Insect DNA Barcode and Image Dataset
Notice bibliographique
Résumé
The data utilized in our experiments was obtained from the Barcode of Life Data System (BOLD), which is a cloud-based data storage and analysis platform developed at the Centre for Biodiversity Genomics in Canada. The insect_dataset.mat consists of 32424 image samples of insect species from four Insecta orders, Diptera, Coleoptera, Lepidoptera and Hymenoptera, each associated with a DNA barcode sequence of that sample. The unseen_insect_dataset.mat consists of 40050 image samples of insects from the same order, but all don't have an indicated species in the BOLD System, so they are real unclassified species (at the time of the dataset creation), having only the genus available, each one is also associated with a DNA barcode sequence of that sample. Description of the .mat: # Insect Dataset * all_images: vector containing the 32424 64x64x3 images (RGB) pre normalized of the insects* all_dnas: vector containing the 32424 DNA barcodes in one-hot encoding 658x5* all_labels: vector containing the species label for the corresponding DNA and image* all_boldids: vector of strings containing the id from boldsystemsv3 (https://v3.boldsystems.org/) they can be used to download from boldsystems the original DNA barcodes and the full size images and other data related to the sample* train_loc: indices of the training samples in all_dnas, all_images, all_labels, all_boldids* val_seen_loc: indices of the validation samples in all_dnas, all_images, all_labels, all_boldids that contain described(seen) species* val_unseen_loc: indices of the validation samples in all_dnas, all_images, all_labels, all_boldids that contain undescribed(unseen) species* test_seen_loc: indices of the test samples in all_dnas, all_images, all_labels, all_boldids that contain described(seen) species* test_unseen_loc: indices of the test samples in all_dnas, all_images, all_labels, all_boldids that contain undescribed(unseen) species* species2genus: the vector contains at index i the genus label of species with label i (e.g. species i has genus species2genus[i])* described_species_labels_train: vector containing the labels of species that appear in the training set* described_species_labels_trainval: vector containing the labels of species that appear in the training set and/or the validation set* all_dna_features_cnn_original: vector of features extractedfrom DNA nucleotides with the method of Badirli, S., Picard, C. J., Mohler, G.,Richert, F., Akata, Z., & Dundar, M. (2023). Classifying the unknown: Insect identification with deep hierarchical Bayesian learning. Methods in Ecology and Evolution, 14,1515-1530. https://doi.org/10.1111/2041-210X.14104* all_image_features_resnet: vector of features extracted from the insect images with the method of the same paper as the all_dna_features_cnn_original with a pretrained resnet101* all_dna_features_cnn_new: vector of features extracted from DNA nucleotides with our CNN* all_image_features_gan: vector of features extracted from the insect images with out method using a ReACGAN Description of the .mat: # Unseen Insect Dataset * all_images: vector containing the 40050 64x64x3 images (RGB) pre normalized of the insects* all_dnas: vector containing the 40050 DNA barcodes in one-hot encoding 658x5 * all_string_dnas: vector containing the 40050 DNA barcodes in string format* all_genus_labels: vector containing the species label for the corresponding DNA and image* all_boldids: vector of strings containing the id from boldsystemsv3 (https://v3.boldsystems.org/) they can be used to download from boldsystems the original DNA barcodes and the full size images and other data related to the sample* all_dna_features_cnn_original: vector of features extractedfrom DNA nucleotides with the method of Badirli, S., Picard, C. J., Mohler, G.,Richert, F., Akata, Z., & Dundar, M. (2023). Classifying the unknown: Insect identification with deep hierarchical Bayesian learning. Methods in Ecology and Evolution, 14,1515-1530. https://doi.org/10.1111/2041-210X.14104* all_image_features_resnet: vector of features extracted from the insect images with the method of the same paper as the all_dna_features_cnn_original with a pretrained resnet101* all_dna_features_cnn_new: vector of features extracted from DNA nucleotides with our CNN* all_image_features_gan: vector of features extracted from the insect images with out method using a ReACGAN Note: all arrays and locs are 1-indexed like in MATLAB. Note: the features were extracted with the same model for both the insect dataset and the unseen insect dataset.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,001 | 0,003 |
| Méta-épidémiologie (sens strict) | 0,002 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,002 | 0,003 |
| Études des sciences et des technologies | 0,001 | 0,000 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,002 | 0,002 |
| Intégrité de la recherche | 0,002 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,028 | 0,050 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».