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.
6,250
datasets available to search
ShareScore release 0.7.1
Dataset results
6,250 results for “Classification”
PlantVillage Disease Classification Challenge - Color Images
<p><br> This work is licensed under a <a href="http://creativecommons.org/licenses/by-sa/3.0/us/">Creative Commons Attribution-ShareAlike 3.0 United States License</a>.<br> <br> # Data origins<br> The dataset is originally hosted at <a href="https://www.crowdai.org/challenges/plantvillage-disease-classification-challenge">PlantVillage Disease Classification Challenge</a>.<br> We use the modified version in <a href="https://github.com/salathegroup/plantvillage_deeplearning_paper_dataset">this github repository</a> to do controlled experiments.<br> We only use the raw color images dataset and delete the unconventional characters in the classes directory name and `.csv` filenames.<br> <br> # Directory explanation<br> The `80-20` direcotry has multiple `.txt` files which contain the training (~80%), validation(~10%) and testing (~10%) datasets instances filenames and the corresponding label indexes. The validation dataset quantity is `5430` in all data separation. In our experiment code (not included in this archive), the validation and testing dataset are merged together.<br> <br> # Data usage<br> ## Replicate our experiments<br> We have used this dataset in writing our paper. The reference information can be seen at https://<a href="https://gitlab.com/huix/leaf-disease-plant-village">gitlab.com/huix/leaf-disease-plant-village</a>.<br> <br> ### Steps<br> 1. `cd` to the direcotry (e.g. `/home/usrname/plantvillage_deeplearning_paper_dataset`) that contains the `color` directory.<br> 2. run `python change_filename_prefix.py --prefix /home/usrname/plantvillage_deeplearning_paper_dataset` to modify the prefix path (which is `/home/h/plantvillage_deeplearning_paper_dataset` in our former generated datasets).<br> 3. Fin. You can use our <a href="https://gitlab.com/huix/leaf-disease-plant-village">opens ource codes repository</a> to do the later experiments.<br> <br> ## Generate your own training/validation/testing datasets<br> This data separation generating code isn't included in the dataset archive, it is in our open source code. Please see our <a href="https://gitlab.com/huix/leaf-disease-plant-village">open source code repository</a> for the detailed information.<br> If you have any questions, you can contact the author through email.<br> The email address is a QR code in the archive.</p>
Method Classification of Open Access INTACT Molecular Interaction data.
<p>Simple classification data derived from open access papers indexed in the INTACT database (https://www.ebi.ac.uk/intact/downloads) based on PSI-MI25 codes for interaction detection methods or participant detection methods based on the subfigure caption text. <br> <br> intact_records_and_captions_complete.tsv - This file links available text of subfigure captions to PSI-MI25 codes for the interaction detection method and participant detection method. </p> <p>evidx_run_file.txt - This file provides execution codes for the 'EvidX' machine learning text classifier (https://github.com/SciKnowEngine/evidX/releases/tag/v0.1.0)</p> <p> </p> <p> </p> <p> </p>
Circulation type classifications for surface temperature and precipitation optimized for Italy
<p>The four files are two couple of files for two circulation type classifications (pct9 and san9) optimized for Italy, in order to stratify precipitation and surface temperature respectively.</p> <p>"pct9.cla" and "san.cla" are the circulation type daily series between 1979 and 2015 computed on mean sea level pressure (MSLP) and geopotential height at 500 hPa (500HGT) respectively. Meteorological fields are extracted by the NCEP-NCAR Reanalysis 2 dataset.</p> <p>"pct-nc.txt" and "san9-nc.txt" are the centroid values of MSLP and 500HGT respectively, computed on 9 classes over a spatial domain of 7 X 7 grid points across Italy.