Programmes > Par auteur > Chèze Laurence

Integration of microscopy, geometric morphometrics and machine learning classification algorithm for the identification of hand preference from stone tools
Alice Rodriguez * , Maria Gema Chacon  1, 2, 3, *@  , Raphaël Cornette  4, *@  , Emmanuelle Pouydebat  5, *@  , Marie-Hélène Moncel  6, *@  , Ameline Bardo * , Laurence Chèze  7, *@  , Radu Iovita  8, *@  , Antony Borel  9, 10, *@  
1 : Histoire naturelle de l\'Homme préhistorique  (HNHP)  -  Site web
Museum National d'Histoire Naturelle, Centre National de la Recherche Scientifique : UMR7194
Institut de Paléontologie Humaine 1, rue René Panhard 75013 Paris -  France
2 : IPHES  -  Site web
Zona Educacional 4 - Campus Sescelades URV (Edifici W3) 43007 - TARRAGONA -  Espagne
3 : Área de Prehistoria, Universidad Rovira i Virgili  (URV)  -  Site web
Facultad de Letras, Av. Catalunya 35, 43002, Tarragona -  Espagne
4 : Institut de Systématique, Evolution, Biodiversité  (ISYEB)  -  Site web
CNRS : UMR7205, Muséum National d'Histoire Naturelle (MNHN), Université Pierre et Marie Curie (UPMC) - Paris VI
57 rue Cuvier - CP 50 F- 75005 Paris -  France
5 : UMR 7179, CNRS-MNHN, Mécanismes adaptatifs, des organismes aux communautés.  (MECADEV)  -  Site web
Ministère de l'Ecologie, du Développement Durable et de l'Energie, Ministère de l'Enseignement Supérieur et de la Recherche, Muséum National d'Histoire Naturelle (MNHN), Centre national de la recherche scientifique - CNRS (France)
Pavillon d'anatomie comparée, 55 rue Buffon, case postale 55, 75231 Paris cedex 5. -  France
6 : Muséum National d'Histoire Naturelle  (MNHN)  -  Site web
Museum National d'Histoire Naturelle, Université de Perpignan Via Domitia, Centre National de la Recherche Scientifique : UMR7194
Institut de Paléontologie Humaine 1, rue René Panhard 75013 Paris -  France
7 : Laboratoire de Biomécanique et Mécanique des Chocs  (LBMC)  -  Site web
IFSTTAR UMR-T 9406, IFSTTAR-TS2, Université Claude Bernard - Lyon I (UCBL), PRES Université de Lyon
25, avenue François Mitterrand, Case24 Cité des mobilités F-69675 Bron Cedex -  France
8 : New York University  (NYU)
9 : Muséum National d'Histoire Naturelle  (MNHN)  -  Site web
UMR 7194 - Histoire Naturelle de l'Homme Préhistorique, UMR7194 - Histoire Naturelle de l'Homme Préhistorique
Musée de l'Homme 7, place du Trocadéro 75016 Paris -  France
10 : Institute of Archaeological Sciences, Eötvös Loránd University  (ELTE)  -  Site web
H-1053 Budapest, Egyetem tér 1-3 -  Hongrie
* : Auteur correspondant

Hand preference is related to areas of the brain linked to several critical functions such as language. Therefore, identifying hand preference in fossil hominids allows describing hand preference evolution but is also essential to characterize the origin and development of complex cognitive capabilities during human evolution. Stone tools, used during all periods and found extensively in archaeological sites, are likely to bear information about the hand which held them during repetitive activities. They are therefore of prime interest to provide new data about hand preference during evolution. However, only few studies, mainly focused on stone tool production, have been carried out with this purpose. Here we propose to focus on a repetitive activity which is very likely to embed better the information concerning hand preference: tool use. We aim at establishing an experimental protocol and a reference collection to build a model allowing determining the hand holding the stone during use.

Monitored experiment has been carried out and both classical use-wear analysis procedures and new quantitative method based on geometric morphometrics on used edges were performed. These techniques provided complementary information to select the best parameters to be used for hand preference inferences. Applying k-nearest neighbors algorithm, we were able to build a model with more than 76% accuracy in classifying stone tools used by right or left handed subjects. The method is still perfectible but already promising and the addition of new stone tools in the reference collection and of new parameters in the model is likely to increase the good classification rate.


Personnes connectées : 4 Flux RSS