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.
9,302
datasets available to search
ShareScore release 0.9.0
Dataset results
9,302 results for “DETECT”
Supplementary data to: Detection of Neoantigen-specific T Cells Following a Personalized Vaccine in a Patient with Glioblastoma
<p>Supplemental Data for the patient described in the manuscript: "Detection of Neoantigen-specific T Cells Following a Personalized Vaccine in a Patient with Glioblastoma". Summary of somatic variant calls from DNA whole exome, gene FPKM from RNA sequencing, and neoantigen predictions for high-affinity (ic<sub>50</sub> <500 nM) candidates.</p>
Structural modelling results to accompany the paper "Uncommon mutational profiles of metastatic colorectal cancer detected during routine genotyping using next generation sequencing: an update"
<p>This repository contains the results of modelling missense mutants in KRAS, NRAS and BRAF observed in our study in the corresponding protein structures. Modelling was performed using FoldX.</p>
Wheat-Ears-Detection-Dataset
<p>Dataset from the Ear density estimation from high resolution RGB imagery using deep learning technique paper</p> <p> <strong>Highlights</strong><br> - 236 high resolution images (6000*4000)<br> - Wheat ears annotated with a bounding box<br> - 30729 ears identified<br> - Spatial resolution (GSD) of 0.13mm/pixel<br> - Two images for each microplots <br> - 20 contrasted genotype with 6 replicated growth in two environment</p> <p>contact : simon.madec@inra.fr </p> <p> </p> <p> </p> <p> </p> <p> </p>
gazeNet: End-to-end eye-movement event detection with deep neural networks
<p>This repository contains synthetic eye-movement dataset used to train deep learning based eye-movement event detection algorithm described in Zemblys, R., Niehorster, D.C. & Holmqvist, K. (2018). gazeNet: End-to-end eye-movement event detection with deep neural networks. Behavior research methods, pp 1–25. <a href="https://doi.org/10.3758/s13428-018-1133-5">https://doi.org/10.3758/s13428-018-1133-5</a></p> <p>Code used to train a model can be found on github <a href="https://github.com/r-zemblys/gazeNet">here</a>. Code to generate synthetic eye-movement data can be downloaded from <a href="https://github.com/r-zemblys/gazeGenNet">here</a>.</p>
Improving Open Source Face Detection by Combining an Adapted Cascade Classification Pipeline and Active Learning
<p>The <em><strong>EAVISE Open Source Face Detection Dataset</strong></em> consists of several items that were used to generate the improved frontal face detection model using LBP features and AdaBoost for OpenCV3.2.</p> <ul> <li>The annotations of the FDDB dataset, converted to the OpenCV format for doing a correct evaluation.</li> <li>The final trained model (IterativeHardPositives+ model) which is included in the OpenCV 3.2 framework.</li> </ul>
Screw and hole detection output results dataset in an autonomous screwing operation
<p>This dataset contains a set of csv files containing the results of a screwing and hole detection developed for a screwing mobile robot. It also contains a set of images representing the inputs, the outputs and some relevant images in the hole detection algorithm.</p> <p>Thee different scenarios were built, and a total of 25 missions were executed in order to build the datasets presented in appendix 5.7. The first scenario (missions 1 to 15), represents a normal operation procedure, meaning, a screwing 6 hole screwing and 5 screws refilling. The second scenario (missions 16 to 20), represents an operation with an exception handling during the refill (the second, third and fourth screws are missing in the refill support). Lastly, the third scenario (missions 21 to 25) has another exception handling, this time on both hole and screw detections (the third, fourth and fifth holes are already screwed, and the screwdriver trigger is not pressed, so the screw is not tightened resulting in a screw detecting after the refilling phase.</p> <p>Also three different group of csv files can be found:</p> <ul> <li><em>hole_detection_mission_xx.csv</em><sup><em><a href="#sdfootnote1sym"><sup>1</sup></a></em></sup>: contains the hole detection result (detected or non detected) and the located hole coordinates (u,v), in pixels;</li> <li> <p><em>detect_screw_screwing_result_mission_xx</em>.csv: contains the screw detection result performed after a screwing to detect if the screw was screwed successfully. 1 means the screwing was ok (there is no screw on the screwdriver), 0 means the screwing was not ok (there was a screw on the screwdriver);</p> </li> <li> <p><em>detect_screw_refill_mission_xx</em>.csv: contains the screw detection result performed after a refill attempt, to check if there was any screw missing in the refill support. 0 means that no screw was missing on the refill support (there was a screw on the screwdriver), 1 means there was a screw missing on the support (there was no screw on the screwdriver).</p> </li> </ul> <p>The <em>mission_xx</em> suffix represents which mission file (rosbag) the mission was acquired in and, each csv file contains the timestamp in which it happens.</p> <p><a href="#sdfootnote1anc">1</a> xx represents the mission number</p>
