Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
42
datasets available to search
ShareScore release 0.9.0
Dataset results
42 results for “insect classification”
Fig. 4 in New species of mirid insects and their importance for the higher classification of plant bugs
Fig. 4. Photographs (A1, A3) and drawings (A2, A4) of femoral trichobothria in mirid insect Metoisops akingbohungbei Herczek and Popov, 2014, holotype male, CEHI BB M HE 4, from the Baltic Amber (unknown locality on Baltic Sea Coast), mid-Eocene. Five mesofemoral trichobothria (A1, A2); six metafemoral trichobothria (A3, A4). Scale bars 0.1 mm.
Fig. 3 in New species of mirid insects and their importance for the higher classification of plant bugs
Fig. 3. Mirid insect Metoisops popovi Kim, Taszakowski, and Jung, sp. nov., holotype female, CNU CNUHHMF005, from the Baltic Amber (unknown locality on Baltic Sea Coast), mid-Eocene. Dorsal habitus. Arrow points to deep incision between calli (A1), lateral habitus (A2), head in dorsal view (A3), head in lateral view (A4), scutellum (A5), hindfemur with trichobothria (A6).
Fig. 2 in New species of mirid insects and their importance for the higher classification of plant bugs
Fig. 2. Mirid insect Metoisops michalskii Kim, Taszakowski, and Herczek sp. nov., holotype male, DZUS HE44-451-1-001, from the Baltic Amber Gdańsk Bay, Poland), mid-Eocene. Dorsal habitus (A1), lateral habitus (A2), head and thorax in lateral view and antennal structure (A3), abdomen and legs in lateral view (A4), hindtarsus (A5), genital segment with parameres (A6). Abbreviations: i, first antennal segment; ii, second antennal segment; iii, third antennal segment; iv, fourth antennal segment; iv-1, first subsegment of fourth antennal segment; iv-2, second subsegment of fourth antennal segment.
Fig. 1 in New species of mirid insects and their importance for the higher classification of plant bugs
Fig. 1. Baltic ambers with specimens of mirid insects. A. Metoisops michalskii Kim, Taszakowski, and Herczek sp. nov., holotype male, DZUS HE44- 451-1-001, from the Baltic Amber (Vistula Spit, Gdańsk Bay, Poland), mid-Eocene. B. Metoisops popovi Kim, Taszakowski, and Jung sp. nov., holotype female, CNU CNUHHMF005, from the Baltic Amber (unknown locality on Baltic Sea Coast), mid-Eocene.
Image dataset for training of an insect classification model
<p> </p><p><strong>This version is deprecated! Please use the updated </strong><a href="https://doi.org/10.5281/zenodo.8325383"><strong>Insect Detect - insect classification dataset v2</strong></a><strong> with more images and classes.</strong></p><p> </p><p>This dataset contains images of various insects and some other arthropods, sitting on or flying above an artificial flower platform. All images were automatically recorded with the <a href="https://maxsitt.github.io/insect-detect-docs/">Insect Detect DIY camera trap</a>, a hardware combination of the Luxonis OAK-1, Raspberry Pi Zero 2 W and PiJuice Zero pHAT for automated insect monitoring (<a href="https://doi.org/10.1101/2023.12.05.570242">bioRxiv preprint</a>).</p><p>This classification dataset contains the cropped bounding boxes, exported from the <a href="https://universe.roboflow.com/maximilian-sittinger/insect_detect_detection/dataset/6">Insect_Detect_detection</a> dataset together with 290 new images of <i>Episyrphus balteatus</i>.</p><h2>Classes</h2><p>The following classes were annotated in this dataset:</p><ul><li><strong>wasp</strong> (mostly <i>Vespula</i> sp.)</li><li><strong>hbee</strong> (<i>Apis mellifera</i>)</li><li><strong>fly</strong> (mostly Brachycera)</li><li><strong>hovfly</strong> (various Syrphidae, e.g. <i>Eupeodes corollae</i>,<i> Scaeva pyrastri</i>)</li><li><strong>episyr_balt</strong> (<i>Episyrphus balteatus</i>)</li><li><strong>other</strong> (all Arthropods with insufficient occurences, e.g. various Hymenoptera, true bugs, beetles)</li><li><strong>shadow</strong> (shadows of the recorded insects)</li></ul><p>View the <a href="https://universe.roboflow.com/maximilian-sittinger/insect_detect_classification/health">Health Check</a> for more info on class balance.</p><h2>Deployment</h2><p>You can use this dataset as starting point to train your own insect classification models. Check the <a href="https://maxsitt.github.io/insect-detect-docs/modeltraining/train_classification/">model training instructions</a> for more information.</p><p>To deploy the image classification model (ONNX format) on your PC for fast CPU inference, follow the provided <a href="https://maxsitt.github.io/insect-detect-docs/deployment/classification/">Step by Step instructions</a>. Open source Python scripts to deploy the trained model can be found at the <a href="https://github.com/maxsitt/insect-detect-ml">insect-detect-ml GitHub repo</a>.</p>
