of bovid teeth. The dataset currently includes extant bovids from 7 tribes and 20 species (~3900). B.O.V.I.D. contains two scaled images per specimen: a color and a black and white (binarized) image. The database is a useful reference for identifying bovid teeth. The large sample size also allows one to observe the natural variation that exists in each taxa. The binarized images can be used in statistical shape analyses, such as taxonomic classification. B.O.V.I.D. is a valuable supplement to other methods for taxonomically identifying bovid teeth. 

We consider the problem of classifying curves when they are observed only partially on their parameter domains. We propose computational methods for (i) completion of partially observed curves; (ii) assessment of completion variability through a nonparametric multiple imputation procedure; (iii) development of nearest neighbor classifiers compatible with the completion techniques. Our contributions are founded on exploiting the geometric notion of shape of a curve, defined as those aspects of a curve that remain unchanged under translations, rotations and reparameterizations. Explicit incorporation of shape information into the computational methods plays the dual role of limiting the set of all possible completions of a curve to those with similar shape while simultaneously enabling more efficient use of training data in the classifier through shape-informed neighborhoods. Our methods are then used for taxonomic classification of partially observed curves arising from images of fossilized Bovidae teeth, obtained from a novel anthropological application concerning paleoenvironmental reconstruction.