CREEP Detection and prevention of cyberbullying
<p>The purpose of CREEP is to provide a set of tools to support the detection and prevention of psychological/behavioral problems of cyberbullying teenage victims. The objective will be achieved combining social media monitoring and motivational technologies (virtual coaches integrating chatbots).</p> <p><em>Homepage</em>: <a href="http://creep-project.eu/it/">http://creep-project.eu/it/</a></p>
Sentinel-1 Satellite Imagery Based Ice Road Detection and Monitoring
<p>Canada’s northern ice roads in winter which is more than 3300 miles are freezing later and melting earlier, drastically reducing the forecasting capabilities for the safe use. An attractive Area of Interest (AoI) could be around the region “Yellowknife” in Canada, which is also mentioned in the recent TV show (<a href="https://en.wikipedia.org/wiki/Ice_Road_Truckers">https://en.wikipedia.org/wiki/Ice_Road_Truckers</a>). This area could be used to train the algorithm to detect the current situation and to forecast the time window to close and open the ice tracks to the citizens. Mockup could be achieved by building a screenshot mockup on mobile device (Smartphone/Tablet).</p>
Semantic Frame Embeddings for Detecting Relations between Software Requirements
<p><strong>FN-RE frame embeddings-is semantic resource built based on embedding-based representations of semantic frames in FrameNet, which was developed to support the detection of relations between software requirements. Our embeddings, which encapsulate contextual information at the semantic frame level, were trained on a large corpus of requirements (i.e., a collection of more than three million mobile application reviews). </strong></p>
AEROARMS - Image Dataset for the Crawler Indirect Detection through its Cage
<p>Dataset containing images and ground-truth position of the crawler's cage used in the AEROARMS project experiments.</p>
AEROARMS - Crawler Direct Detection Image Dataset
<p>Dataset containing images and ground-truth position of the crawler used in the AEROARMS project experiments.</p>
Planetary Surface Features Change Detection Dataset
<p><strong>Summary</strong></p> <p>This dataset contains bi-temporal images pairs with associated labels of <em>change </em>or <em>no-change</em> describing whether there was a change in surface features between the two images acquired over the same location at two different times. This dataset contains images from four different instruments orbiting three different planets, each of which contains four representations of the bi-temporal image pair: composite grayscale, absolute difference, signed difference, and autoencoder bottleneck representations (described in detail in [1]). We also include the grayscale image tiles these representational datasets were created from. All datasets contain 100x100 images tiles that were cropped from larger images. We describe each below. </p> <p><strong>Contents</strong></p> <p><strong>hirise_rsl.zip</strong> : all subdirectories contain <em>change </em>and <em>no-change </em>examples represented as composite grayscale, absolute difference, signed difference, and autoencoder bottleneck from a before and after HiRISE image of recurring slope lineae on Mars<em>. </em>Subdirectory names are garni_XXXXXX_YYYYYY where Garni is the name of the crater on Mars shown in the images, XXXXXX is the HiRISE image ID of the before image, and YYYYYY is the HiRISE image ID of the after image. The "*_lcn" ending on some directories indicates that local contrast normalization was applied. The "*_gs_illum" and "*_gs_slope" directories contain composite grayscale representation with a third band that contains the difference between illumination (illum) and slope values at the same locations. Images with line endings _vflip, _hflip, _rot90, _rot180, and _rot270 were the result of vertical flips, horizontal flips, 90-deg rotations, 180-deg rotations, and 270-deg rotations of the image with the corresponding prefix.</p> <p><strong>ctx_impacts.zip</strong> : all subdirectories contain <em>change </em>and <em>no-change </em>examples represented as composite grayscale, absolute difference, signed difference, and autoencoder bottleneck from a before and after CTX image of meteorite impacts on Mars. The prefix in each image name corresponds to the image pair described in the Appendix in [1].