A carregar...
2 resultados
Resultados da pesquisa
A mostrar 1 - 2 de 2
- Classifying polish in use-wear analysis with convolutional neural networksPublication . Eleftheriadou, Anastasia; Djellal, Youssef; McPherron, Shannon; Marreiros, JoaoLithic use-wear analysis examines micro- and macroscopic traces on tool surfaces resulting from human use and post-depositional processes. Polish, formed through surface abrasion with different materials, is a key diagnostic feature that is increasingly analyzed using machine learning to enhance automation and standardization. However, further research is needed to explore whether deep learning approaches, in particular, can be effectively applied to use-wear analysis and to determine the optimal surface area size (e.g., patch size and microscope objectives) and model architecture (custom vs. pre-trained) for achieving the best results. This study employs convolutional neural networks (CNNs) to classify experimental polish based on contact material (wood, hide, bone) and use intensity, while also assessing optimal imaging and analytical parameters. The results of this exploratory study suggest that CNNs may effectively identify polish from bone and hide but perform less effectively with wood. The models also successfully distinguish between polish formed by short- and long-term use. Custom models outperformed pre-trained ones, particularly when using images that captured smaller areas of the tool’s surface, suggesting that bigger surface areas may lack the necessary information for optimal results. These findings underscore the need to expand use-wear datasets in terms of size and variability and optimize CNN architectures and workflows.
- Unveiling the behavioural significance of the Aterian coarse-grained lithic assemblages: insights from use-wear analysis of Rhafas Cave, Northeast MoroccoPublication . Djellal, Youssef; Bouzouggar, Abdeljalil; Talbi, El Hassan; Longet, Benoit; Ghayati, Noufel; Pedergnana, Antonella; Marreiros, JoaoRecent discoveries have shown that Homo sapiens has a Pan-African origin, and North Africa has been an important region for the development and expansion of its biological and cultural traits. Early manifestations of Homo sapiens complex behaviour in North Africa are tied to the emergence of the Aterian culture around 150 ka BP. The Aterian repertoire includes stone, bone, and ivory tools, vegetal, animal and marine remains, as well as pigment and perforated shells for symbolic expressions. Within this cultural package, investigating the typotechnological variability observed in the stone tool assemblage is crucial to better understanding the emergence and development of Homo sapiens behaviour. However, the latter can only be fully reconstructed when complemented with the study of the tools’ function. Use-wear studies on Aterian lithics are very limited including coarse-grained materials despite their abundance in several Aterian sequences. This study presents the results of the use-wear analysis on the quartzite assemblage from the Aterian sequence of Rhafas cave. A use-wear experimental reference collection was created, against which the diagnostic use-wear on archaeological artefacts was compared. Sequential experiments demonstrated the dynamic performance and suitability of quartzite tools when subjected to mechanical stress during working of different materials. The analysis of the archaeological assemblage, guided by the experimental reference collection, revealed diagnostic use-wear associated with wood and bone working. In sum, our study shows the suitability, and the complementary role of quartzite tools in the technological versatility of the Aterian groups.