Using digital archaeology and machine learning to determine sex in finger flutings

Published

2-12-2025

Type of Work

Conference Presentation

Advisors and Contributors

Many thanks to the co-authors of the paper, April Nowell and Keryn Walshe, and to the participants who contributed samples of finger flutings for the tactile and virtual experiments. We would also like the acknowledge the Mirning People and Koonalda Cave for inspiring this work.

Project Affiliation

Griffith University AEL; Australia Research Council Discovery Early Career Research Award; Social Sciences and Humanities Research Council of Canada

Abstract

One of the earliest and most enigmatic forms of rock art are finger flutings. Previous methods of studying them relied on biometric finger ratios from modern populations to make assumptions about the people who left the flutings—an approach that is both theoretically and methodologically problematic. This study presents a proof-of-concept for a paradigm shift away from error-prone human measurements and controversial theories, toward computational digital archaeology methods using an innovative experimental design that integrates tactile, virtual, and machine learning approaches. We conducted a digital archaeology experiment using tactile and virtual samples from 96 participants. A machine learning model was trained on this known dataset to determine the sex of the individuals who made the flutings. While the virtual dataset lacked sufficiently distinct features for reliable sex classification, the tactile experiment showed promising potential for identifying the sex of fluting artists. However, a larger sample size is needed to support generalization. The significant contribution of this study is the development of a foundational set of methods and materials. We offer a novel digital archaeology framework for data creation, collection, and analysis that is replicable, scalable, and quantifiable.

Citation

Jalandoni, A., Haubt, R., Farrar, C., Tuxworth, G., Zhang, Z. (2025) Using digital archaeology and machine learning to determine sex in finger flutings. Poster Session. Australian Archaeological Association Conference, Perth, 2025. https://www.aaaconference.com.au/wp-content/uploads/2025/11/Calum-Farrar-Poster.pdf

Income (grants or other funding)

Other

This project was funded by a 2023 Griffith University AEL Research Project Grant, Australia Research Council Discovery Early Career Research Award (DE240100030), and Social Sciences and Humanities Research Council of Canada Insight Grant (#435-2019-0656).

Link to Full Text

Share

COinS