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.
4,612
datasets available to search
ShareScore release 0.9.0
Dataset results
4,612 results for “labelled”
Рис. 5–10. Pterostichus (Petrophilus) magoides, этикетки и генитаΛии самца. 5 – этикетки гоΛотипа; 6 – этикетки паратипа; 7 – энΔофаΛΛус, виΔ сΛева (экземпΛяр из Рахмановского Λесничества, Казахстан); 8–9 – меΔиаΛьная ΔоΛя эΔеагуса (экземпΛяр с Курчумского хребта, Казахстан): 8 – виΔ сΛева, 9 – виΔ сверху; 10 – правая парамера, виΔ сбоку (этот же экземпΛяр). Figs 5–10. Pterostichus (Petrophilus) magoides, labels and male genitalia. 5 – labels of the holotype; 6 – labels of the paratype; 7 – endophallus, left view (specimen from the Rakhmanovskoe Forestry, Kazakhstan); 8–9 – median lobe of aedeagus (specimen from the Kurchum Mountain Range, Kazakhstan): 8 – left view, 9 – dorsal view; 10 – right paramere, lateral view (the same specimen). in To the systematic position of Pterostichus (Petrophilus) magoides (Straneo, 1937) (Coleoptera: Carabidae) from the Altai Mountains
Рис. 5–10. Pterostichus (Petrophilus) magoides, этикетки и генитаΛии самца. 5 – этикетки гоΛотипа; 6 – этикетки паратипа; 7 – энΔофаΛΛус, виΔ сΛева (экземпΛяр из Рахмановского Λесничества, Казахстан); 8–9 – меΔиаΛьная ΔоΛя эΔеагуса (экземпΛяр с Курчумского хребта, Казахстан): 8 – виΔ сΛева, 9 – виΔ сверху; 10 – правая парамера, виΔ сбоку (этот же экземпΛяр). Figs 5–10. Pterostichus (Petrophilus) magoides, labels and male genitalia. 5 – labels of the holotype; 6 – labels of the paratype; 7 – endophallus, left view (specimen from the Rakhmanovskoe Forestry, Kazakhstan); 8–9 – median lobe of aedeagus (specimen from the Kurchum Mountain Range, Kazakhstan): 8 – left view, 9 – dorsal view; 10 – right paramere, lateral view (the same specimen).
NHANES II Spinal X-ray with Extra Labels For Reference Vertebral Bodies (C2, S1)
<p>The NHANES radiographs (https://www.nlm.nih.gov/databases/download/nhanes.html) were scanned by Dr. Bernie Huang at the University of California at Los Angeles and the University of California at San Francisco. It originally contained 17,000 Spinal X-rays with 600 of them annotated with vertebra coordinates. Based on this fact we invited two internal radiologists to create extra reference vertebra coordinates for S1 and C2 for these 600 annotated X-rays. The project is sponsored by Novartis and the University of Oxford jointly.</p>
EMG from Combination Gestures with Ground-truth Joystick Labels
<p>Dataset of surface EMG recordings from 11 subjects performing single and combination gestures, from "**A Multi-label Classification Approach to Increase Expressivity of EMG-based Gesture Recognition**" by Niklas Smedemark-Margulies, Yunus Bicer, Elifnur Sunger, Stephanie Naufel, Tales Imbiriba, Eugene Tunik, Deniz Erdogmus, and Mathew Yarossi.</p> <p>For more details and example usage, see the following:</p> <ul> <li>Paper pdf - <a href="https://arxiv.org/pdf/2309.12217.pdf">https://arxiv.org/pdf/2309.12217.pdf</a></li> <li>Experiment code - <a href="https://github.com/neu-spiral/multi-label-emg">https://github.com/neu-spiral/multi-label-emg</a></li> </ul> <h1>Contents</h1> <p>Dataset of single and combination gestures from 11 subjects. <br>Subjects participated in 13 experimental blocks.<br>During each block, they followed visual prompts to perform gestures while also manipulating a joystick.<br>Surface EMG was recorded from 8 electrodes on the forearm; labels were recorded according to the current visual prompt and the current state of the joystick.</p> <p>Experiments included the following blocks:</p> <ul> <li>1 Calibration block</li> <li>6 Simultaneous-Pulse Combination blocks (3 without feedback, 3 with feedback)</li> <li>6 Hold-Pulse Combination blocks (3 without feedback, 3 with feedback)</li> </ul> <p>The contents of each block type were as follows:</p> <ul> <li>In the Calibration block, subjects performed 8 repetitions of each of the 4 direction gestures, 2 modifier gestures, and a resting pose.<br>Each Calibration trial provided 160 overlapping examples, for a total of: 8 repetitions x 7 gestures x 160 examples = 8960 examples.