</p> <p>These files are created through the COST733 software package (DOI: 10.1002/joc.3920). </p> <p>The pct9 and san9 classifications were selected as the best performing for the stratifacation of precipitation and surface temperature respectively across Italian peninsula, through a sensitivity analysis detailed in a specific study (DOI: 10.1002/joc.5219). In summary several circulation type classifications were computed with different classification methods, number of types and classification variables (i.e. predictands). Then such classifications were compared through the use of proper statistical indexes in order to assess the stratification of the ground-level precipitation and the surface air temperature across Italian peninsula.</p> <p>These two classifications could be evaluated also for other meteorological or environmental variables.</p>
Data and material for: "Content classification of development emails"
<p>This data and material support the paper "Content classification of development emails" published in the proceedings of the 34th International Conference on Software Engineering (ICSE 2012).</p> <p>Every software system has a history. <strong>We find traces of a system's history in software repositories</strong>, which are used by developers when building and maintaining their systems. Each repository tells us a part of the history, from its perspective: Issue repositories murmur dark events involving defective and flawed entities; versioning system repositories narrate about restless artifacts and classes that nobody would ever touch; mailing list archives report of unexpected stories on developers’ interactions and opinions.</p> <p>But... <strong>can we seriously trust these repositories?</strong> Can we just listen to what they tell us and behave accordingly? Many wise researchers warmly warned us about the risks of showing such a naive faith in data repositories: Versioning system repositories might seduce us with enchanting stories of always changing entities, but in reality many of these entities may just modify their make up and maintain their old behaviour; or issue repositories might tell us a partial truth about certain very special entities, or developers. We do agree with these researchers: Especially <strong>natural language documents contain information in different languages, surrounded by much noise</strong>. We must pay a special attention when using them.</p> <p>We created <strong>MUCCA</strong>, a classification method to use when dealing with natural language documents. It recognizes source code fragments, patches, stack traces, noise, and natural language with significantly high accuracy. In this way, it allows one to subsequently apply ad hoc analysis techniques to exploit the peculiarities of each category, and extract reliable information.</p> <p>This Zenodo upload supports the paper that describe our work on this topic.</p> <p> </p> <p><strong>1. Source code & Virtual Image</strong></p> <p>MUCCA is written in <a href="http://www.cincomsmalltalk.com/main/products/visualworks/overview/">Cincom VisualWorks Smalltalk</a> and is composed of several components.<br> You can download the source code of the following MUCCA components from this upload (<code>mucca-source_code</code> folder):</p> <ul> <li>Miler2, the core of MUCCA, including metamodels, importers, classification engine, etc.;</li> <li>MailPeek, our web application for the manual classification of email content;</li> <li>PetitIsland, our grammar to generate island parsers;</li> <li>PetitJava, the grammar of Java, which we implemented for PetitParser;</li> <li>PetitSTrace, our island parser for java stack traces.</li> </ul> <p>Note that, in order to make Miler2 run, you will also need the following external Smalltalk components: <a href="http://www.moosetechnology.org/">Moose</a>, <a href="http://www.glorp.org/">Glorp</a>, <a href="http://www.seaside.st/">Seaside</a>, TwoFlower, MetaDB, <a href="http://www.lukas-renggli.ch/blog/petitparser-1">PetitParser</a>.</p> <p>In addition, we make use of the <a href="http://www.cs.waikato.ac.nz/ml/weka/">Weka</a> workbench, for the machine learning tasks. You can download the two trained classifiers that compose MUCCA (<code>mucca-classifiers</code> folder): Naive Bayes based classifier (<code>classifier1-nb.model</code>), Decision Tree based classifier (<code>classifier2-dt.model</code>).