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.
34
datasets available to search
ShareScore release 0.9.0
Dataset results
34 results for “Automatic Classification”
EUNIS-ESy: Expert system for automatic classification of European vegetation plots to EUNIS habitats
<p><strong>EUNIS-ESy</strong> is an expert system for automatic classification of European vegetation plots to habitat types of the EUNIS Habitat Classification. The EUNIS classification and the principles of the expert system are described by <a href="https://doi.org/10.1111/avsc.12519">Chytrý et al. (2020)</a>. The classification of a set of vegetation plots can be run using the JUICE program (<a href="https://doi.org/10.1111/j.1654-1103.2002.tb02069.x">Tichý 2002</a>; <a href="https://www.sci.muni.cz/botany/juice/">https://www.sci.muni.cz/botany/juice/</a>), TURBOVEG 3 program (Hennekens 2015) and an R script (<a href="https://doi.org/10.1111/avsc.12562">Bruelheide et al. 2021</a>).</p> <p>This dataset contains two parts: (1) the expert system and related files necessary for running it; (2) characterization of EUNIS habitats based on the results of the expert system classification.</p> <p><strong>1. Expert system and related files necessary to run it</strong></p> <p>1.1. <strong>EUNIS-ESy-2025-10-03.txt </strong>– a file containing the script for the classification of vegetation plots by EUNIS-ESy. This version contains tested definitions for the revised EUNIS classification of vegetated Marine (MA), Coastal (N), Wetland (Q), Grassland (R), Shrubland (S), Forest (T), Inland sparsely vegetated (U) and Man-made (V). It also contains tested definitions of Aquatic plant communities (P3) and Springs (P2N). This file is different from the analogous file in the previous versions.</p> <p>1.2. <strong>Nomenclature-translation-from-Turboveg-2-databases.zip </strong>– an archive containing the scripts for automatic translation of taxon concepts and names used in individual European Turboveg 2 databases (<a href="https://doi.org/10.2307/3237010">Hennekens & Schaminée 2001</a>; <a href="https://www.synbiosys.alterra.nl/turboveg/">https://www.synbiosys.alterra.nl/turboveg/</a>) to the nomenclature that can be used as an input for EUNIS-ESy. This file is the same as in the previous versions.</p> <p>1.3. <strong>EUNIS-ESy-User-Guide.pdf </strong>– a brief user guide to the classification of vegetation plots by EUNIS-ESy using the JUICE program. Please read this guide carefully before running the expert system to avoid misclassifications. This file is the same as in the previous versions.</p> <p><strong>2. Characterization of the EUNIS habitats based on the results of the EUNIS-ESy classification</strong></p> <p>2.1. <strong>EUNIS-habitats-2025-10-03.xlsx </strong>– the current list of EUNIS habitats. This file is different from the analogous file in the previous versions.</p> <p>2.2. <strong>EUNIS-EuroVegChecklist-crosswalk-2025-10-03.xlsx</strong> – a crosswalk between the EUNIS habitat classification and phytosociological alliances of EuroVegChecklist (<a href="http://doi.org/10.1111/avsc.12257">Mucina et al. 2016</a>; <a href="https://floraveg.eu/vegetation/">https://floraveg.eu/vegetation/</a>).</p> <p>2.3. <strong>EUNIS-habitats-Characteristic-species-combintation-2025-10-03.xlsx </strong>– a database of habitats' characteristic species combinations in a spreadsheet format. These species combinations are based on the analysis of vegetation plots from the European Vegetation Archive (EVA; <a href="https://doi.org/10.1111/avsc.12191">Chytrý et al. 2016</a>; <a href="http://euroveg.org/eva-database">http://euroveg.org/eva-database</a>) and other databases classified by EUNIS-ESy v2025-10-03. Analytical methods are described in <a href="https://doi.org/10.1111/avsc.12519">Chytrý et al. (2020)</a>. This file is different from the analogous file in the previous versions.</p> <p>2.4. <strong>EUNIS-habitats-Distribution-maps-2025-10-03.xlsx </strong>– a set of distribution maps in the TIFF format based on the analysis of vegetation plots from the European Vegetation Archive (EVA; <a href="https://doi.org/10.1111/avsc.12191">Chytrý et al. 2016</a>; <a href="http://euroveg.org/eva-database">http://euroveg.org/eva-database</a>) and other databases classified by EUNIS-ESy v2025-10-03.