</li> <li>In Simultaneous-Pulse Combination blocks, subjects performed 8 trials of combination gestures, where both components were performed simultaneously.<br>Each Simultaneous-Pulse trial provided 240 overlapping examples, for a total of: 8 trials x 240 examples = 1920 examples.</li> <li>In Hold-Pulse Combination blocks, subjects performed 28 trials of combination gestures, where 1 gesture component was held while the other was pulsed.<br>Each Hold-Pulse trial provided 240 overlapping examples, for a total of: 28 trials x 240 examples = 6720 examples.</li> </ul> <p>A single data example (from any block) corresponds a window 250ms of EMG recorded at 1926Hz (built-in 20–450 Hz bandpass filtering applied).<br>A 50ms step size was used between each window; note that neighboring data examples are therefore overlapping.</p> <p>Feedback was provided as follows:</p> <ul> <li>In blocks with feedback, a model pre-trained on the Calibration data was used to give realtime visual feedback during the trial.</li> <li>In blocks without feedback, no model was used, and the visual prompt was the only source of information about the current gesture.</li> </ul> <p>For more details, see the paper.</p> <h1>Labels</h1> <p>Two types of labels are provided: </p> <ul> <li>joystick labels were recorded based on the position of the joystick, and are treated as ground-truth.</li> <li>visual labels were also recorded based on what prompt was currently being shown to the subject.</li> </ul> <p>For both joystick and visual labels, the following structure applies. Each gesture trial has a two-part label.</p> <p>The first label component describes the direction gesture, and takes values in {0, 1, 2, 3, 4}, with the following meaning:</p> <ul> <li>0 - "Up" (joystick pull)</li> <li>1 - "Down" (joystick push)</li> <li>2 - "Left" (joystick left)</li> <li>3 - "Right" (joystick right)</li> <li>4 - "NoDirection" (absence of a direction gesture; none of the above)</li> </ul> <p>The second label component describes the modifier gesture, and takes values in {0, 1, 2}, with the following meaning:</p> <ul> <li>0 - "Pinch" (joystick trigger button)</li> <li>1 - "Thumb" (joystick thumb button)</li> <li>2 - "NoModifier" (absence of a modifier gesture; none of the above)</li> </ul> <h2>Examples of Label Structure</h2> <p>Single gestures have labels like (0, 2) indicating ("Up", "NoModifier") or (4, 1) indicating ("NoDirection", "Thumb").</p> <p>Combination gesture have labels like (0, 0) indicating ("Up", "Pinch") or (2, 1) indicating ("Left", "Thumb").</p> <h1>File layout</h1> <p>Data are provided in Numpy and MATLAB format. Descriptions below apply for both.</p> <p>Each experimental block is provided in a separate folder.<br>Within one experimental block, the following files are provided:</p> <ul> <li>`data.npy` - Raw EMG data, with shape (items, channels, timesteps).</li> <li>`joystick_direction_labels.npy` - one-hot joystick direction labels, with shape (items, 5).</li> <li>`joystick_modifier_labels.npy` - one-hot joystick modifier labels, with shape (items, 3).</li> <li>`visual_direction_labels.npy` - one-hot visual direction labels, with shape (items, 5).</li> <li>`visual_modifier_labels.npy` - one-hot visual modifier labels, with shape (items, 3).</li> </ul> <h1>Loading data</h1> <p>For example code snippets for loading data, see the associated code repository.</p>
CryoVirusDB: An Expert Labelled Cryo-EM Image Dataset for AI-Driven Virus Particle recognition and Extraction
<p><span>With the advancements in instrumentation, image processing algorithms, and computational capabilities, single-particle electron cryo-microscopy (cryo-EM) has achieved nearly atomic resolutions in the 3D reconstruction of viruses. These detailed structures play a crucial role in comprehending the biological functions and advancing the development of more precise vaccines and antiviral treatments. Despite the effectiveness of deep learning in analyzing microscopic images, its potential in identifying and extracting virus particles from cryo-EM micrographs has been hindered by the limited availability of diverse and high-quality datasets. In this study, we introduce 'CryoVirusDB,' a labeled dataset containing coordinates of accurately selected virus particles in cryo-EM micrographs. CryoVirusDB comprises 9,941 micrographs featuring 9 different viruses along with the coordinates of 0.2 million virus particles in total. We anticipate that CryoVirusDB will enhance the capabilities of deep learning in accurately identifying virus particles in cryo-EM micrographs, thereby facilitating the subsequent 2D-3D reconstruction process.