Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology
Although the manual classification of microfossils is possible, it can become burdensome. Machine learning offers an alternative that allows for automatic classification. Our contribution is to use machine learning to develop an automated approach for classifying images of <i>Pectinodon bakker...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/7/2/45 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849431858485395456 |
|---|---|
| author | Jacob Bahn Germán H. Alférez Keith Snyder |
| author_facet | Jacob Bahn Germán H. Alférez Keith Snyder |
| author_sort | Jacob Bahn |
| collection | DOAJ |
| description | Although the manual classification of microfossils is possible, it can become burdensome. Machine learning offers an alternative that allows for automatic classification. Our contribution is to use machine learning to develop an automated approach for classifying images of <i>Pectinodon bakkeri</i> teeth. This can be expanded for use with many other species. Our approach is composed of two steps. First, PCA and K-means were applied to a numerical dataset with 459 samples collected at the Hanson Ranch Bonebed in eastern Wyoming, containing the following features: crown height, fore-aft basal length, basal width, anterior denticles, and posterior denticles per millimeter. The results obtained in this step were used to automatically organize the <i>P. bakkeri</i> images from two out of three clusters generated. Finally, the tooth images were used to train a convolutional neural network with two classes. The model has an accuracy of 71%, a precision of 71%, a recall of 70.5%, and an F1-score of 70.5%. |
| format | Article |
| id | doaj-art-c7fe28bad3224818920d8bfe29434a55 |
| institution | Kabale University |
| issn | 2504-4990 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj-art-c7fe28bad3224818920d8bfe29434a552025-08-20T03:27:29ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902025-05-01724510.3390/make7020045Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur MorphologyJacob Bahn0Germán H. Alférez1Keith Snyder2School of Computing, Southern Adventist University, 4881 Taylor Cir, Collegedale, TN 37315, USASchool of Computing, Southern Adventist University, 4881 Taylor Cir, Collegedale, TN 37315, USADepartment of Biology, Southern Adventist University, 4881 Taylor Cir, Collegedale, TN 37315, USAAlthough the manual classification of microfossils is possible, it can become burdensome. Machine learning offers an alternative that allows for automatic classification. Our contribution is to use machine learning to develop an automated approach for classifying images of <i>Pectinodon bakkeri</i> teeth. This can be expanded for use with many other species. Our approach is composed of two steps. First, PCA and K-means were applied to a numerical dataset with 459 samples collected at the Hanson Ranch Bonebed in eastern Wyoming, containing the following features: crown height, fore-aft basal length, basal width, anterior denticles, and posterior denticles per millimeter. The results obtained in this step were used to automatically organize the <i>P. bakkeri</i> images from two out of three clusters generated. Finally, the tooth images were used to train a convolutional neural network with two classes. The model has an accuracy of 71%, a precision of 71%, a recall of 70.5%, and an F1-score of 70.5%.https://www.mdpi.com/2504-4990/7/2/45microfossilsPrincipal Component Analysis (PCA)K-meansconvolutional neural network |
| spellingShingle | Jacob Bahn Germán H. Alférez Keith Snyder Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology Machine Learning and Knowledge Extraction microfossils Principal Component Analysis (PCA) K-means convolutional neural network |
| title | Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology |
| title_full | Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology |
| title_fullStr | Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology |
| title_full_unstemmed | Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology |
| title_short | Machine Learning Classification of Fossilized <i>Pectinodon bakkeri</i> Teeth Images: Insights into Troodontid Theropod Dinosaur Morphology |
| title_sort | machine learning classification of fossilized i pectinodon bakkeri i teeth images insights into troodontid theropod dinosaur morphology |
| topic | microfossils Principal Component Analysis (PCA) K-means convolutional neural network |
| url | https://www.mdpi.com/2504-4990/7/2/45 |
| work_keys_str_mv | AT jacobbahn machinelearningclassificationoffossilizedipectinodonbakkeriiteethimagesinsightsintotroodontidtheropoddinosaurmorphology AT germanhalferez machinelearningclassificationoffossilizedipectinodonbakkeriiteethimagesinsightsintotroodontidtheropoddinosaurmorphology AT keithsnyder machinelearningclassificationoffossilizedipectinodonbakkeriiteethimagesinsightsintotroodontidtheropoddinosaurmorphology |