</p> <p>Alternatively, we created a <a href="http://www.virtualbox.org/">VirtualBox</a> image with a pre-configured VisualWorks environment, which includes all the MUCCA components, and pre-requisites (both Smalltalk and Java): <code>MUCCA.ova</code> (Both user and password are <code>muccauser</code>).</p> <p> </p> <p><strong>2. Benchmark</strong></p> <p>To train machine-learning classifiers and evaluate the effectiveness of the different approaches, we <strong>manually</strong> create a benchmark, in which emails are classified at character granularity.</p> <p>Given the time and effort needed to create such a benchmark, we humbly think it is a valuable contribution to the community. With the help of this benchmark, other researchers can reproduce our experiments and devise new classification methods, which can be immediately compared to ours.</p> <p>You can download the dataset from the <a href="https://github.com/ilredeitopi/mucca-dataset">GitHub repository</a> (a dump of the GitHub repository is uploaded here (<code>benchmark/githubDump.zip</code>), or download the full database dump in PostgreSQL format (<code>benchmark/benchmarkDump.tar.bz2</code>).</p>
THE HIGH CADENCE TRANSIENT SURVEY (HITS): Source, light-curve and classification catalogs
<p>The High Cadence Transient Survey (HiTS) aims to discover and study transient objects with characteristic timescales between hours and days, such as pulsating, eclipsing and exploding stars. This survey represents a unique laboratory to explore large <em>etendue</em> observations from cadences of about 0.1 days and to test new computational tools for the analysis of large data. This work follows a fully <em>Data Science</em> approach: from the raw data to the analysis and classification of variable sources. We compile a catalog of ~15 million object detections and a catalog of ~2.5 million light-curves classified by variability. The typical depth of the survey is 24.2, 24.3, 24.1 and 23.8 in <em>u</em>, <em>g</em>, <em> </em>r, and <em>i</em> bands, respectively. We classified all point-like non-moving sources by first extracting features from their light--curves and then applying a Random Forest classifier. For the classification, we used a training set constructed using a combination of cross-matched catalogs, visual inspection, transfer/active learning, and data augmentation. The classification model consists of several Random Forest classifiers organized in a hierarchical scheme. The classifier accuracy estimated on a test set is approximately 97%. In the unlabeled data, 3,485 sources were classified as variables, of which 1,321 were classified as periodic. Among the periodic classes we discovered with high confidence, 1 <span class="math-tex">\(\delta\)</span> scuti, 39 eclipsing binaries, 48 rotational variables, and 90 RR-Lyrae. For the non-periodic classes we discovered 1 cataclysmic variables, 630 QSO, and 1 supernova candidate.</p>
Data for: Tang et al., Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline. bioRxiv 2018.
<p>Datasets containing 63 whole slide images (WSIs) and their segmented 256x256 pixel tiles with approximately 80,000 tile-level amyloid-β pathology expert annotations.</p> <p><strong>Paper</strong>: "Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline", bioRxiv 454793; DOI: <a href="https://doi.org/10.1101/454793">https://doi.org/10.1101/454793</a>.</p> <p><strong>Details:</strong> A total of 63 WSIs for 63 unique decedent cases spanning Alzheimer’s disease (AD) to non-AD and possessing a variety of CERAD scores. WSIs comprise three datasets as follows:</p> <ol> <li><em>Development (Phases I-II)</em>. 33 WSIs used for convolutional neural network (CNN) model development (29 training, 4 validation).</li> <li><em>Hold-out (Phase III)</em>. 10 WSIs selected by an expert neuropathologist as a held-out test set to assess the generalizability of the CNN model.</li> <li><em>CERAD-like hold-out</em>. 20 blinded WSIs collected solely for use in a CERAD-like scoring comparison study.</li> </ol> <p>Datasets 1 and 2 were color-normalized and segmented to 256x256 pixel image tiles for model training set (61,370 images), validation set (8,630 images), and hold-out test set (10,873 images). Dataset 3 was color-normalized but not segmented.