This paper [1] presents an innovative approach to address the prevalent challenge of unbalanced datasets in coin type recognition, shifting the focus from coin class type recognition to coin mint recognition. Despite this shift, the issue of unbalanced data persists. To mitigate this, the authors introduce a method to split larger classes into smaller ones, integrating them into an 'additional class layer'.

Three distinct machine learning (ML) methodologies were employed to identify new possible classes, with one approach utilising unsupervised clustering alongside manual intervention, while the others leverage object detection, and Natural Language Processing (NLP) techniques. However, despite these efforts, overfitting remained a persistent issue, prompting the authors to explore alternative methods such as dataset improvement and Generative Adversarial Networks (GANs).

The paper contributes significantly to the intersection of ML techniques and archaeology, particularly in addressing overfitting challenges. Furthermore, the authors' candid acknowledgment of the limitations of their approaches serves as a valuable resource for researchers encountering similar obstacles.

This study stems from the D4N4 project, aimed at developing a machine learning-based coin recognition model for the extensive "Corpus Nummorum" dataset, comprising over 19,600 coin types and 49,000 coins from various ancient landscapes. Despite encountering challenges with overfitting due to the dataset's imbalance, the authors' exploration of multiple methodologies and transparent documentation of their limitations enriches the academic discourse and provides a foundation for future research in this field.

Reference

[1] Gampe, S. and Tolle, K. (2024). Creating an Additional Class Layer with Machine Learning to counter Overfitting in an Unbalanced Ancient Coin Dataset. Zenodo, 8298077, ver. 4 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.8298077

The paper (Callieri, M. et al. 2023) describes the “Dynamic Collections” project, an online platform initially created to showcase digital archaeological collections of Lund University. During a phase of testing by department members, new functionalities and artefacts were added resulting in an interactive platform adapted to university-level teaching and learning. The paper introduces into the topic and related works after which it starts to explain the project itself. The idea is to resemble the possibilities of interaction of non-digital collections in an online platform. Besides the objects themselves, the online platform offers annotations, measurement and other interactive tools based on the already known 3DHOP framework. With the possibility to create custom online collections a collaborative working/teaching environment can be created.

The already wide-spread use of the 3DHOP framework enabled the authors to develop some functionalities that could be used in the “Dynamic Collections” project. Also, current and future plans of the project are discussed and will include multiple 3D models for one object or permanent identifiers, which are both important additions to the system. The paper then continues to explain some of its further planned improvements, like comparisons and support for teaching, which will make the tool an important asset for future university-level education.

The paper in general is well-written and informative and introduces into the interactive tool, that is already available and working. It is very positive, that the authors rely on up-to-date methodologies in creating 3D online repositories and are in fact improving them by testing the tool in a teaching environment. They mention several times the alignment with upcoming EU efforts related to the European Collaborative Cloud for Cultural Heritage (ECCCH), which is anticipatory and far-sighted and adds to the longevity of the project. Comments of the reviewers were reasonably implemented and led to a clearer and more concise paper. I am very confident that this tool will find good use in heritage research and presentation as well as in university-level teaching and learning.

Although the authors never answer the introductory question explicitly (What characteristics should a virtual environment have in order to trigger dynamic interaction?), the paper gives the implicit answer by showing what the "Dynamic Collections" project has achieved and is able to achieve in the future.

Bibliography

Callieri, M., Berggren, Å., Dell'Unto, N., Derudas, P., Dininno, D., Ekengren, F., and Naponiello, G. (2023). The Dynamic Collections – a 3D Web Platform of Archaeological Artefacts designed for Data Reuse and Deep Interaction, Zenodo, 10067103, ver. 3 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.10067103