</span></p> <p><span>Instructions to download and use dataset: https://github.com/BioinfoMachineLearning/CryoVirusDB</span></p>
Dataset to manuscript entitled "Non-fluorescent transient states of tyrosine - a basis for label-free protein conformation and interaction studies" submitted to Scientifc Reports
<p><strong>This folder contains all raw data underlying the results presented in a manuscript, submitted to</strong><strong> </strong><strong><em>Scientifc Reports, </em>and entitled</strong><strong>:</strong></p> <p><strong><em>Non-fluorescent transient states of tyrosine - a basis for label-free protein conformation and interaction studies</em></strong></p> <p> </p> <p><strong>Authored by:</strong></p> <p><strong>Niusha Bagheri <sup>1</sup>, Hongjian Chen <sup>1</sup>, Mihailo Rabasovic <sup>2</sup>, Jerker Widengren <sup>1,*</sup></strong></p> <p><sup>1 </sup>Royal Institute of Technology (KTH), Experimental Biomolecular Physics, Dept. Applied Physics, Albanova University Center 106 91 Stockholm, Sweden</p> <p><sup>2 </sup>Laboratory for Biophysics, Institute of Physics Belgrade, Pregrevica 118<br>11080 Zemun-Belgrade, Serbia</p> <p>* Corresponding author (jwideng@kth.se)</p> <p><strong> </strong></p> <p><strong>The data files are grouped into the different techniques used to generate them, and refer to the figures/tables in the manuscript where the extracted results are presented. </strong></p> <p> </p> <p><strong>ABSTRACT</strong></p> <p>The amino acids tryptophan, tyrosine, and phenylalanine have been extensively used for different label-free protein studies, based on the intensity, lifetime, wavelength and/or polarization of their emitted fluorescence. Like most fluorescent organic molecules, these amino acids also tend to undergo transitions into dark meta-stable states, such as triplet and photo-radical states. While this may be perceived as a problem, these transitions are also highly environment-sensitive and can be used as an additional set of parameters, reflecting interactions, folding states, and immediate environments around the proteins. In this work, we applied the transient state monitoring (TRAST) technique, analyzing the average intensity of tyrosine emission under different excitation modulations, to characterize the photo physics of tyrosine for such readout purposes. By investigating how the dark state transitions of tyrosine varied with excitation intensity and solvent conditions we established a photophysical model for tyrosine. Next, we studied Calmodulin (containing two tyrosines), which upon calcium binding takes a more folded conformation. From these TRAST experiments, performed with 280nm time-modulated excitation, we show that tyrosine dark state transitions clearly change with the calmodulin conformation, and may thus represent a useful source of information for (label-free) analyses of protein conformations and interactions.</p>
Fig.ç4.Ec hinoderes ohtsukai sp. nov., paratype, female (ZIHU 3983), scanning electron micrographs. A, Mouth cone, lateral view; B, introvert, lateral view. Abbreviations: oo, outer oral styles; sc, scalids; sp, spinoscalids; tr, trichoscalids. Digits a er the labels refer to introvert ring numbers. in A New Brackish-water Species of Echinoderes (Kinorhyncha: Cyclorhagida) from the Seto Inland Sea, Japan
Fig.ç4.Ec hinoderes ohtsukai sp. nov., paratype, female (ZIHU 3983), scanning electron micrographs. A, Mouth cone, lateral view; B, introvert, lateral view. Abbreviations: oo, outer oral styles; sc, scalids; sp, spinoscalids; tr, trichoscalids. Digits a er the labels refer to introvert ring numbers.