</p> <p>2.5. <strong>Data-sources-EUNIS-classification-2025-10-03.pdf </strong>– a list of data sources used to produce the distribution maps and characteristic species combinations.</p> <p>-----------------------------------------------------------------------------------------------------</p> <p><strong>Differences from the previous version (2021-06-01)</strong></p> <p>Aquatic plant communities (P3), spring (P2N), some wetland (Q61-Q63) and some inland sparsely vegetated (U71-U72) habitats were added to the EUNIS-ESy expert system. Plant taxon concepts and nomenclature were extensively revised. Some previously included habitat definitions were slightly refined. New vegetation-plot records added to the EVA database by 8 August 2025 were used to characterize habitat types. Unlike in the previous version, this version does not provide Habitat factsheets because summarized information about each habitat is now available in the FloraVeg.EU database at <a href="https://floraveg.eu/habitat/">https://floraveg.eu/habitat/</a>.</p> <p>-----------------------------------------------------------------------------------------------------</p> <p> </p> <p><strong>Recommended citation of this version of the EUNIS-ESy expert system</strong></p> <p>Chytrý et al. (2020), version 2025-10-03</p> <p>Chytrý M., Tichý L., Hennekens S.M., Knollová I., Janssen J.A.M., Rodwell J.S., Peterka T., Marcenò C., Landucci F., Danihelka J., Hájek M., Dengler J., Novák P., Zukal D., Jiménez-Alfaro B., Mucina L., Abdulhak S., Aćić S., Agrillo E., Attorre F., Bergmeier E., Biurrun I., Boch S., Bölöni J., Bonari G., Braslavskaya T., Bruelheide H., Campos J.A., Čarni A., Casella L., Ćuk M., Ćušterevska R., De Bie E., Delbosc P., Demina O., Didukh Y., Dítě D., Dziuba T., Ewald J., Gavilán R.G., Gégout J.-C., Giusso del Galdo G.P., Golub V., Goncharova N., Goral F., Graf U., Indreica A., Isermann M., Jandt U., Jansen F., Jansen J., Jašková A., Jiroušek M., Kącki Z., Kalníková V., Kavgacı A., Khanina L., Korolyuk A.Yu., Kozhevnikova M., Kuzemko A., Küzmič F., Kuznetsov O.L., Laiviņš M., Lavrinenko I., Lavrinenko O., Lebedeva M., Lososová Z., Lysenko T., Maciejewski L., Mardari C., Marinšek A., Napreenko M.G., Onyshchenko V., Pérez-Haase A., Pielech R., Prokhorov V., Rašomavičius V., Rodríguez Rojo M.P., Rūsiņa S., Schrautzer J., Šibík J., Šilc U., Škvorc Ž., Smagin V.A., Stančić Z., Stanisci A., Tikhonova E., Tonteri T., Uogintas D., Valachovič M., Vassilev K., Vynokurov D., Willner W., Yamalov S., Evans D., Palitzsch Lund M., Spyropoulou R., Tryfon E., Schaminée J.H.J. (2020) EUNIS Habitat Classification: expert system, characteristic species combinations and distribution maps of European habitats. Applied Vegetation Science, 23, 648–675. https://doi.org/10.1111/avsc.12519</p>
CzechVeg-ESy: Expert system for automatic classification of vegetation plots from the Czech Republic
<p><strong>Expertní systém pro automatickou klasifikaci fytocenologických snímků z České republiky </strong><br> [popis a instrukce v češtině jsou uvedeny níže]</p> <p>***************************************************************************************************************</p> <p><strong>CzechVeg-ESy</strong> is an expert system for automatic classification of vegetation plots from the Czech Republic to the vegetation types defined in the monograph <em>Vegetation of the Czech Republic</em> (<a href="https://www.sci.muni.cz/botany/vegsci/vegetace.php?page=monograph&lang=en">Chytrý 2007-2013</a>). It is delivered in two main versions: The <strong>main version 1 (v1) </strong>is the original version used for the vegetation classification in that monograph, described in detail in its English Summary (<a href="https://www.sci.muni.cz/botany/chytry/Vegetation-Czech-Rep-Summary.pdf">Chytrý 2007</a>). Its subversions (indicated by dates) contains corrections of minor errors and species nomenclature. This version only classifies vegetation to the phytosociological associations. The <strong>main version 2 (v2)</strong> uses the same classification system as accepted in the <em>Vegetation of the Czech Republic</em>, but includes more advanced functions to provide more accurate classification. Moreover, it is hierarchical, performing classification not only to associations but also to alliances and classes (for the plots not classified at lower levels).