A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification
The concept of equifinality is currently one of the largest issues in taphonomy, frequently leading analysts to erroneously interpret the formation and functionality of archaeological and paleontological sites. An example of this equifinality can be found in the differentiation between anthropic cut...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/1/150 |
| _version_ | 1818519058358730752 |
|---|---|
| author | Lloyd A. Courtenay Rosa Huguet Diego González-Aguilera José Yravedra |
| author_facet | Lloyd A. Courtenay Rosa Huguet Diego González-Aguilera José Yravedra |
| author_sort | Lloyd A. Courtenay |
| collection | DOAJ |
| description | The concept of equifinality is currently one of the largest issues in taphonomy, frequently leading analysts to erroneously interpret the formation and functionality of archaeological and paleontological sites. An example of this equifinality can be found in the differentiation between anthropic cut marks and other traces on bone produced by natural agents, such as that of sedimentary abrasion and trampling. These issues are a key component in the understanding of early human evolution, yet frequently rely on qualitative features for their identification. Unfortunately, qualitative data is commonly susceptible to subjectivity, producing insecurity in research through analyst experience. The present study intends to confront these issues through a hybrid methodological approach. Here, we combine Geometric Morphometric data, 3D digital microscopy, and Deep Learning Neural Networks to provide a means of empirically classifying taphonomic traces on bone. Results obtained are able to reach over 95% classification, providing a possible means of overcoming taphonomic equifinality in the archaeological and paleontological register. |
| first_indexed | 2024-12-11T01:18:35Z |
| format | Article |
| id | doaj.art-6c3ed07d30224e9a9b07115d7014ac77 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T01:18:35Z |
| publishDate | 2019-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6c3ed07d30224e9a9b07115d7014ac772022-12-22T01:25:46ZengMDPI AGApplied Sciences2076-34172019-12-0110115010.3390/app10010150app10010150A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark ClassificationLloyd A. Courtenay0Rosa Huguet1Diego González-Aguilera2José Yravedra3Department of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, University of Salamanca, Hornos Caleros 50, 05003 Ávila, SpainÁrea de Prehistoria, Universitat Rovira i Virgili (URV), Avignuda de Catalunya 35, 43002 Tarragona, SpainDepartment of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, University of Salamanca, Hornos Caleros 50, 05003 Ávila, SpainDepartment of Prehistory, Complutense University, Prof. Aranguren s/n, 28040 Madrid, SpainThe concept of equifinality is currently one of the largest issues in taphonomy, frequently leading analysts to erroneously interpret the formation and functionality of archaeological and paleontological sites. An example of this equifinality can be found in the differentiation between anthropic cut marks and other traces on bone produced by natural agents, such as that of sedimentary abrasion and trampling. These issues are a key component in the understanding of early human evolution, yet frequently rely on qualitative features for their identification. Unfortunately, qualitative data is commonly susceptible to subjectivity, producing insecurity in research through analyst experience. The present study intends to confront these issues through a hybrid methodological approach. Here, we combine Geometric Morphometric data, 3D digital microscopy, and Deep Learning Neural Networks to provide a means of empirically classifying taphonomic traces on bone. Results obtained are able to reach over 95% classification, providing a possible means of overcoming taphonomic equifinality in the archaeological and paleontological register.https://www.mdpi.com/2076-3417/10/1/150taphonomymicroscopyequifinalityarchaeological data science |
| spellingShingle | Lloyd A. Courtenay Rosa Huguet Diego González-Aguilera José Yravedra A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification Applied Sciences taphonomy microscopy equifinality archaeological data science |
| title | A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification |
| title_full | A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification |
| title_fullStr | A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification |
| title_full_unstemmed | A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification |
| title_short | A Hybrid Geometric Morphometric Deep Learning Approach for Cut and Trampling Mark Classification |
| title_sort | hybrid geometric morphometric deep learning approach for cut and trampling mark classification |
| topic | taphonomy microscopy equifinality archaeological data science |
| url | https://www.mdpi.com/2076-3417/10/1/150 |
| work_keys_str_mv | AT lloydacourtenay ahybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT rosahuguet ahybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT diegogonzalezaguilera ahybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT joseyravedra ahybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT lloydacourtenay hybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT rosahuguet hybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT diegogonzalezaguilera hybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification AT joseyravedra hybridgeometricmorphometricdeeplearningapproachforcutandtramplingmarkclassification |