</p> <p>Expert labels of plaques for Dataset 1 and 2 tiles are included in corresponding CSV files.</p> <p><strong>Slide source and preparation:</strong> All samples were retrieved from archives of the University of California, Davis Alzheimer’s Disease Center Brain Bank (<a href="https://www.ucdmc.ucdavis.edu/alzheimers/">https://www.ucdmc.ucdavis.edu/alzheimers/</a>). Archival samples analyzed in this study were 5 μm formalin fixed, paraffin embedded sections of the superior and middle temporal gyrus from human brain. The tissue had been previously stained with an amyloid-β antibody (4G8, recognizing residues 17-24, BioLegend, formerly Covance) that were first pretreated with formic acid to rid samples of endogenous protein. All slides were digitized using an Aperio AT2 up to 40x magnification.</p> <p><strong>Code:</strong> Please visit <a href="https://github.com/keiserlab/plaquebox-paper">https://github.com/keiserlab/plaquebox-paper</a></p> <p> </p>
Recognising innovative companies by using a diversified stacked generalisation method for website classification – the raw results
<p><strong>Introduction</strong></p> <p>The classification models were trained out by using the Classification and Regression Training package (caret) [1]. The models' parameters were fine-tuned by the 10-fold cross-validation procedure [2].</p> <p><strong>Cluster parameters</strong></p> <p>Most computations were carried out on a cluster having the following parameters:</p> <ul> <li>GPU: NVIDIA Tesla P100;</li> <li>CPU: 2.0 GHz Intel® Xeon® Platinum 8167M;</li> <li>The number of GPUs: 2;</li> <li>The number of CPU cores: 28;</li> <li>The number of CPU threads: 56;</li> <li>RAM: 192 GB;</li> <li>Storage: 3 TB.</li> </ul> <p>Only one model (k-nn) was calculated on a cluster having the following parameters:</p> <ul> <li>Processor: Intel(R) Core(TM) i7-4770 CPU @ 3.40GHz 3.40 GHz;</li> <li>RAM: 16 GB;</li> <li>Windows 64 bit.</li> </ul> <p><strong>Performance statistics</strong></p> <p>All performance statistics are stored in cvs files. Each file corresponds to a particular machine learning method such as a file, "methodName-stat.csv" contains all data regarding a method, "methodName." All files cover the following columns:</p> <ul> <li><em>dataSetName – </em>a name of a data set on which evaluation was carried out; there are three possible values: (i) <em>firstPages</em> refers to the first data set (<em>L<sub>D</sub></em>) that contains textual description of a company; (ii) <em>firstPageLabels</em> refers to the second data set (<em>L<sub>L</sub></em>) that involves link labels that were extracted from an index page; (iii) <em>aggregateDocument</em> refers to the third data set (<em>L<sub>B</sub></em>) that consists of a so-called big document;</li> <li><em>fmeasure</em> - the number of features that were taken into account during evaluation;</li> <li><em>method</em> - the name of function in the caret package;</li> <li><em>parameters</em> - the values of parameters received from a tuning phase of a given classification method;</li> <li><em>precision </em>– the value of method’s precision;</li> <li><em>recall </em>– the value of method’s recall;</li> <li><em>fmeasure</em> - the value of method’s F-measure; </li> <li><em>error</em> - the value of method’s error;</li> <li><em>acc </em>– the value of method’s.</li> </ul> <p><strong>Time processing statistics</strong></p> <p>All time processing statistics, like the performance statistics, are stored in cvs files. Each file corresponds to a particular machine learning method such as a file, "methodName-time.csv". All files cover the following columns:</p> <ul> <li><em>dataSetName – </em>a name of a data set on which evaluation was carried out; there are three possible values: (i) <em>firstPages</em> refers to the first data set (<em>L<sub>D</sub></em>) that contains textual description of a company; (ii) <em>firstPageLabels</em> refers to the second data set (<em>L<sub>L</sub></em>) that involves link labels that were extracted from an index page; (iii) <em>aggregateDocument</em> refers to the third data set (<em>L<sub>B</sub></em>) that consists of a so-called big document;</li> <li><em>featureNo</em> - the number of features that were taken into account during evaluation;</li> <li><em>method</em> - the name of function in the caret package;</li> <li><em>user</em> - user time elapsed for executing a <em>method</em> as an R process;</li> <li><em>system</em> - system time elapsed for executing a <em>method</em> as an R process;</li> <li><em>elapsed</em> - total time elapsed for executing a <em>method</em> as an R process.