Images of mouse VTA and SNc sections labeled for neurotransmitter phenotype markers via RNAscope
<p>48 coronal sections from 3 male and 3 female C57Bl/6J mice were labeled for mRNAs encoding the canonical vesicular transporters for dopamine (VMAT2), GABA (VGAT), and glutamate (VGLUT2). These sections were then imaged via confocal microscopy and saved as CZI files, editable with Zeiss Zen software. These image files include 'event marker' graphics, indicating where neurons positive for one or more of the above transporters are. </p> <p>The protocols used for sample preparation, labeling, imaging, and counting are linked in the Related Works section. </p> <p>Cell count data are organized by subregion (SUBREGION counts for R.csv), anterior-posterior (e.g. VGATVTA.csv), or anterior-posterior and medial-lateral distribution (e.g. 'snc triple.csv' or 'snc vmat2 AP and ML.csv').</p> <p>The R code provided uses these csv files to visualize expression patterns across VTA and SNc. </p>
Pockmark Bounding Box Detection and Segmentation Labels
<p>This dataset contains 256x256 pixel jpeg images of gridded depth values as well as binary masks for pixels containing pockmarks (these jpegs are merged together with the depth image on the left and the mask on the right, making a 512x256 image). These are contained within the subdirectory 'PockmarkMaskAnnotations'.</p> <p>Additionally, this dataset contains a csv containing bounding box annotations (label, bounding box coordinates in terms of image pixels, and a unique integer for the label) of pockmarks in each image. These are contained within the subdirectory 'PockmarkBoxAnnotations'.</p> <p>Together, these annotations can be used to construct either a bounding box object detector, a bounding box and mask object detector, or a semantic segmentation model.</p> <p>These were the labels used for the experiments described in Lundine et al., 2023. See this reference to find original data sources to the collected bathymetry data.</p> <p>Lundine, M., Brothers, L., Trembanis, A., Deep learning-based pockmark detection: implications for quantitative seafloor characterization, Geomorphology, 2023, Volume 421, 108524, <a href="https://doi.org/10.1016/j.geomorph.2022.108524">https://doi.org/10.1016/j.geomorph.2022.108524</a>.</p> <p> </p>
Dead Sea Scrolls data collection (images, labels, prediction plots) for dating ancient manuscripts using radiocarbon and AI-based writing style analysis
<p>The dataset is associated with the following article:<br>Title: <strong>Dating ancient manuscripts using radiocarbon and AI-based writing style analysis</strong><br>Authors: Mladen Popović, Maruf A. Dhali, Lambert Schomaker, Johannes van der Plicht, Kaare Lund Rasmussen, Jacopo La Nasa, Ilaria Degano, Maria Perla Colombini, and Eibert Tigchelaar<br><em>(Under review)</em></p> <p>This data set is collected for the ERC project:<br>The Hands that Wrote the Bible: Digital Palaeography and Scribal Culture of the Dead Sea Scrolls<br>PI: Mladen Popović<br>Grant agreement ID: 640497<br>Project website: <a href="https://cordis.europa.eu/project/id/640497">https://cordis.europa.eu/project/id/640497</a></p> <p> </p> <p><strong>Copyright (c) </strong> University of Groningen, 2024. All rights reserved.<br><strong>Disclaimer and copyright notice for all data contained on the *.tar.gz files:</strong></p> <p><strong>1)</strong> permission is hereby granted to use the data for research purposes. It is not allowed to distribute this data for commercial purposes.</p> <p><strong>2) </strong>provider gives no express or implied warranty of any kind, and any implied warranties of merchantability and fitness for purpose are disclaimed.</p> <p><strong>3) </strong>provider shall not be liable for any direct, indirect, special, incidental, or consequential damages arising out of any use of this data.