</p> <p>Each version is delivered in two variants. The <strong>basic variant </strong>(CzechVeg-ESy-basic-v1.txt) assigns vegetation plots to associations following their formal definitions created using the Cocktail method (<a href="https://doi.org/10.2307/3236796">Bruelheide 2000</a>) modified by <a href="https://www.sci.muni.cz/botany/chytry/Koci_etal2003_JVS.pdf">Kočí et al (2003)</a>. These definitions are based on the presence of sociological species groups and the dominance of selected species. The expert system evaluates individual vegetation plots and assigns them to the associations. A classification process is considerably faster when the basic variant is used, as opposed to the full variant. The <strong>full variant</strong> (file CzechVeg-ESy-full-v1.txt) performs the same functions as the basic variant, but in addition, it can also assign the plots not classified by formal definitions based on their numerical similarity to the plots that fulfil the requirements of the formal definitions. Most of such plots can be considered as untypical from the phytosociological point of view, i.e. with poor correspondence to any of the defined vegetation types, in most cases because of the lack of ecologically specialized species. The method of similarity-based assignment is the Frequency-Positive Fidelity Index (FPFI) described in <a href="https://www.sci.muni.cz/botany/chytry/Koci_etal2003_JVS.pdf">Kočí et al. (2003)</a> and <a href="https://doi.org/10.1007/s11258-004-5798-8">Tichý (2005)</a>.</p> <p><strong>Instructions for using CzechVeg-ESy version 1</strong></p> <ol> <li>Vegetation plots have to be stored in the TURBOVEG 2 program (<a href="https://www.synbiosys.alterra.nl/turboveg/">https://www.synbiosys.alterra.nl/turboveg/</a>) with the species list Czechia-Slovakia-2015 (contained in the file TurbovegSlBackup_Czechia_slovakia_2015.zip), which is largely compatible with the older species lists called Czechia-Slovakia-2012 and Central-Europe.</li> <li>Export plots from TURBOVEG 2 to a CC! file (Export / Other formats / JUICE input files) and import this file to the JUICE program (<a href="https://www.sci.muni.cz/botany/juice/">https://www.sci.muni.cz/botany/juice/</a>) using the species list in the file Checklist-Danihelka-et-al-2012-ver-2019-07-06.txt, which converts the plant nomenclature to correspond with the Checklist of vascular plants of the Czech Republic (<a href="http://www.preslia.cz/P123Danihelka.pdf">Danihelka et al. 2012</a>).</li> <li>Select Analysis / Expert system in the JUICE program.</li> <li>Upload the expert system file (either CzechVeg-ESy-basic-v1.txt or CzechVeg-ESy-full-v1.txt) by pressing Load ES File button.</li> <li>Modify species nomenclature by pressing the Modify Species Names button.</li> <li>If there are juvenile species in the herb layer in the plots to be analysed, delete them by pressing Delete Juveniles button.</li> <li>In some cases, narrow species concepts were changed to broader concepts, resulting in repetitions of the same names in the table. These must be merged using the Merge Same Spec. Names button. This will also merge records of the same species in different vegetation layers because the expert system assumes that each species name is contained only once in the same plot.</li> <li>When using the full version of the expert system, a threshold similarity value for similarity-based assignment must be specified in the field in the bottom right part of the form. The higher the value, the fewer plots will be assigned, while only those plots will be assigned that have a high similarity to the association. If the threshold value is set to 0, all the plots will be assigned, but some of them may be very dissimilar to the associations which they are assigned to.</li> <li>Run expert system using the Classify Relevé button (a plot marked by a previous mouse click will be classified) or Classify [colour] Relevés button (all the plots of the selected colour will be assigned).</li> <li>If a single plot is classified, species groups present in this plot and the assignment of the plot to an association will be shown. If the plot is not classified, no association will be listed. Occasionally, a plot can be assigned to more than one association. If the full version of the expert system is used, the table will contain a list of associations ranked by decreasing similarity to the plot.