Out-of-distribution detection algorithms for robust insect classification dataset and models
<p>This folder contains trained models and datasets for reproducing the results in the paper on out-of-distribution detection algorithms for robust insect classification. Specifically, it contains the following folders: </p> <p> </p> <ul> <li>OODInsect (out-of-distribution data)</li> <li>MSP, MAH, and EBM trained models, each wrapped around the three classifiers of ResNet50, RegNet32, and VGG11, and different combinations of ID and OOD test data for reproducing RQ1, RQ2, and RQ3.</li> <li>ID3 (in-distribution test data)</li> </ul>
FIGURES 6–9. Sugophytichnida pertusura Enushchenko and A in Revision of existing classification of fossil insect feeding traces and description of new ichnotaxa from Middle Jurassic sediments of Eastern Siberia (Russia)
FIGURES 6–9. Sugophytichnida pertusura Enushchenko and A. Frolov, ichnogen., ichnospec. nov. (specimen No Iya -2011- 14/17-2, Holotype): 6, 7—common view of S. pertusura, 8—S. pertusura, confied to the vein of Ginkgo tapkensis, 9—S. pertusura far from the vein of G. tapkensis.
FIGURE 16 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 16. Hendersonaspis anomala (Green), adult female, illustrated from type material. The dorsal surface is shown on the left and the ventral surface on the right. Below the main figure is an enlarged image of the pygidium. To the upper right of the main figure are enlarged images of an antenna, a perispiracular pore, and a ventral thoracic duct.
FIGURE 14 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 14. Phylogeny of the tribe Aonidiini (Aspidiotinae), whose relationship to other Aspidiotinae is shown in Fig. 3. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 17 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 17. Hendersonaspis anomala (Green), second-instar female, illustrated from type material. The dorsal surface is shown on the left and the ventral surface on the right. The small figure to the lower left shows a ventral view of the pygidium of the puparium (sclerotized cuticle of the second-instar female) with the caudal valve open and the pygidium of the adult female protruding. The other small figures show enlarged images of an antenna and a dorsal duct.
FIGURE 11 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 11. Phylogeny of the subtribe Chionaspidina (Diaspidinae: Diaspidini), whose relationship to the other Diaspidini is shown in Fig. 2. One clade is represented by triangular placeholder labelled "Chionaspis and allies". Its phylogeny can be seen in Fig. 12. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 9 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 9. Phylogeny of the grass-feeding clade of Fioriniina, including species heretofore placed in Kuwanaspidina (Diaspidinae: Diaspidini: Fioriniina). This figure shows the phylogeny of the clade labeled "grass-feeding Fioriniina" in Fig. 8. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 7 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 7. Phylogeny of the subtribe Diaspidina (Diaspidinae: Diaspidini), whose relationship to other Diaspidini is shown in Fig. 2. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 5 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 5. Phylogeny of Pseudoparlatoria Cockerell and allies (Diaspidinae: Lepidosaphidini). This figure shows the phylogeny of the clade labeled "Pseudoparlatoria sensu lato" in Fig. 4. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 19 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 19. Brimblecombia rotundicauda (Brimblecombe), adult female, ventral surface. Adapted from Brimblecombe (1959b).