</p> <p><strong>4) </strong>the user should refer to the first public article mentioned above on this data set.</p> <p><strong>5) </strong>the recipient should refrain from proliferating the data set to third parties external to his/her local research group. Please refer interested researchers to this site to obtain their own copy.</p> <p> </p> <p><strong>Organization of the data:<br></strong><em>(Update on 19 April 2024: OxCal data for accepted 2-sigma ranges are updated with the incusion and exclusion of minor peaks. New prediction plots are added after the model is trained with accepted 2-sigma ranges, including minor peaks. The old plots are also kept. <br><br><OLD Updates below; disregard><br>updated on 07-Feb-2024: OxCal data for selected ranges added in a new directory in addition to previously available original OxCal data. Enoch's prediction plots and test images are reorganized for easy access to the users.<br><OLD Updates above; disregard><br><br>Please use the files from this version and disregard the previous two versions: 10.5281/zenodo.10629480 and 10.5281/zenodo.8168210)</em></p> <p>There are four *.tar.gz files:</p> <p><em><strong>C14-Oxcal-data-updated.tar.gz</strong></em> contains one directory with radiocarbon data (OxCal [1] raw data) for all 30 manuscripts. Three additional directories contain name-corrected files for original OxCal data, files with accepted ranges, and files with accepted ranges including minor peaks. Please refer to the original article for details about OxCal data and the manuscripts. 25 out of 30 raw OxCal data are used (accepted ranges only) as the training labels during the training of Enoch, the date prediction model.</p> <p><em><strong>train-images-c14.tar.gz</strong></em> contains the clean and preprocessed (binarized, aligned, and arrangement corrected) training images for the 25 radiocarbon-dated training manuscripts (including 4Q52; 64 images in total). </p> <p><em><strong>test-images-all.tar.gz</strong></em> contains the clean and preprocessed test images for 135 previously undated manuscripts. The images are organized in three different directories: the first one with all 359 images for the 135 manuscripts, the second one with the selected 135 images, and the final one with 25 images to illustrate the poor quality of images. </p> <p><em><strong>Enoch-prediction-new-with-minor-peaks.tar.gz</strong></em> contains the new date prediction plots for each of the 135 test images, where Enoch was trained with the inclusion of minor peaks for the 2-sigma accepted ranges and with a data balancing threshold of 0.05. These plots are used by expert palaeographers' evaluation of Enoch's style-based date predictions of 135 previously undated manuscripts.</p> <p><em><strong>Enoch-predictions.tar.gz</strong></em> contains the date prediction plots for each of the 135 test images. There are two directories inside the *.tar.gz file:<br><br>- <em>prediction-plots-for-selected-135:</em> Prediction plots with data balancing threshold of 0.05. <br>- <em>extra-plots:</em> contains four additional directories:<br> - <em>Enoch-predictions-c14wo4Q52-balanced05:</em> Prediction plots with data balancing threshold of 0.05. <br> - <em>Enoch-predictions-c14wo4Q52-balanced10:</em> Prediction plots with data balancing threshold of 0.1.<br> - <em>Enoch-predictions-c14wo4Q52-unbalanced:</em> Unbalanced raw predictions.<br> - <em>Enoch-predictions-c14wo4Q52-combined:</em> Combined plots with all three prediction plots (unbalanced, 0.05, 0.1).<br>Please refer to the original article for more details.</p> <p>The updated code to run the plot is available here: <a href="https://doi.org/10.5281/zenodo.10998860">https://doi.org/10.5281/zenodo.10998860</a></p> <p><strong>If you have any questions, please get in touch with us:</strong><br>Mladen Popović <m.popovic(at)rug.nl><br>Maruf A. Dhali <m.a.dhali(at)rug.nl><br>Lambert Schomaker <l.r.b.schomaker(at)rug.nl></p> <p> </p> <p><strong>References:</strong><br>1. Bronk Ramsey, C. (2001). Development of the radiocarbon calibration program. <em>Radiocarbon</em>, <em>43</em>(2A), 355-363.</p>
