Data · dataset · 2025
Replication Data for: "REASSESSING DEEP LEARNING (AND META-LEARNING) COMPUTER VISION AS AN EFFICIENT METHOD TO DETERMINE TAPHONOMIC AGENCY IN BONE SURFACE MODIFICATIONS"
Listed in e-cienciaDatos
This repository contains the three image datasets and code used for the study of publication of the same title.
Description
The study analysed different types of bone surface modifications. Each dataset contains the raw images for each of the three code scripts.
To conduct k-fold validation, please create a folder within each dataset (named "k-fold"), where each type of mark resides in a separate folder, and copy the specific class images there. | Dataset 1 contains images of crocodile tooth marks and cut marks made with simple stone flakes. The original study was published in: Natalia Abellán, Enrique Baquedano, Manuel Domínguez-Rodrigo.2022. High-accuracy in the classification of butchery cut marks and crocodile tooth marks using machine learning methods and computer vision algorithms, Geobios, Volumes 72–73,Pages 12-21,doi.org/10.1016/j.geobios.2022.07.001.
Read the rest (3 more)
(sciencedirect.com/science/article/pii/S0016699522000377) Dataset 2 contains images of cut marks made with stone tools, tooth marks made by wolves and lions, and trampling marks made with sand and gravel. The original study was published in: Domínguez-Rodrigo, M., Cifuentes-Alcobendas, G., Jiménez-García, B. et al. Artificial intelligence provides greater accuracy in the classification of modern and ancient bone surface modifications.
Sci Rep 10, 18862 (2020). doi.org/10.1038/s41598-020-75994-7 Dataset 3 contains images of tooth scores made by bears, hyenas, lions and wolves, cut marks made with stone flakes, and trampling marks made with different types of sediments. The original study was published in: Pizarro-Monzo, M., Rosell, J., Rufà, A., Rivals, F., & Blasco, R. (2023). A deep learning-based taphonomical approach to distinguish the modifying agent in the Late Pleistocene site of Toll Cave (Barcelona, Spain).
Historical Biology, 36(10), 2114–2123. doi.org/10.1080/08912963.2023.2242370
Links
Where it is published
- Dataverse dataset page edatos.consorciomadrono.es/dataset.xhtml?persistentId=doi%3A10.7910%2FDVN%2FWUSGSW ↗
landing page · from edatos consorciomadrono es
- DOI doi.org/10.7910/dvn/wusgsw ↗
DOI / persistent id · from edatos consorciomadrono es
Catalogue records · 1
- Dataverse API edatos.consorciomadrono.es/api/datasets/:persistentId/?persistentId=doi%3A10.7910%2FDVN%2… ↗
metadata API · from edatos consorciomadrono es
Topics
- From keywords
- Computer Science & AI · Social Science
- Inferred from text
- Image 75% · Machine learning 70%
Provenance · 1 source records, 9 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| e-cienciaDatos | doi:10.7910/DVN/WUSGSW | 13 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[field].anzsrc:group:4611 | enrichment · edatos consorciomadrono es | taxonomy-embedding@1.1.0 | title+keywords+description (70%) |
| concepts[field].local:field:computer-science-ai | mapping · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | /subjects |
| concepts[field].local:field:social-science | mapping · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | /subjects |
| concepts[modality].local:modality:image | enrichment · edatos consorciomadrono es | keyword-concept-rules@1.0.0 | title+description (75%) |
| created_date | source · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | |
| description | source · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | /description |
| publication_date | source · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | |
| title | source · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 | /name |
| updated_date | source · edatos consorciomadrono es | connector:edatos_consorciomadrono_es@1.0.0 |