FIGURE 3 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 3. Phylogeny of Aspidiotinae, whose relationship to the other subfamilies of Diaspididae is shown in Fig. 1. Triangular placeholders are used to represent 4 tribes, whose phylogeny is shown in one or more subsequent figures: Leucaspidini (Fig. 13), Aonidiini (Fig. 14), Parlatoriini (Fig. 15), and Aspidiotini (Figs. S1–S5). For Gymnaspidini and Odonaspidini, all sampled individuals are shown. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 20 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 20. Brimblecombia rotundicauda (Brimblecombe), adult female pygidium. Adapted from Brimblecombe (1959b). The dorsal surface is shown on the left and the ventral surface on the right.
FIGURE 4 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 4. Phylogeny of the tribe Lepidosaphidini (Diaspidinae), excluding Hulaspis. This is the clade labelled "other Lepidosaphidini" in Fig. 2, and its relationship to the other lineages of Diaspidinae is shown in that figure. Two clades are represented here by triangular placeholders, and an expanded view of the phylogeny of each can be seen in a subsequent figure: Pseudoparlatoria sensu lato (Fig. 5) and Lepidosaphes + Australian Lepidosaphidini (Fig. 6). For the rest of the tribe, all sampled individuals are shown. For further explanation of the analysis and notation, see the caption to Fig. 1.
FIGURE 1 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 1. Phylogenetic relationships of Diaspididae: outgroups, Ancepaspidinae and Furcaspidinae. This tree, resulting from a Bayesian analysis of 4 loci, includes 5 outgroup families and shows the relationships of the 4 diaspidid subfamilies under the proposed new classification, as well as relationships of sampled taxa within Ancepaspidinae and Furcaspidinae. The 2 larger subfamilies of Diaspididae, Diaspidinae and Aspidiotinae, are depicted here with triangular placeholders and shown in more detail in Figs. 2–15 and S1–S5. Note that Comstockiella, traditionally placed in within Diaspididae in the monotypic subfamily Comstockiellinae, is here depicted as a member of Halimococcidae. Figures 1–15 and S1–S5 represent the results of the Bayesian analysis of all 4 loci. Taxon names consist of the species name, the type of identification, the name or initials of the identifier, the country of origin, and the prep number. Identifiers are listed in Table 1. ID = identification based on morphological examination of that specimen itself on a microscope slide; lotID = identification based on morphological examination of 1 or more other specimens of the same series on a microscope slide; fieldID = identification in the field. Values given for internodes are posterior probabilities. Posterior probabilities under 0.5 and most of those within species have been omitted to reduce clutter. Species names are given as the combinations used prior to this study; for species transferred to new genera (Table 9), the new generic assignment is given at the end of the species name. Undescribed species are designated as "ud" followed by a number.
FIGURE 2 in Phylogeny and classification of armored scale insects (Hemiptera: Coccomorpha: Diaspididae)
FIGURE 2. Phylogeny of Diaspidinae, whose relationship to the other subfamilies of Diaspididae is shown in Fig. 1. Triangular placeholders are used to represent 4 large clades, whose phylogeny is shown in one or more subsequent figures: other Lepidosaphidini (Figs. 4–6), Diaspidina (Fig. 7), Fioriniina (Figs. 8–10), and Chionaspidina (Fig. 11). For the present we regard Furchadaspis, Prodiaspis, and Ischnaspis as Diaspidini incertae sedis, and we regard Unaspis as a member of Chionaspidina. For further explanation of the analysis and notation, see the caption to Fig. 1.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.