RoadTrafficMARKS: Dataset of 10057 images (256x256 pixels) of Curved arrow, Straight arrow, Pedestrian crossing, Straight-right merge arrow, Merge arrow, Left arrow, Yield, Stop, Right arrow, Straight-left merge arrow, Speed limit and Straight-right-left merge arrow markings and their BoundingBox labels
<p><strong>The dataset consists of 10057 PNG images (256x256 pixels) of </strong><strong>high resolution aerial orthoimages </strong><strong>taggged with </strong><strong>twelve classes of traffic signals</strong><strong>: (1) Curved arrow, (2) Straight arrow, (3) Pedestrian crossing, (4) Straight-right merge arrow, (5) Merge arrow, (6) Left arrow, (7) Yield, (8) Stop, (9) Right arrow, (10) Straight-left merge arrow, (11) Speed limit and (12) Straight-right-left merge arrow markings, together with their corresponding Bounding Boxes. The dataset has been created in the framework of the SROADEX project to train an identification process based on artificial neural networks.</strong></p> <p><strong>The dataset was created by manually tagging the twelve class of marks on orthoimage tiles of 256x256 pixels </strong><strong><strong>with the LabelMe tool</strong>. After the semantic labeling (manual digitalization of the contour of the signals), a transformation and random splitting process has been carried to prepare the data for the neural networks</strong><strong><strong> training</strong>. It resulted in 80% of the images for training (8031), 10% for validation (1000) and 10% for testing (1021).</strong></p> <p><strong>The next table presents the number of images of each class on the </strong><strong><strong>"train", "valid" and "test" </strong>sets.</strong></p> <table> <tbody> <tr> <td> </td> <td>Train</td> <td>Valid</td> <td>Test</td> <td>Total</td> </tr> <tr> <td>CURVED ARROW</td> <td>319</td> <td>43</td> <td>48</td> <td>410</td> </tr> <tr> <td>STRAIGHT ARROW</td> <td>6730</td> <td>806</td> <td>843</td> <td>8379</td> </tr> <tr> <td>PEDESTRIAN CROSSING</td> <td>3881</td> <td>465</td> <td>485</td> <td>4831</td> </tr> <tr> <td>STRIGNT-RIGHT MERGE ARROW</td> <td>1373</td> <td>187</td> <td>177</td> <td>1737</td> </tr> <tr> <td>MERGE ARROW</td> <td>550</td> <td>91</td> <td>59</td> <td>700</td> </tr> <tr> <td>LEFT ARROW </td> <td>238</td> <td>33</td> <td>31</td> <td>302</td> </tr> <tr> <td>YIELD</td> <td>356</td> <td>47</td> <td>40</td> <td>443</td> </tr> <tr> <td>STOP</td> <td>141</td> <td>19</td> <td>15</td> <td>175</td> </tr> <tr> <td>RIGHT ARROW</td> <td>836</td> <td>93</td> <td>111</td> <td>1040</td> </tr> <tr> <td>STRIGNT-LEFT MERGE ARROW</td> <td>152</td> <td>19</td> <td>21</td> <td>192</td> </tr> <tr> <td>SPEED LIMIT</td> <td>392</td> <td>50</td> <td>45</td> <td>487</td> </tr> <tr> <td>STRIGNT-RIGHT-LEFT MERGE ARROW</td> <td>82</td> <td>9</td> <td>9</td> <td>100</td> </tr> </tbody> </table>
MultiPosture: A Dataset of body joints keypoints extracted using MediaPipe for multi-task sitting posture recognition with upper and lower body labels
