SlideShare ist ein Scribd-Unternehmen logo
1 von 15
Downloaden Sie, um offline zu lesen
Taxonomic classification of
digitized specimens using
machine learning
Rutger Vos
Taxonomic classification1
of digitized specimens2
using machine learning3
1.  To give the right taxonomic name to a thing, or at least
approximate it to a higher level (e.g. Genus, Family)
2.  Photographs of biological objects, e.g. from a natural
history collection and taken in a standardized setup
3.  Machine learning explores the study and construction of
algorithms that can learn from and make predictions on
data
Case study: slipper orchids
Slipper orchids
•  Traded illegally
•  Photographed “in the wild”
Case study: Javanese butterflies
Van Groenendael-Krijger collection
•  Collected in the 1930s
•  Photographed in standardized setup
Project structure overview
•  Open source, freely
available at:
github.com/naturalis
•  Designed as loosely
coupled, swappable
modules
•  Intended for re-use for
multiple cases
Project structure: reference images
photos [table]
id INTEGER NOT NULL
md5sum VARCHAR(32) NOT NULL
path VARCHAR(255)
title VARCHAR(100)
description VARCHAR(255)
photos_tags [table]
photo_id INTEGER NOT NULL
tag_id INTEGER NOT NULL
tags [table]
id INTEGER NOT NULL
name VARCHAR(50) NOT NULL
photos_taxa [table]
photo_id INTEGER NOT NULL
taxon_id INTEGER NOT NULL
taxa [table]
id INTEGER NOT NULL
rank_id INTEGER NOT NULL
name VARCHAR(50) NOT NULL
description VARCHAR(255)
ranks [table]
id INTEGER NOT NULL
name VARCHAR(50) NOT NULL
Project structure: image processing
Speeded Up Robust Features
Project structure: machine learning
Project structure: optimization
Project structure: user interface
Results: SURF features
•  PCA plots of the “speeded up robust
features” show clustering both at the
genus (top) and species (bottom) level
•  Some species are so dimorphic that
the sexes are treated as separate
species (not shown)
•  Some individuals are
“gynandromorphic”, though there is
likely positive collection bias
•  Some taxa are much more variable
than others
Results: k-folds cross-validation
•  Split the data in k (2, 5, 10) partitions
•  Train on 1 partition, use k-1 as “out-of-sample” data
•  Count number of correct/incorrect/unknown identifications
Next steps
•  Application of trained neural networks to the entire
VGKS collection (once that is fully digitized)
•  Testing other classifiers in addition to ANNs
•  Improvement of the end user interface, possibly
as a native ‘app’ or on the web
•  Extension of the platform to additional cases,
such as shells (snails, bivalves)
•  Do more with the image feature data: mimicry,
character displacement, dimorphism
Acknowledgements
Naturalis sector Collection
•  Max Caspers
•  Luc Willemse
•  Jan Moonen
•  Digitization volunteers
Hogeschool Leiden
•  Barbara Gravendeel
•  Patrick Wijntjes
•  Saskia de Vetter
LIACS
•  Fons Verbeek
•  Mengke Li
•  Yuanhao Guo
IBL
•  Wim van Tongeren
WUR
•  Feia Matthijssen
Made possible by
•  Naturalis internal grant for
application-oriented research
•  The Van Groenendael-Krijger
Stichting
•  Kind contributions of photos by
numerous orchid breeders
Thanks for
listening!

Weitere ähnliche Inhalte

Andere mochten auch

Monera and protista
Monera and protistaMonera and protista
Monera and protistaJojo Johnson
 
Unit 4: Monera, Protoctist, Fungi and Plants
Unit 4: Monera, Protoctist, Fungi and PlantsUnit 4: Monera, Protoctist, Fungi and Plants
Unit 4: Monera, Protoctist, Fungi and PlantsMónica
 
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylums
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal PhylumsKingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylums
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylumswww.sciencepowerpoint.com
 
Animal Kingdom
Animal KingdomAnimal Kingdom
Animal Kingdomitutor
 
Animals classification
Animals classificationAnimals classification
Animals classificationjoseklo
 

Andere mochten auch (9)

Monera and protista
Monera and protistaMonera and protista
Monera and protista
 
Unit 4: Monera, Protoctist, Fungi and Plants
Unit 4: Monera, Protoctist, Fungi and PlantsUnit 4: Monera, Protoctist, Fungi and Plants
Unit 4: Monera, Protoctist, Fungi and Plants
 