</li> <li>If multiple plots are classified, association codes will appear in the header of those plots that were assigned based on the formal definitions. The legends for the codes can be found in a printed version of the <em>Vegetation of the Czech Republic</em>, in its online version (<a href="https://pladias.cz/en/vegetation/">https://pladias.cz/en/vegetation/</a>) or in the expert system txt file. Plots not assigned to any association will be marked with ? and those assigned to more than one association will be marked with +. If the full version of the expert system is used, the output will contain the most similar associations for those plots which have remained unassigned to associations or were assigned to more than one association.</li> <li>Using the formal definition, the expert system normally assigns some plots of a single vegetation stand to a certain association while other plots of the same stand remain unassigned. This means that the stand consists of patches with species composition typical of the given association and patches with a less typical species composition. If different plots from a single relatively homogeneous stand are assigned to different associations, it is appropriate to interpret the stand as transitional between these associations.</li> </ol> <p>This electronic publication of CzechVeg-ESy was supported by the Czech Science Foundation (grant no. 17-15168S).</p> <p>***************************************************************************************************************</p> <p><strong>CzechVeg-ESy</strong> je expertní systém pro automatickou klasifikaci fytocenologických snímků z České republiky do vegetačních typů definovaných v monografii <em>Vegetace České republiky </em>(<a href="https://www.sci.muni.cz/botany/vegsci/vegetace.php?lang=en&page=monograph">Chytrý 2007-2013</a>). Existují dvě hlavní verze tohoto expertního systému: <strong>Hlavní verze 1 (v1) </strong>je originální verze použitá pro klasifikaci v této národní vegetační monografii, která je podrobně popsaná v její metodické kapitole. Její dílčí verze (označené datem) obsahují opravy drobných chyb a nomenklatury druhů. Tato verze klasifikuje fytocenologické snímky pouze do fytocenologických asociací. <strong>Hlavní verze 2 (v2)</strong> používá stejný klasifikační systém, jaký byl použit ve Vegetaci České republiky, ale používá pokročilejší funkce umožňující přesnější klasifikaci. Tato verze také provádí hierarchickou klasifikaci nejen do asociací, ale také do svazů a tříd (pro snímky nezařazené do nižších jednotek).</p> <p>Každá verze má dvě varianty. <strong>Základní varianta </strong>(soubor CzechVeg-ESy-basic-v1.txt) přiřazuje fytocenologické snímky do asociací na základě jejich formálních definic vytvořených metodou Cocktail (<a href="https://doi.org/10.2307/3236796">Bruelheide 2000</a>) v úpravě podle práce <a href="https://www.sci.muni.cz/botany/chytry/Koci_etal2003_JVS.pdf">Kočí et al (2003)</a>. Tyto definice jsou založeny na prezenci sociologických skupin druhů a dominanci vybraných druhů. Expertní systém vyhodnocuje každý jednotlivý fytocenologický snímek v datovém souboru a řadí jej do asociace. Klasifikace pomocí základní varianty je výrazně rychlejší než klasifikace pomocí plné varianty. <strong>Plná varianta </strong>(soubor CzechVeg-ESy-full-v1.txt) zajišťuje stejné funkce jako základní varianta, ale navíc klasifikuje i snímky neklasifikované formálními definicemi, a to na základě jejich numerické podobnosti ke skupinám snímků, které vyhovují podmínkám formálních definic asociací. Většinu takových snímků lze považovat z fytocenologického hlediska za netypické porosty, tj. takové, které plně neodpovídají definovaným vegetačním typům, zpravidla kvůli absenci ekologicky specializovaných druhů. Klasifikace na základě podobnosti se počítá pomocí indexu FPFI (Frequency-Positive Fidelity Index), který definovali <a href="https://www.sci.muni.cz/botany/chytry/Koci_etal2003_JVS.pdf">Kočí et al. (2003)</a> a <a href="https://doi.org/10.1007/s11258-004-5798-8">Tichý (2005)</a>.</p> <ol> <li>Fytocenologické snímky určené k analýze musí být uloženy v databázi v programu TURBOVEG 2 (<a href="https://www.synbiosys.alterra.nl/turboveg/">https://www.synbiosys.alterra.nl/turboveg/</a>) s druhovým seznamem Czechia-Slovakia-2015 (soubor TurbovegSlBackup_Czechia_slovakia_2015.zip), který je kompatibilní s druhovými seznamy Czechia-Slovakia-2012 a Central-Europe.