</p> <p><strong>lroc_impacts.zip </strong>: all subdirectories contain <em>change </em>and <em>no-change </em>examples represented as composite grayscale, absolute difference, signed difference, and autoencoder bottleneck from a before and after LROC image of meteorite and spacecraft landing impacts on the Moon. Filenames correspond to pair names provided in the Appendix in [1].</p> <p><strong>planet_misc.zip</strong> : all subdirectories contain <em>change </em>and <em>no-change </em>examples represented as composite grayscale, absolute difference, signed difference, and autoencoder bottleneck from a before and after PlanetScope image of miscellaneous processes on Earth. Filenames correspond to pair names provided in the Appendix in [1].</p> <p><strong>*_before_after_grayscale.zip</strong> : before and after grayscale tiles used to create image representations in above directories (indicated with _before and _after suffix in filenames). Images that contain "_0_" in the filename have the label <em>no-change </em>and images with "_1_" in the filename have the label <em>change</em>.</p> <p>[1] Kerner et al. (2019) Deep Learning Methods Toward Generalized Change Detection on Planetary Surfaces. In review at <em>Journal of Selected Topics in Earth Observations and Remote Sensing</em>.</p> <p><strong>Attribution</strong></p> <p>If you use this dataset in your own work, please cite this DOI: 10.5281/zenodo.2373798 as well as the paper below:</p> <p>Kerner, H. R., Wagstaff, K. L., Bue, B. D., Gray, P. C., Bell, J. F., & Amor, H. B. (2019). Toward generalized change detection on planetary surfaces with convolutional autoencoders and transfer learning. <em>IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing</em>, <em>12</em>(10), 3900-3918.</p>
Dataset of tweets, used to detect hazardous events at the Baths of Diocletian site in Rome
<p>This dataset is composed by 276865 tweets, extracted from the Twitter stream, in the period from May 2018 to May 2019. Each element is characterized by the ID, that permits to retrieve the tweet from the stream, the text content, the GPS information (if it is provided or not), the localization, and the time. The last attribute of the elements of the dataset is the label associated to the tweet after the process of event detection. If the tweet has been identified as containing useful information of an hazardous event at the Baths of Diocletian site in Rome, the last attribute (Generated Useful Info at BOD) is "yes", otherwise its value is "no".</p>
Systematic assessment of burst impurity in confocal-based single-molecule fluorescence detection using Brownian motion simulations - photon timetag simulation files
<p>Attached are the photon timestamp and channels simulated for different 3D diffusing molecules simulations at different conditions (simulation was performed by PyBroMo).</p> <p>Each of the files has, in its name, a code. The meaning of the codes are as following:</p> <pre>f32445 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a numerical PSF model </pre> <pre>a01f8f - 15 molecules at a concentration of 31 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a numerical PSF model</pre> <pre>9ff667 - 15 molecules at a concentration of 15.5 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a numerical PSF model</pre> <pre>71154a - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 22.5 micron^2/s - 60 second simulation using a numerical PSF model</pre> <pre>ad926d - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 5.625 micron^2/s - 60 second simulation using a numerical PSF model</pre> <pre>1ab235 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s - 180 second simulation using a numerical PSF model</pre> <pre>d00978 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 5.625 micron^2/s - 180 second simulation using a numerical PSF model</pre> <p> </p> <pre>2469bb - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a Gaussian PSF model </pre> <pre>4be121 - 15 molecules at a concentration of 31 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a Gaussian PSF model</pre> <pre>a7088f - 15 molecules at a concentration of 15.5 pM, with a diffusion coefficient of 90 micron^2/s - 60 second simulation using a Gaussian PSF model</pre> <pre>023983 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 22.5 micron^2/s - 60 second simulation using a Gaussian PSF model</pre> <pre>653f61 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 5.625 micron^2/s - 60 second simulation using a Gaussian