Innovative multidisciplinary method using Machine Learning to define human behaviors and environments during the Caune de l'Arago (Tautavel, France) Middle Pleistocene occupations.
Résumé
SCHOPPER ANR project aim to develop a method to test research hypotheses using Machine Learning and immersives virtual environments. After 54 years of excavations, the Caune de l'Arago cave delivers a large amount of raw data and many archaeometric databases were developed through the study of this Lower Paleolithic site. The current tests focused on the evaluation of paleoenvironmental conditions and behavioral ones in each archaeological levels between 560,000 years and 90,000 years BP. All archaeological and environmental variable providing information on these issues were collected and organized by the multidisciplinary team to be studied by Machine Learning approach able to build models based on current repositories or Expert hypothesis, to learn on these models and then classify the archeological levels according to these patterns. The different steps of this innovative method are presented in this paper.
Fichier principal
Innovative multidisciplinary method using Machine.pdf (18.73 Mo)
Télécharger le fichier
| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|