</li> </ul> <p>For more information about user, system and total elapsed time, please see documentation [3].</p> <p><strong>References</strong></p> <p>[1] https://cran.r-project.org/web/packages/caret/</p> <p>[2] https://topepo.github.io/caret/model-training-and-tuning.html</p> <p>[3] https://stat.ethz.ch/R-manual/R-devel/library/base/html/proc.time.htm</p>
Dataset and code for "Classification of Solar Wind With Machine Learning"
<p>Matlab software and data from http://www.mlspaceweather.org/ for the paper</p> <p>https://agupubs.onlinelibrary.wiley.com/doi/full/10.1002/2017JA024383</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>
INEGI Uso del Suelo y Vegetacion Land Cover Classifications for Mexico (1985, 1993, 2002, 2007, 2011), Harmonized with NLCD 2011 Legend
<p>We have taken the Uso del Suelo y Vegetacion land cover classification products for Mexico (courtesy of Mexico's Instituto Nacional de Estadistica y Geografia, or INEGI) for years 1985, 1993, 2002, 2007, and 2011 (INEGI, 2015); and harmonized their classes with the classes of the Multi-Resolution Land Characteristics Consortium (MRLC) National Land Cover Database (NLCD) (Homer et al., 2015). Details of processing, along with the processing scripts, are archived in GitHub in the <a href="https://github.com/tbohn/NLCD_INEGI/tree/v1.5">NLCD_INEGI</a> project (Bohn, 2019).</p> <p>This project contains the following g-zipped tar files:</p> <ul> <li>SERIE_I.tgz - land cover from 1985</li> <li>SERIE_II.tgz - land cover from 1993</li> <li>SERIE_III.tgz - land cover from 2002</li> <li>SERIE_IV.tgz - land cover from 2007</li> <li>SERIE_V.tgz - land cover from 2011</li> </ul> <p>On LINUX, the contents of these files can be extracted via "tar":</p> <p>tar -xvzf SERIE_I.tgz >& log.tar.txt</p> <p>On Windows, applications such as "7-zip" can extract the contents.</p> <p>Each of these .tgz files contain a folder with the same name but without the ".tgz". Within each of these folders are the following sub-folders:</p> <ul> <li>For SERIE_I to SERIE_IV: <ul> <li>metatiles/ - original land cover shapefiles, with Mexico divided into "metatiles" along UTM zones, as documented in <a href="https://github.com/tbohn/NLCD_INEGI/tree/v1.0/docs/Processing_of_INEGI_USOSV_dataset.docx">Processing_of_INEGI_USOSV_dataset.docx</a></li> <li>geo/ - shapefiles from "metatiles", reprojected into geographic</li> <li>entire/ - shapefiles from "geo" merged into a single file for the entire country</li> </ul> </li> <li>For SERIE_V: <ul> <li>entire/ - original land cover shapefile in Lambert Conical projection, covering all of Mexico</li> <li>geo/ - shapefile from "entire" reprojected into geographic</li> </ul> </li> <li>SERIE_I to SERIE_V: <ul> <li>cve_union/ - shapefiles covering all of Mexico, in geographic projection, with land cover reclassified to NLCD 2011 legend</li> <li>rasters/ - files from "cve_union", rasterized at 0.000350884 degree resolution</li> <li>ascii/ - raster files from "rasters", exported to ascii ESRI grid file format</li> </ul> </li> </ul> <p>Output files (in the "ascii" folders) are ESRI ascii raster grid files, in geographic projection, with cellsize = 0.000350884 degrees.</p>
Human activity classification
<p>Collected dataset comprises body position recordings for various persons of diverse profile while performing six physical activities.</p> <p>The values include: </p> <p>- Cod_pat is the unique code for each person;<br> - Time is the timestamp;<br> - Ax, Ay, Az represent the axis of the acceleration;<br> - Mx, My, Mz represent the axis of the magnetometer;<br> - Ch is the compass heading;<br> - Label is the Class that provide the activity of the person.</p> <p> </p>
Phenology metric layers and their classification layers for the NDVI approximated phenological cycle of Donana from 01/12/2015 to 31/11/2016.