</li> <li>Snímky se exportují z programu TURBOVEG 2 do souboru CC! (Export / Other formats / JUICE input files) a tento soubor se importuje do programu JUICE (<a href="https://www.sci.muni.cz/botany/juice/">https://www.sci.muni.cz/botany/juice/</a>) s použitím druhového seznamu v souboru Checklist-Danihelka-et-al-2012-ver-2019-07-06.txt, čímž se nomenklatura konvertuje do nomenklatury odpovídající Seznamu cévnatých rostlin květeny České republiky (<a href="http://www.preslia.cz/P123Danihelka.pdf">Danihelka et al. 2012</a>).</li> <li>V programu JUICE se zvolí menu Analysis / Expert system.</li> <li>Tlačítkem Load ES File se nahraje do paměti soubor s příslušným expertním systémem (buď CzechVeg-ESy-basic-v1.txt, nebo CzechVeg-ESy-full-v1.txt).</li> <li>Tlačítkem Modify Species Names se upraví nomenklatura druhů tak, aby odpovídala nomenklatuře používané expertním systémem.</li> <li>Obsahují-li snímky určené k analýze juvenilní dřeviny v bylinném patru, je potřeba je vymazat tlačítkem Delete Juveniles.</li> <li>Při převodu nomenklatury se v některých případech převedlo užší pojetí druhů na širší, čímž vznikly v tabulce druhové údaje vedené pod stejnými jmény. Ty je potřeba sloučit tlačítkem Merge Same Spec. Names. Přitom se sloučí i údaje stejného druhu v různých patrech, protože expertní systém předpokládá jen jeden výskyt stejného druhového jména v jednom snímku.</li> <li>Pokud je používána plná (Full) verze expertního systému, je potřeba v okénku vpravo dole nastavit prahovou hodnotu podobnosti pro přiřazování snímků k asociacím pomocí podobnosti. Čím vyšší hodnota, tím méně snímků se přiřadí, ale přiřadí se ty, které se dané asociaci více podobají. Při hodnotě 0 se přiřadí všechny snímky, ale některé budou dané asociaci velmi nepodobné.</li> <li>Spustí se běh expertního systému, a to buď tlačítkem Classify Relevé (bude se klasifikovat jeden snímek, na který se předtím kliklo myší) nebo Classify [colour] Relevés (budou se klasifikovat všechny snímky vybrané barvy).</li> <li>Při klasifikaci jednoho snímku se zobrazí v tabulce druhové skupiny, jejich zastoupení v daném snímku a asociace, do které byl snímek přiřazen pomocí formální definice. Pokud přiřazen nebyl, nezobrazí se žádná asociace. Snímek může být přiřazen i do více než jedné asociace. Při použití plné verze expertního systému se do tabulky vypíší asociace v pořadí klesající podobnosti ke snímku, a to u těch snímků, které nebyly přiřazeny do žádné asociace nebo byly přiřazeny do více než jedné asociace.</li> <li>Při klasifikaci více snímků se do záhlaví tabulky vepíší kódy asociací u těch snímků, které se přiřadily na základě formálních definic. Převod kódů na jména asociací lze dohledat v tištěné verzi <em>Vegetace České republiky</em>, v její online verzi (<a href="https://pladias.cz/en/vegetation/">https://pladias.cz/vegetation/</a>) nebo v textovém souboru expertního systému. U snímků, které se nepřiřadily k žádné asociaci, se v záhlaví zobrazí znak ?. U snímků přiřazených do více než jedné asociace se zobrazí znak +. Při použití plné verze expertního systému se do tabulky vypíší nejpodobnější asociace u těch snímků, které nebyly přiřazeny do žádné asociace nebo byly přiřazeny do více než jedné asociace.</li> <li>Expertní systém běžně přiřazuje pomocí formálních definic některé snímky v porostu nebo lokálně rozlišovaném rostlinném společenstvu do určité asociace a jiné do žádné asociace, což znamená, že se porost skládá z míst s druhovým složením typickým pro danou asociaci a míst s méně typickým druhovým složením. Pokud expertní systém přiřadí různé snímky z jednoho relativně homogenního porostu k různým asociacím, je vhodné porost interpretovat jako přechodný mezi těmito asociacemi.</li> </ol> <p>Tato elektronická publikace expertního systému CzechVeg-ESy byla podpořena Grantovou agenturou České republiky (grant 17-15168S).</p>
A Semi-Automatic Classification Approach for River Shape Extraction from Sentinel-2 Imagery