PSF model</pre> <pre>4f06ee - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s - 180 second simulation using a Gaussian PSF model</pre> <pre>dec32c - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 5.625 micron^2/s - 180 second simulation using a Gaussian PSF model</pre> <p> </p> <pre>85b0a1 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s , 10 of which belong to a sub-population with a mean FRET efficiency of 0.75, and the leftover 5 belong to another sub-populations with a mean FRET efficiency of 0.50 - 60 second simulation using a Numerical PSF model</pre> <pre>964ef3 - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s , 10 of which belong to a sub-population with a mean FRET efficiency of 0.75, and the leftover 5 belong to another sub-populations with a mean FRET efficiency of 0.50 - 180 second simulation using a Numerical PSF model</pre> <p> </p> <pre>f28f6e - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s , 10 of which belong to a sub-population with a mean FRET efficiency of 0.75, and the leftover 5 belong to another sub-populations with a mean FRET efficiency of 0.50 - 60 second simulation using a Gaussian PSF model</pre> <pre>c311dd - 15 molecules at a concentration of 62 pM, with a diffusion coefficient of 90 micron^2/s , 10 of which belong to a sub-population with a mean FRET efficiency of 0.75, and the leftover 5 belong to another sub-populations with a mean FRET efficiency of 0.50 - 180 second simulation using a Gaussian PSF model</pre>
Supplementary data for: Detection of expressed mutations in acute myeloid leukemia cells using single cell RNA-sequencing
<p>Supplemental data for the publication:<br> Detection of expressed mutations in acute myeloid leukemia cells using single cell RNA-sequencing </p> <p>Contents: <br> - expression_matrices.tar - Gene/Barcode expression matrices from `cellranger count`<br> - *.seurat.rds - R object files with Seurat analyses and data structures for each sample<br> - scrna_mutations.tar.gz - copy of a git repository containing additional scripts and data - also hosted at <a href="https://github.com/genome/scrna_mutations">https://github.com/genome/scrna_mutations</a> (snapshot as of May 20, 2019)</p>
Baseline Detection in Arabic-script Manuscripts Dataset (BADAM)
<p>A freely licensed dataset of 400 annotated Arabic-script manuscript pages for baseline detection. Refer to the <a href="https://hal.archives-ouvertes.fr/hal-02167164">article</a> for more information.</p> <p> </p> <p> </p>
Validity of accelerometry in step detection and gait speed measurement in orthogeriatric patients (DATASET)
<p>see README.txt for descriptions of files and formats<br> </p>
Detecting weak and strong Islamophobic hate speech on social media
<p>Data, code and annotation guidelines for our publication, 'Detecting weak and strong Islamophobic hate speech on social media' (2019).</p>
Datasets from Costa Rican news sources for fake news detection
<p>Today, technology has changed the way information is propagated and how the message is received. The interpretation of the news may have different angles depending on the source of origin. Because of this, there has been an increase in misinformation, in the way of influencing public opinion and in how we perceive or estimate reality.<br> The objective of this beta dataset is to be used for the evaluation of data mining models that allow the classification of true or potentially fake news that are generated by Costa Rican news sites only. This is intended to assess the level of reliability of the models and extend the scope of this research in future work.</p> <p>The dataset has been pre-processed (standarized using lower cases, lemmatized and removed any possible noise from it) and analyzed using LIWC dictionaries. One version has the news text in Spanish and was processed using LIWC2007 dictionary in Spanish. The second version was processed using LIWC2015 English dictionary and has the news text in English. The reason to having two versions is to be able to test using the newer LIWC dictionary which includes more Summary Language Variables that the Spanish version doesn't have and analyze how this and other variables can contribute to different results when creating models. </p> <p>The file "DescripcionVariables" provides a description of all variables used.</p> <p> </p>
Logistics Transport Label Data - 'Lean Training Data Generation for Planar Object Detection Models in Unsteady Logistics Contexts'
<p>Example dataset described in ICMLA2019 Paper 'Lean Training Data Generation for Planar Object Detection Models in Unsteady Logistics Contexts' (Dörr, Brandt, Meyer, Pouls).</p>
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.