<p>Analysis of changes in the phenological cycle of different plant species provide important information that may be used to assess the impact of seasonal and inter-annual climate variations on terrestrial vegetation. Phenex software has been used for estimating phenology related layers for Donana marshes relying on NDVI time series covering one year period from 01/12/2015 to 31/11/2016.</p> <p>“Phenology_metrics_layer_Dec2015_Nov2016.tif” includes the following layers: (i) green up day, (ii) senescence day, (iii) day of max NDVI value, and (iv) total number of NDVI peaks. These layers are also provided separately with the names: “Greenup_day_Dec2015_Nov2016.tif”, “Senescence_day_Dec2015_Nov2016.tif”, “Max_day_Dec2015_Nov2016.tif”, “Number_of_peaks_Dec2015_Nov2016.tif”.</p> <p>Classification layers based on these layers have been also generated. In particular, "ISODATA_classification_all_input_layers_Dec2015_Nov2016.tif" layer contains the classes generated when providing all phenology related layers as input to the ISODATA algorithm, while "ISODATA_classification_three_input_layers_Dec2015_Nov2016.tif" layer contains contains the classes generated when providing three penology related layers (i.e. greenup day, day of max NDVI value, senescence day layers) as input to the ISODATA algorithm.</p> <p>The above files are accompanied by INSPIRE metadata XML files. Detailed information can be found in the “Readme.pdf” included in the zip containing the dataset.</p> <p> </p>
CLDF dataset derived from Hsiu's "Classification of Na-Meo" from 2015
<p>Cite the source of the dataset as:</p> <blockquote> <p>Hsiu, Andrew (2015): The classification of Na Meo, a Hmong-Mien language of Vietnam. Handout prepared for SEALS 25 (Chiang Mai, 2015/05/27-29).</p> </blockquote>
Accelerometer-Based Multivariate Time-Series Dataset for Calf Behavior Classification
<p><strong>AcTBeCalf Dataset Description</strong></p> <p>The AcTBeCalf dataset is a comprehensive dataset designed to support the classification of pre-weaned calf behaviors from accelerometer data. It contains detailed accelerometer readings aligned with annotated behaviors, providing a valuable resource for research in multivariate time-series classification and animal behavior analysis. The dataset includes accelerometer data collected from 30 pre-weaned Holstein Friesian and Jersey calves, housed in group pens at the Teagasc Moorepark Research Farm, Ireland. Each calf was equipped with a 3D accelerometer sensor (AX3, Axivity Ltd, Newcastle, UK) sampling at 25 Hz and attached to a neck collar from one week of birth over 13 weeks.</p> <p>This dataset encompasses 27.4 hours of accelerometer data aligned with calf behaviors, including both prominent behaviors like lying, standing, and running, as well as less frequent behaviors such as grooming, social interaction, and abnormal behaviors.</p> <p>The dataset consists of a single CSV file with the following columns:</p> <ul> <li><strong>dateTime</strong>: Timestamp of the accelerometer reading, sampled at 25 Hz.</li> <li><strong>calfid</strong>: Identification number of the calf (1-30).</li> <li><strong>accX</strong>: Accelerometer reading for the X axis (top-bottom direction)*.</li> <li><strong>accY</strong>: Accelerometer reading for the Y axis (backward-forward direction)*.</li> <li><strong>accZ</strong>: Accelerometer reading for the Z axis (left-right direction)*.</li> <li><strong>behavior</strong>: Annotated behavior based on an ethogram of 23 behaviors.</li> <li><strong>segId</strong>: Segment identification number associated with each accelerometer reading/row, representing all readings of the same behavior segment.</li> </ul> <p>* the directions are mentioned in relation to the position of the accelerometer sensor on the calf.</p> <p><strong>Code Files Description</strong></p> <p>The dataset is accompanied by several code files to facilitate the preprocessing and analysis of the accelerometer data and to support the development and evaluation of machine learning models. The main code files included in the dataset repository are:</p> <ol> <li><strong>accelerometer_time_correction.ipynb</strong>: This script corrects the accelerometer time drift, ensuring the alignment of the accelerometer data with the reference time.</li> <li><strong>shake_pattern_detector.py</strong>: This script includes an algorithm to detect shake patterns in the accelerometer signal for aligning the accelerometer time series with reference times.</li> <li><strong>aligning_accelerometer_data_with_annotations.ipynb</strong>: This notebook aligns the accelerometer time series with the annotated behaviors based on timestamps.