Kingdom Animalia
Kingdom AnimaliaKingdom Animalia
Kingdom Animalia
 
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylums
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal PhylumsKingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylums
Kingdom Animalia Biology Lesson PowerPoint, Taxonomy, Animal Phylums
 
Kingdom animalia
Kingdom animaliaKingdom animalia
Kingdom animalia
 
Kingdom Animalia
Kingdom AnimaliaKingdom Animalia
Kingdom Animalia
 
Animal Kingdom
Animal KingdomAnimal Kingdom
Animal Kingdom
 
Power Point Animals
Power Point AnimalsPower Point Animals
Power Point Animals
 
Animals classification
Animals classificationAnimals classification
Animals classification
 

Ähnlich wie Taxonomic classification of digitized specimens using machine learning

Foundations for the Future of Science
Foundations for the Future of ScienceFoundations for the Future of Science
Foundations for the Future of ScienceGlobus
 
Learning, Training,  Classification,  Common Sense and Exascale Computing
Learning, Training,  Classification,  Common Sense and Exascale ComputingLearning, Training,  Classification,  Common Sense and Exascale Computing
Learning, Training,  Classification,  Common Sense and Exascale ComputingJoel Saltz
 
Keynote IEEE International Workshop on Cloud Analytics. Dennis Gannon
Keynote IEEE International Workshop on Cloud Analytics. Dennis  GannonKeynote IEEE International Workshop on Cloud Analytics. Dennis  Gannon
Keynote IEEE International Workshop on Cloud Analytics. Dennis GannonMicrosoft Azure for Research
 
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...DeVonne Parks, CEM
 
Slicing and Dicing a Newspaper Corpus for Historical Ecology Research
Slicing and Dicing a Newspaper Corpus for Historical Ecology ResearchSlicing and Dicing a Newspaper Corpus for Historical Ecology Research
Slicing and Dicing a Newspaper Corpus for Historical Ecology ResearchMarieke van Erp
 
Using Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and FriendsUsing Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and Friendslucenerevolution
 
Using Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and FriendsUsing Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and Friendslucenerevolution
 
Large Scale Data Mining using Genetics-Based Machine Learning
Large Scale Data Mining using   Genetics-Based Machine LearningLarge Scale Data Mining using   Genetics-Based Machine Learning
Large Scale Data Mining using Genetics-Based Machine LearningXavier Llorà
 
Biomedical Atlas Centre
Biomedical Atlas CentreBiomedical Atlas Centre
Biomedical Atlas CentreELIXIR UK
 
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...Spark Summit
 
Transfer learning for unsupervised influenza-like illness models from online ...
Transfer learning for unsupervised influenza-like illness models from online ...Transfer learning for unsupervised influenza-like illness models from online ...
Transfer learning for unsupervised influenza-like illness models from online ...Vasileios Lampos
 
Introduction to Next Generation Sequencing
Introduction to Next Generation SequencingIntroduction to Next Generation Sequencing
Introduction to Next Generation SequencingEdizonJambormias2
 
The Future of Microalgal Taxonomy
The Future of Microalgal TaxonomyThe Future of Microalgal Taxonomy
The Future of Microalgal TaxonomyAnne Thessen
 
Chapter-OBDD.pptx
Chapter-OBDD.pptxChapter-OBDD.pptx
Chapter-OBDD.pptxXanGwaps
 
clustering-151017180103-lva1-app6892 (1).pdf
clustering-151017180103-lva1-app6892 (1).pdfclustering-151017180103-lva1-app6892 (1).pdf
clustering-151017180103-lva1-app6892 (1).pdfprasad761467
 

Ähnlich wie Taxonomic classification of digitized specimens using machine learning (20)

Foundations for the Future of Science
Foundations for the Future of ScienceFoundations for the Future of Science
Foundations for the Future of Science
 
Learning, Training,  Classification,  Common Sense and Exascale Computing
Learning, Training,  Classification,  Common Sense and Exascale ComputingLearning, Training,  Classification,  Common Sense and Exascale Computing
Learning, Training,  Classification,  Common Sense and Exascale Computing
 
Keynote IEEE International Workshop on Cloud Analytics. Dennis Gannon
Keynote IEEE International Workshop on Cloud Analytics. Dennis  GannonKeynote IEEE International Workshop on Cloud Analytics. Dennis  Gannon
Keynote IEEE International Workshop on Cloud Analytics. Dennis Gannon
 
SAX-VSM
SAX-VSMSAX-VSM
SAX-VSM
 
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...
December 2, 2015: NISO/NFAIS Virtual Conference: Semantic Web: What's New and...
 