<p>To extract the river from satellite imagery, at first we have to classify the waterbody from satellite imagery. Then we will differentiate the river from waterbody. We have used three different techniques to classify the waterbody from satellite imagery. At first, pixel based iso-cluster unsupervised classification was used to classify the waterbody in Sentinel 2 imagery. We excluded the supervised classification in decided methodology as we are interested about automatic process of river extraction. Then we have used Segment mean shift classification tool as image segmentation techniques. Indices based NDWI (Normalize difference water indices) classification was also used in this research.</p>
ITTV - A Dataset of Italian Television for Automatic Genre Classification
<p>ITTV is a publicly available dataset of Italian TV programs introduced in </p> <blockquote> <p>Alessandro Ilic Mezza, Paolo Sani, and Augusto Sarti, "Automatic TV Genre Classification Based on Visually-Conditioned Deep Audio Features," in 2023 31st European Signal Processing Conference (EUSIPCO), 2023.</p> </blockquote> <p>ITTV consists of 2625 manually annotated YouTube videos, totaling over 670 hours. Each clip is assigned one of seven classes:</p> <ul> <li>Cartoons</li> <li>Commercials</li> <li>Football</li> <li>Music</li> <li>News</li> <li>Talk Shows</li> <li>Weather Forecast</li> </ul> <p>ITTV genre taxonomy is similar to that of the well-known RAI dataset described in</p> <blockquote> <p>Maurizio Montagnuolo and Alberto Messina, "Parallel neural networks for multimodal video genre classification,” Multimedia Tools and Applications, vol. 41, no. 1, pp. 125–159, 2009.</p> </blockquote> <p>The dataset contains genre annotations and metadata in CSV format. Please note that audio data is not provided.</p> <p>We provide the annotations for a balanced training (1575 clips) and validation (525 clips) split, as well as for a disjoint test set containing 525 installments from TV programs not included in the development set.</p> <p>As YouTube continuously updates, some videos may not be available in the future. Although we intend to keep ITTV updated as best as possible, please note that some content may not be available at any given time.</p> <p>Some YouTube videos (especially from the <code>Football</code> class and, to a lesser extent, the <code>Cartoons</code> class) may only be available in some countries due to regional restrictions imposed by the content creator. All videos are known to be accessible from Italy (last accessed on Nov. 25th, 2022.)<br> <br> Please contact Alessandro Ilic Mezza for further questions (e-mail: alessandroilic.mezza@polimi.it).</p>
BgMA-ESy: Expert system for automatic classification of vegetation plots of subalpine tall-herb vegetation (class Mulgedio-Aconitetea) from Bulgaria
<p>*****</p> <p>BgMA-ESy is an expert system that classifies vegetation plots of the class <em>Mulgedio-Aconitetea</em> (<a href="https://doi.org/10.1111/avsc.12257">Mucina et al. 2016</a>) occurring in Bulgaria. The expert system can be run using the JUICE program (<a href="https://doi.org/10.1111/j.1654-1103.2002.tb02069.x">Tichý 2002</a>; <a href="https://www.sci.muni.cz/botany/juice/">https://www.sci.muni.cz/botany/juice/</a>).</p> <p>The aggregation of vascular plants included within the BgMA-ESy is adopted from EUNIS-ESy (<a href="https://doi.org/10.1111/avsc.12519">Chytrý et al. 2020</a>; <a href="https://doi.org/10.5281/zenodo.4812736">https://doi.org/10.5281/zenodo.4812736</a>), and in a few cases, it is adjusted.</p> <p>*****</p> <p><strong>Specifications</strong></p> <p>The analyzed data (vegetation plots) cannot: </p> <ul> <li>include scrub vegetation (cover of tall shrub species > 8%; e.g., <em>Pinus mugo</em>, <em>Salix </em>spp.).</li> <li>contain tree species with cover > 1% (e.g., <em>Fagus sylvatica</em>, <em>Picea abies</em>).</li> <li>contain <em>Pteridium aquilinum </em>as a dominant species.</li> </ul> <p>The expert system was trained on vegetation plots with 5–100 m<sup>2</sup> area that occur above 1000 m a. s. l.</p> <p>* Exceptions from EUNIS-ESy aggregation:</p> <p>Heracleum sphondylium agg. does not include H. sphondylium subsp. verticillatum.</p> <p> </p> <p>*****</p> <p>When using this work, please cite:</p> <p>Szokala D., Kočí M. & Vassilev K. (2024): Subalpine tall-herb vegetation in Bulgaria: diversity and ecology. – Plant Biosystems 158: 490–510. <a href="https://doi.org/10.1080/11263504.2024.2327865">https://doi.org/10.1080/11263504.2024.2327865</a>.</p> <p>*****</p>
Automatic plankton image classification - can capsules and filters help coping with data set shift?
