Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204750504> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W3204750504 abstract "Ammonoid identification is crucial to biostratigraphy, systematic palaeontology, and evolutionary biology, but may prove difficult when shell features and sutures are poorly preserved. This necessitates novel approaches to ammonoid taxonomy. This study aimed to taxonomize ammonoids by their conch geometry using supervised and unsupervised machine learning algorithms. Ammonoid measurement data (conch diameter, whorl height, whorl width, and umbilical width) were taken from the Paleobiology Database (PBDB). 11 species with ≥50 specimens each were identified providing N=781 total unique specimens. Naive Bayes, Decision Tree, Random Forest, Gradient Boosting, K-Nearest Neighbours, Support Vector Machine, and Multilayer Perceptron classifiers were applied to the PBDB data with a 5x5 nested cross-validation approach to obtain unbiased generalization performance estimates across a grid search of algorithm parameters. All supervised classifiers achieved ≥70% accuracy in identifying ammonoid species, with Naive Bayes demonstrating the least over-fitting. The unsupervised clustering algorithms K-Means, DBSCAN, OPTICS, Mean Shift, and Affinity Propagation achieved Normalized Mutual Information scores of ≥0.6, with the centroid-based methods having most success. This presents a reasonably-accurate proof-of-concept approach to ammonoid classification which may assist identification in cases where more traditional methods are not feasible." @default.
- W3204750504 created "2021-10-11" @default.
- W3204750504 creator A5023889941 @default.
- W3204750504 date "2021-10-01" @default.
- W3204750504 modified "2023-10-16" @default.
- W3204750504 title "Performance of machine-learning approaches in identifying ammonoid species based on conch properties" @default.
- W3204750504 cites W1612577478 @default.
- W3204750504 cites W2178703576 @default.
- W3204750504 cites W3086565865 @default.
- W3204750504 cites W3094439952 @default.
- W3204750504 cites W3203900017 @default.
- W3204750504 cites W4205137642 @default.
- W3204750504 doi "https://doi.org/10.24072/pci.paleo.100010" @default.
- W3204750504 hasPublicationYear "2021" @default.
- W3204750504 type Work @default.
- W3204750504 sameAs 3204750504 @default.
- W3204750504 citedByCount "0" @default.
- W3204750504 crossrefType "journal-article" @default.
- W3204750504 hasAuthorship W3204750504A5023889941 @default.
- W3204750504 hasBestOaLocation W32047505041 @default.
- W3204750504 hasConcept C10485038 @default.
- W3204750504 hasConcept C119857082 @default.
- W3204750504 hasConcept C12267149 @default.
- W3204750504 hasConcept C127313418 @default.
- W3204750504 hasConcept C151730666 @default.
- W3204750504 hasConcept C153180895 @default.
- W3204750504 hasConcept C154945302 @default.
- W3204750504 hasConcept C169258074 @default.
- W3204750504 hasConcept C2781230701 @default.
- W3204750504 hasConcept C41008148 @default.
- W3204750504 hasConcept C52001869 @default.
- W3204750504 hasConceptScore W3204750504C10485038 @default.
- W3204750504 hasConceptScore W3204750504C119857082 @default.
- W3204750504 hasConceptScore W3204750504C12267149 @default.
- W3204750504 hasConceptScore W3204750504C127313418 @default.
- W3204750504 hasConceptScore W3204750504C151730666 @default.
- W3204750504 hasConceptScore W3204750504C153180895 @default.
- W3204750504 hasConceptScore W3204750504C154945302 @default.
- W3204750504 hasConceptScore W3204750504C169258074 @default.
- W3204750504 hasConceptScore W3204750504C2781230701 @default.
- W3204750504 hasConceptScore W3204750504C41008148 @default.
- W3204750504 hasConceptScore W3204750504C52001869 @default.
- W3204750504 hasLocation W32047505041 @default.
- W3204750504 hasOpenAccess W3204750504 @default.
- W3204750504 hasPrimaryLocation W32047505041 @default.
- W3204750504 hasRelatedWork W2096363641 @default.
- W3204750504 hasRelatedWork W2595988085 @default.
- W3204750504 hasRelatedWork W2979979539 @default.
- W3204750504 hasRelatedWork W2985924212 @default.
- W3204750504 hasRelatedWork W3127425528 @default.
- W3204750504 hasRelatedWork W3204641204 @default.
- W3204750504 hasRelatedWork W4205958290 @default.
- W3204750504 hasRelatedWork W4311106074 @default.
- W3204750504 hasRelatedWork W4320483443 @default.
- W3204750504 hasRelatedWork W4320494184 @default.
- W3204750504 isParatext "false" @default.
- W3204750504 isRetracted "false" @default.
- W3204750504 magId "3204750504" @default.
- W3204750504 workType "article" @default.