Slicing and Dicing a Newspaper Corpus for Historical Ecology Research
Slicing and Dicing a Newspaper Corpus for Historical Ecology ResearchSlicing and Dicing a Newspaper Corpus for Historical Ecology Research
Slicing and Dicing a Newspaper Corpus for Historical Ecology Research
 
Using Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and FriendsUsing Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and Friends
 
Using Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and FriendsUsing Lucene/Solr to Build CiteSeerX and Friends
Using Lucene/Solr to Build CiteSeerX and Friends
 
Large Scale Data Mining using Genetics-Based Machine Learning
Large Scale Data Mining using   Genetics-Based Machine LearningLarge Scale Data Mining using   Genetics-Based Machine Learning
Large Scale Data Mining using Genetics-Based Machine Learning
 
Biomedical Atlas Centre
Biomedical Atlas CentreBiomedical Atlas Centre
Biomedical Atlas Centre
 
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...
Escaping Flatland: Interactive High-Dimensional Data Analysis in Drug Discove...
 
STEM in 3D
STEM in 3DSTEM in 3D
STEM in 3D
 
Approaches to Mining Large-Scale Heterogeneous Data: Old and New
Approaches to Mining Large-Scale Heterogeneous Data: Old and NewApproaches to Mining Large-Scale Heterogeneous Data: Old and New
Approaches to Mining Large-Scale Heterogeneous Data: Old and New
 
Transfer learning for unsupervised influenza-like illness models from online ...
Transfer learning for unsupervised influenza-like illness models from online ...Transfer learning for unsupervised influenza-like illness models from online ...
Transfer learning for unsupervised influenza-like illness models from online ...
 
Introduction to Next Generation Sequencing
Introduction to Next Generation SequencingIntroduction to Next Generation Sequencing
Introduction to Next Generation Sequencing
 
Open science 2014
Open science 2014Open science 2014
Open science 2014
 
The Future of Microalgal Taxonomy
The Future of Microalgal TaxonomyThe Future of Microalgal Taxonomy
The Future of Microalgal Taxonomy
 
Chapter-OBDD.pptx
Chapter-OBDD.pptxChapter-OBDD.pptx
Chapter-OBDD.pptx
 
Clustering
ClusteringClustering
Clustering
 
clustering-151017180103-lva1-app6892 (1).pdf
clustering-151017180103-lva1-app6892 (1).pdfclustering-151017180103-lva1-app6892 (1).pdf
clustering-151017180103-lva1-app6892 (1).pdf
 

Mehr von Rutger Vos

Anna Karenina on hooves - what makes an animal fit for domestication?
Anna Karenina on hooves - what makes an animal fit for domestication?Anna Karenina on hooves - what makes an animal fit for domestication?
Anna Karenina on hooves - what makes an animal fit for domestication?Rutger Vos
 
10 Misverstanden Over Evolutie
10 Misverstanden Over Evolutie10 Misverstanden Over Evolutie
10 Misverstanden Over EvolutieRutger Vos
 
Crash Course Biodiversiteit
Crash Course BiodiversiteitCrash Course Biodiversiteit
Crash Course BiodiversiteitRutger Vos
 
Natural history research as a replicable data science
Natural history research as a replicable data scienceNatural history research as a replicable data science
Natural history research as a replicable data scienceRutger Vos
 
Species delimitation - species limits and character evolution
Species delimitation - species limits and character evolutionSpecies delimitation - species limits and character evolution
Species delimitation - species limits and character evolutionRutger Vos
 
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.Rutger Vos
 
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...Rutger Vos
 
Assembling the Tree of Life from public DNA sequence data
Assembling the Tree of Life from public DNA sequence dataAssembling the Tree of Life from public DNA sequence data
Assembling the Tree of Life from public DNA sequence dataRutger Vos
 
Hoe leer je een robot soorten te herkennen?
Hoe leer je een robot soorten te herkennen?Hoe leer je een robot soorten te herkennen?
Hoe leer je een robot soorten te herkennen?Rutger Vos
 
Modeling the biosphere: the natural historian's perspective
Modeling the biosphere: the natural historian's perspectiveModeling the biosphere: the natural historian's perspective
Modeling the biosphere: the natural historian's perspectiveRutger Vos
 