<p>This data set is related to the article 'Automatic plankton image classification - can capsules and filters help coping with data set shift?' published in 'Limnology and Oceanography: Methods' by Plonus <em>et al.</em> (2021).</p> <p>The images belong to the trainings set used to train the models in the aforementioned paper (training_) and three different additional data sets which were used to evaluate the performance of the trained models in application mode (fs446_; fs466_; fs534_). The Python-Script 'separate_files.py' can be used to move all the images in different folders for each data set and class respectively.</p>
Automatic Classification of Final Assignments at the Nuclear Polytechnic Library
<p>This study aimed to look for a method to automatically classify the final projects of Indonesian Nuclear Technology Polytechnic students.</p>
ReSpa - Towards an automatic requirements classification in a new Spanish dataset
<p>ReSpa (Spanish Dataset for requirements classification) dataset is conformed by requirements collected from final degree projects from one University. It was presented in the paper 'Towards an automatic requirements classification in a new Spanish dataset' and used also in the paper 'Requirements Classification Using FastText and BETO in Spanish Documents'.</p> <p>Cited as:</p> <p>Limaylla-Lunarejo, M. I., Condori-Fernandez, N., & Luaces, M. R. (2022, August). Towards an automatic requirements classification in a new Spanish dataset. In <em>2022 IEEE 30th International Requirements Engineering Conference (RE)</em> (pp. 270-271). IEEE. https://doi.org/10.1109/RE54965.2022.00039</p> <p> </p> <p> </p> <p> </p> <p> </p>
Data Cleaning, Translation & Split of the Dataset for the Automatic Classification of Documents for the Classification System for the Berliner Handreichungen zur Bibliotheks- und Informationswissenschaft
<ul> <li>Cleaned_Dataset.csv – The combined CSV files of all scraped documents from DABI, e-LiS, o-bib and Springer.</li> <li>Data_Cleaning.ipynb – The Jupyter Notebook with python code for the analysis and cleaning of the original dataset.</li> <li>ger_train.csv – The German training set as CSV file.</li> <li>ger_validation.csv – The German validation set as CSV file.</li> <li>en_test.csv – The English test set as CSV file.</li> <li>en_train.csv – The English training set as CSV file.</li> <li>en_validation.csv – The English validation set as CSV file.</li> <li>splitting.py – The python code for splitting a dataset into train, test and validation set.</li> <li>DataSetTrans_de.csv – The final German dataset as a CSV file.</li> <li>DataSetTrans_en.csv – The final English dataset as a CSV file.</li> <li>translation.py – The python code for translating the cleaned dataset.</li> </ul>
BRAIN Journal-Automatic Anthropometric System Development Using Machine Learning-Figure 6. The result of building a 3D model based on RF and SVM classification with "Important features".
<p>From the chart of figure 6, we found that "Important Features" gave the best 3D model, which fits with the object in the image. The pattern is close to 90% compared with the true size. Apply classification algorithm RF increases the accuracy of the results and reduces computing time for the program. There are many methods for data classifying. One of them is the method of the support vector machine (SVM). The SVM method is represented by Vladimir N. Vapnik (1995) in Support Vector Machines (SVM) - a set of learning algorithms similar with the supervisor has two main tasks: the classification and the regression analysis. In this article we use the method of the SVM classification problem for the size of the human body with 5 classes to compare the performance between SVM methods and Random Forest algorithm. </p>
BRAIN Journal-Automatic Anthropometric System Development Using Machine Learning-Figure 5. Flowchart of data classification
<p>The Random Forest is a powerful classification method because of the following. First, errors are minimized as a result of a random forest, synthesizing through training (learner). The second, random choice at every stage in the Random Forest will reduce the correlation between the learners in the synthesis of the results. In addition, we also found that the total error of layered forest trees depends on their individual errors in forest trees, as well as the correlation between the trees. The article uses the wrapper model (Christopher Tong, 2000) with the objective function for the evaluation, Random Forest algorithm is shown in figure 5. </p>
Automatic global climate classification, preserving Köppen thermal classes with added aridity information and a hypertropical class
<p>A streamlined system using growing degree days for climate classification that delivers both temperature and aridity information in all classes and an added hypertropical class. Primary thermal classes remain consistent with the primary Köppen climate classes and their established connection to biomes.</p> <p>The eight class to tif tool ends with a .tif file of climate classes. </p> <p>The steps may need to be modified if using different inputs than Envirem and WorldClim 1.4. Envirem is missing datum information, but ArcGIS makes the same calculations <br> without the project raster step. Note that WorldClim 1.4 applies a scaling factor of 10 for temperature data, which is propagated in Envirem.</p> <p>Import the symbology layer file climate_8_class. If ArcGIS is being cranky about displaying the (blue) hypertropical class, try reseting with the 'Add All Values' button,<br> followed by hitting 'Default Colors'.</p>
Exploring the Automatic Classification of Usage Information in Feedback
<p>Datasets and list of relevant papers for the publication "Exploring the Automatic Classification of Usage Information in Feedback".</p><p>Please read the included readMe for more information on formatting of Json-Files</p>
Pixel-based forest classification of Sentinel-2 images using automatically generated datasets