</li> <li><strong>manual_inspection_ts_validation.ipynb</strong>: This notebook provides a manual inspection process for ensuring the accurate alignment of the accelerometer data with the annotated behaviors.</li> <li><strong>additional_ts_generation.ipynb</strong>: This notebook generates additional time-series data from the original X, Y, and Z accelerometer readings, including Magnitude, ODBA (Overall Dynamic Body Acceleration), VeDBA (Vectorial Dynamic Body Acceleration), pitch, and roll.</li> <li><strong>genSplit.py: </strong>This script provides the logic used for the generalized subject separation for machine learning model training, validation and testing.</li> <li><strong>active_inactive_classification.ipynb</strong>: This notebook details the process of classifying behaviors into active and inactive categories using a RandomForest model, achieving a balanced accuracy of 92%.</li> <li><strong>four_behv_classification.ipynb</strong>: This notebook employs the mini-ROCKET feature derivation mechanism and a RidgeClassifierCV to classify behaviors into four categories: drinking milk, lying, running, and other, achieving a balanced accuracy of 84%.</li> </ol> <p>Kindly cite one of the following papers when using this data:</p> <p>Dissanayake, O., McPherson, S. E., Allyndrée, J., Kennedy, E., Cunningham, P., & Riaboff, L. (2024). <em>Evaluating ROCKET and Catch22 features for calf behaviour classification from accelerometer data using Machine Learning models</em>. arXiv preprint arXiv:2404.18159.</p> <p>Dissanayake, O., McPherson, S. E., Allyndrée, J., Kennedy, E., Cunningham, P., & Riaboff, L. (2024). <em>Development of a digital tool for monitoring the behaviour of pre-weaned calves using accelerometer neck-collars</em>. arXiv preprint arXiv:2406.17352</p>
Automated Classification of Conversation Valence and Arousal using Autonomic Nervous System Responses
<p>This repository contains the supplementary file for our study "Automated Classification of Conversation Valence and Arousal using Autonomic Nervous System Responses". The MS Excel file contains all physiological features (individual features and synchrony features) for all valid dyads and all intervals together with self-report ratings of the conversation (Self-Assessment Manikin) and personality trait data (CES-D, BFNES, QCAE). Synchrony features were calculated using code from a previous Zenodo submission (https://zenodo.org/record/7140829).</p>
Land-Cover Classification of Mesoamerica's Cimate Hubs
<p>This project presents land use classification maps obtained through satellite image analyses for 10 study areas in Mesoamerica. A classification algorithm was adapted specifically for the tropics and developed using the latest satellite images available. We applied Object Based Image Analysis method & Random Forest algorithm on 10m Sentinel 1 (S1) & Sentinel 2 (S2) image collections of years 2022/2023. The study area encompassed 10 landscapes spanning 8 countries across Mesoamerica. These areas cover a total of 256 971 km² and were previously defined by Osa Conservation as potential climate adaptation hubs.</p>
EOL computer vision pipelines: Classification for Image Tagging: Flower Fruit
<p>Angiosperms: Stats from Colab:</p> <ul> <li>Number of positive identified reproductive structures: 490</li> <li>Number of possible identified reproductive structures: 4611</li> <li>Number of negative identified reproductive structures: 14833</li> </ul> <p> </p>
EOL computer vision pipelines: Classification for Image Tagging: Image Type: Anura
<p>Produced by the EOL Image Type Classifier. Classifies images as map, phylogeny, illustration, herbarium sheet, or none. Dataset generated for EOL Anura images. See model on the CV for <a href="https://www.kaggle.com/models/eolorg/image-quality-rating-bad-vs-good" target="_blank" rel="noopener">EOL Images Model Zoo on Kaggle</a>.</p>
EOL computer vision pipelines: Classification for Image Tagging: Image Rating: Chiroptera
<p>Produced by the EOL Image Rating Classifier. Classifies images as bad or good quality (used for image gallery sorting). Dataset generated for EOL Chiroptera images. See model on the CV for <a href="https://www.kaggle.com/models/eolorg/image-quality-rating-bad-or-good" target="_blank" rel="noopener">EOL Images Model Zoo on Kaggle</a>.</p>
The classification of names
<p>Cite the source of the dataset as:</p> <blockquote> <p>Handschuh, C. (2019). The classification of names, STUF - Language Typology and Universals, 72(4), 539-572. doi: https://doi.org/10.1515/stuf-2019-0021</p> </blockquote>
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.