Kunnen we een tomaat van 400 jaar oud proeven
Kunnen we een tomaat van 400 jaar oud proevenKunnen we een tomaat van 400 jaar oud proeven
Kunnen we een tomaat van 400 jaar oud proevenRutger Vos
 
PhyloTastic: names-based phyloinformatic data integration
PhyloTastic: names-based phyloinformatic data integrationPhyloTastic: names-based phyloinformatic data integration
PhyloTastic: names-based phyloinformatic data integrationRutger Vos
 
SUPERSMART pipeline intro
SUPERSMART pipeline introSUPERSMART pipeline intro
SUPERSMART pipeline introRutger Vos
 
Reconstructing paleoenvironments using metagenomics
Reconstructing paleoenvironments using metagenomicsReconstructing paleoenvironments using metagenomics
Reconstructing paleoenvironments using metagenomicsRutger Vos
 
Synthesising disparate data resources to obtain composite estimates of geophy...
Synthesising disparate data resources to obtain composite estimates of geophy...Synthesising disparate data resources to obtain composite estimates of geophy...
Synthesising disparate data resources to obtain composite estimates of geophy...Rutger Vos
 
The Galaxy bioinformatics workflow environment
The Galaxy bioinformatics workflow environmentThe Galaxy bioinformatics workflow environment
The Galaxy bioinformatics workflow environmentRutger Vos
 
Retrieving useful information from connected specimen- and data collections
Retrieving useful information from connected specimen- and data collectionsRetrieving useful information from connected specimen- and data collections
Retrieving useful information from connected specimen- and data collectionsRutger Vos
 
NeXML - phylogenetic data as XML
NeXML - phylogenetic data as XMLNeXML - phylogenetic data as XML
NeXML - phylogenetic data as XMLRutger Vos
 
Vos at NCB Naturalis
Vos at NCB NaturalisVos at NCB Naturalis
Vos at NCB NaturalisRutger Vos
 

Mehr von Rutger Vos (20)

Anna Karenina on hooves - what makes an animal fit for domestication?
Anna Karenina on hooves - what makes an animal fit for domestication?Anna Karenina on hooves - what makes an animal fit for domestication?
Anna Karenina on hooves - what makes an animal fit for domestication?
 
10 Misverstanden Over Evolutie
10 Misverstanden Over Evolutie10 Misverstanden Over Evolutie
10 Misverstanden Over Evolutie
 
Crash Course Biodiversiteit
Crash Course BiodiversiteitCrash Course Biodiversiteit
Crash Course Biodiversiteit
 
Natural history research as a replicable data science
Natural history research as a replicable data scienceNatural history research as a replicable data science
Natural history research as a replicable data science
 
Species delimitation - species limits and character evolution
Species delimitation - species limits and character evolutionSpecies delimitation - species limits and character evolution
Species delimitation - species limits and character evolution
 
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.
Onderzoek bio-informatica Naturalis. Raad voor Cultuur 2017.
 
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...
Self-Updating Platform for the Estimation of Rates of Speciation, Migration A...
 
Assembling the Tree of Life from public DNA sequence data
Assembling the Tree of Life from public DNA sequence dataAssembling the Tree of Life from public DNA sequence data
Assembling the Tree of Life from public DNA sequence data
 
Hoe leer je een robot soorten te herkennen?
Hoe leer je een robot soorten te herkennen?Hoe leer je een robot soorten te herkennen?
Hoe leer je een robot soorten te herkennen?
 
Modeling the biosphere: the natural historian's perspective
Modeling the biosphere: the natural historian's perspectiveModeling the biosphere: the natural historian's perspective
Modeling the biosphere: the natural historian's perspective
 
Kunnen we een tomaat van 400 jaar oud proeven
Kunnen we een tomaat van 400 jaar oud proevenKunnen we een tomaat van 400 jaar oud proeven
Kunnen we een tomaat van 400 jaar oud proeven
 
PhyloTastic: names-based phyloinformatic data integration
PhyloTastic: names-based phyloinformatic data integrationPhyloTastic: names-based phyloinformatic data integration
PhyloTastic: names-based phyloinformatic data integration
 
SUPERSMART pipeline intro
SUPERSMART pipeline introSUPERSMART pipeline intro
SUPERSMART pipeline intro
 
Reconstructing paleoenvironments using metagenomics
Reconstructing paleoenvironments using metagenomicsReconstructing paleoenvironments using metagenomics
Reconstructing paleoenvironments using metagenomics
 
Synthesising disparate data resources to obtain composite estimates of geophy...
Synthesising disparate data resources to obtain composite estimates of geophy...Synthesising disparate data resources to obtain composite estimates of geophy...
Synthesising disparate data resources to obtain composite estimates of geophy...
 