<p>Contains six training datasets, composed of 800, 1600 and 3200 images. Each training dataset made up of OSM (<em>OpenStreetMap</em>) masks or HRL (<em>Copernicus pan-European High Resolution Layers</em>).</p> <p>Additional 2 evaluation datasets based on OSM and HRL. Composed of 200 evaluation images.</p> <p>For study area <em>lithuania_2018_06.tiff</em> is provided. This contains a fully preprocessed study area (removed clouds, composed mosaic).</p> <p>We provide additionally a merged mosaic of Lithuanian HRL in <em>lithuania_HRL.tiff </em>file.</p> <p><em>OpenStreetMap</em> database is not provided, it can be found at https://planet.openstreetmap.org.</p>
Using photodiodes and supervised Machine Learning for automatic classification of weld defects in laser welding of thin foils copper-to-steel battery tabs
<p>In this folder, excel files are stored with the results of signal processing that supported findings in the following paper:</p> <p>"Using photodiodes and supervised Machine Learning for automatic classification of weld defects in laser welding of thin foils copper-to-steell battery tabs".</p> <p>Matlab scripts and orginal signals will be uploaded soon with more detailed description.</p> <p> </p>
Physical Features for my study on Automatic Seismic Event Classification System in Pacific Northwest (Origin time - 50, +100)
<p>These features used the revised version of the feature extraction code. The revision involves changing the envelope filtering options and some minor modifications. </p>
Assisting the appraisal of e-mail records with automatic classification
<p>This spreadsheet shows the results of training a series of Support Vector Machine (SVM) classifiers to replicate the decision process for identifying e-mails of business value from among 846 e-mails in two corporate mailboxes. One set of SVMs were trained on emails without including the text of attachments and with the inclusion of attachments. For the sake of comparison, these SVMs were also trained on Spam / Ham and on a randomly selected subset of Enron emails half of which were arbitrarily tagged as "business value".</p>
Automatic Complaints Classification in E-Commerce: A Case Study Using CRISP-DM
<p>The growth of e-commerce has been remarkable in recent years, driven by increasing consumer demand for attention and quick responses. Given the large volume of transactions and complaints accompanying this increase, automating the classification of these complaints can help quickly route them to the appropriate departments. This paper presents a computational approach using the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology to automate the complaints screening process. We categorized 600 real complaints from three e-commerce platforms in Brazil. The learning model was trained progressively, using an initial set of 25 complaints in each category. The classification model obtained an accuracy of 85\% and an average of over 80\% across all relevant metrics, including precision, recall, and F1-Score. The results confirmed the effectiveness of the developed model for automated complaint classification in e-commerce, providing a computational strategy that improves the customer service process and allows for quicker problem resolution.</p>
Automatic Classification of Non-functional Requirements in App User Reviews Based on System Model and Artificial Intelligence
<p>This is the replication package for the paper: "Automatic Classification of Non-functional Requirements in App User Reviews Based on System Model and Artificial Intelligence". It contains the dataset of our experiment for the replication by other researchers. In the meanwhile, we provide brief description of the files in the replication package in the following.</p> <p><strong>1. dataset folder</strong></p> <ul> <li>dataset_user_reviews.xlsx contains 1278 labelled non-requirement user reviews.</li> <li>readme.txt describes the meaning of the data in dataset_user_reviews.xlsx in detail.</li> </ul>
Data from: Towards the automatic classification of avian flight calls for bioacoustic monitoring
Automatic classification of animal vocalizations has great potential to enhance the monitoring of species movements and behaviors. This is particularly true for monitoring nocturnal bird migration, where automated classification of migrants' flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we investigate the automatic classification of bird species from flight calls, and in particular the relationship between two different problem formulations commonly found in the literature: classifying a short clip containing one of a fixed set of known species (N-class problem) and the continuous monitoring problem, the latter of which is relevant to migration monitoring. We implemented a state-of-the-art audio classification model based on unsupervised feature learning and evaluated it on three novel datasets, one for studying the N-class problem including over 5000 flight calls from 43 different species, and two realistic datasets for studying the monitoring scenario comprising hundreds of thousands of audio clips that were compiled by means of remote acoustic sensors deployed in the field during two migration seasons. We show that the model achieves high accuracy when classifying a clip to one of N known species, even for a large number of species. In contrast, the model does not perform as well in the continuous monitoring case. Through a detailed error analysis (that included full expert review of false positives and negatives) we show the model is confounded by varying background noise conditions and previously unseen vocalizations. We also show that the model needs to be parameterized and benchmarked differently for the continuous monitoring scenario. Finally, we show that despite the reduced performance, given the right conditions the model can still characterize the migration pattern of a specific species. The paper concludes with directions for future research.
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.