The Galaxy bioinformatics workflow environment
The Galaxy bioinformatics workflow environmentThe Galaxy bioinformatics workflow environment
The Galaxy bioinformatics workflow environment
 
Retrieving useful information from connected specimen- and data collections
Retrieving useful information from connected specimen- and data collectionsRetrieving useful information from connected specimen- and data collections
Retrieving useful information from connected specimen- and data collections
 
NeXML - phylogenetic data as XML
NeXML - phylogenetic data as XMLNeXML - phylogenetic data as XML
NeXML - phylogenetic data as XML
 
Vos at NCB Naturalis
Vos at NCB NaturalisVos at NCB Naturalis
Vos at NCB Naturalis
 
Tree of Life
Tree of LifeTree of Life
Tree of Life
 

Kürzlich hochgeladen

Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINsankalpkumarsahoo174
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfSumit Kumar yadav
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.Nitya salvi
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoSérgio Sacani
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfrohankumarsinghrore1
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bSérgio Sacani
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticssakshisoni2385
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Sérgio Sacani
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSSLeenakshiTyagi
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 

Kürzlich hochgeladen (20)

Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on Io
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSS
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 

Taxonomic classification of digitized specimens using machine learning

  • 1. Taxonomic classification of digitized specimens using machine learning Rutger Vos
  • 2. Taxonomic classification1 of digitized specimens2 using machine learning3 1.  To give the right taxonomic name to a thing, or at least approximate it to a higher level (e.g. Genus, Family) 2.  Photographs of biological objects, e.g. from a natural history collection and taken in a standardized setup 3.  Machine learning explores the study and construction of algorithms that can learn from and make predictions on data
  • 3. Case study: slipper orchids Slipper orchids •  Traded illegally •  Photographed “in the wild”
  • 4. Case study: Javanese butterflies Van Groenendael-Krijger collection •  Collected in the 1930s •  Photographed in standardized setup
  • 5. Project structure overview •  Open source, freely available at: github.com/naturalis •  Designed as loosely coupled, swappable modules •  Intended for re-use for multiple cases
  • 6. Project structure: reference images photos [table] id INTEGER NOT NULL md5sum VARCHAR(32) NOT NULL path VARCHAR(255) title VARCHAR(100) description VARCHAR(255) photos_tags [table] photo_id INTEGER NOT NULL tag_id INTEGER NOT NULL tags [table] id INTEGER NOT NULL name VARCHAR(50) NOT NULL photos_taxa [table] photo_id INTEGER NOT NULL taxon_id INTEGER NOT NULL taxa [table] id INTEGER NOT NULL rank_id INTEGER NOT NULL name VARCHAR(50) NOT NULL description VARCHAR(255) ranks [table] id INTEGER NOT NULL name VARCHAR(50) NOT NULL
  • 7. Project structure: image processing Speeded Up Robust Features
  • 11. Results: SURF features •  PCA plots of the “speeded up robust features” show clustering both at the genus (top) and species (bottom) level •  Some species are so dimorphic that the sexes are treated as separate species (not shown) •  Some individuals are “gynandromorphic”, though there is likely positive collection bias •  Some taxa are much more variable than others
  • 12. Results: k-folds cross-validation •  Split the data in k (2, 5, 10) partitions •  Train on 1 partition, use k-1 as “out-of-sample” data •  Count number of correct/incorrect/unknown identifications
  • 13. Next steps •  Application of trained neural networks to the entire VGKS collection (once that is fully digitized) •  Testing other classifiers in addition to ANNs •  Improvement of the end user interface, possibly as a native ‘app’ or on the web •  Extension of the platform to additional cases, such as shells (snails, bivalves) •  Do more with the image feature data: mimicry, character displacement, dimorphism
  • 14. Acknowledgements Naturalis sector Collection •  Max Caspers •  Luc Willemse •  Jan Moonen •  Digitization volunteers Hogeschool Leiden •  Barbara Gravendeel •  Patrick Wijntjes •  Saskia de Vetter LIACS •  Fons Verbeek •  Mengke Li •  Yuanhao Guo IBL •  Wim van Tongeren WUR •  Feia Matthijssen Made possible by •  Naturalis internal grant for application-oriented research •  The Van Groenendael-Krijger Stichting •  Kind contributions of photos by numerous orchid breeders