<p>This dataset contains skeletal pose data extracted from video recordings of 13 participants performing various sitting postures in home environments. The data was processed using MediaPipe Pose Heavy model and includes 4,800 frames of 3D skeletal coordinates (x, y, z) for 11 key body joints, with each frame manually labeled for both upper and lower body posture classifications.</p> <p>The data is stored in CSV format with normalized coordinates relative to hip center, containing 33 input dimensions (11 joints × 3 coordinates) representing key skeletal points. To protect participant privacy, only the processed skeletal coordinates are included, with no raw video or image data due to privacy constraints.<br><br></p> <p>Upper Body Labels:</p> <ul> <li>TUP: Upright trunk position</li> <li>TLB: Trunk leaning backward</li> <li>TLF: Trunk leaning forward</li> <li>TLR: Trunk leaning right</li> <li>TLL: Trunk leaning left</li> </ul> <p>Lower Body Labels:</p> <ul> <li>LAP: Legs apart</li> <li>LWA: Legs wide apart</li> <li>LCS: Legs closed</li> <li>LCR: Legs crossed right over left</li> <li>LCL: Legs crossed left over right</li> <li>LLR: Legs lateral right</li> <li>LLL: Legs lateral left</li> </ul> <p>Each frame in the dataset has been manually labeled and validated by experts, making it particularly suitable for developing and evaluating machine learning models for ergonomic monitoring systems, ambient assisted living applications, and general posture recognition research.</p> <p>This dataset was collected as part of the study:</p> <p><strong>D. Carneros-Prado, L. Cabañero-Gómez, E. Johnson, I. González, J. Fontecha and R. Hervás, "A Comparison Between Multilayer Perceptrons and Kolmogorov-Arnold Networks for Multi-Task Classification in Sitting Posture Recognition," in <em>IEEE Access</em>, vol. 12, pp. 180198-180209, 2024, doi: 10.1109/ACCESS.2024.3510034. </strong><em><a href="https://ieeexplore.ieee.org/abstract/document/10772228" target="_blank" rel="noopener">link</a></em></p> <p> </p>
Dataset: A Labeled Dataset for Osteoporosis Screening Based on Electromagnetic Attenuation
<p><strong>README</strong></p> <p><strong>Dataset name:</strong> osseus_dataset.csv </p> <p><strong>Version:</strong> 1.0 </p> <p><strong>Dataset period:</strong> 07/01/2021 - 09/31/2023</p> <p><strong>Dataset Characteristics:</strong> Multivalued </p> <p><strong>Number of Instances:</strong> 669</p> <p><strong>Number of Attributes:</strong> 31</p> <p><strong>Missing Values:</strong> yes</p> <p><strong>Area(s):</strong> Health and technology </p> <p><strong>Sources:</strong> </p> <ul> <li> <p>Electronic Patient Record (EPR) - University Hospital Onofre Lopes of Federal University of Rio Grande do Norte (HUOL/UFRN), Brazil;</p> </li> <li> <p>OSSEUS (Osteoporosis screening based on electromagnetic waves); and,</p> </li> <li> <p>DXA (Dual-energy x-ray absorptiometry). </p> </li> </ul> <p> </p> <p><strong>Description</strong>: The dataset “osseus_dataset.csv” (Table 1) contains elementary data related to risk factors and examinations performed by individuals in Rio Grande do Norte, Brazil, to investigate bone mineral density. Data were collected using the EPR of HUOL/UFRN, DXA, and OSSEUS, a low-cost device based on electromagnetic waves, which measures the attenuation of the signal when crossing the medial phalanx of the middle finger (PINHEIRO et al., 2021, ALBUQUERQUE et al., 2022).</p> <p><strong>Descrição</strong>: O conjunto de dados “osseus_dataset.csv” (Tabela 1) contém dados elementares relacionados a fatores de risco e exames realizados por indivíduos no Estado do Rio Grande do Norte, Brasil, para a investigação da densidade mineral óssea. Os dados foram coletados por meio do EPR do HUOL/UFRN, DXA e OSSEUS, um dispositivo de baixo custo baseado em ondas eletromagnéticas, que mede a atenuação do sinal ao atravessar a falange medial do dedo médio (PINHEIRO et al., 2021, ALBUQUERQUE et al., 2022).</p> <p> </p> <p><strong><strong>Table 1: </strong></strong>Description of Dataset Features.</p> <div> <table> <tbody> <tr> <td> <p><strong>Attributes</strong></p> </td> <td> <p><strong>Description</strong></p> </td> <td> <p><strong>datatype </strong></p> </td> <td> <p><strong>Value</strong></p> </td> </tr> <tr> <td> <p><strong>Electronic Patient Record (EPR)</strong></p> </td> </tr> <tr> <td> <p><strong>id</strong></p> </td> <td> <p>Unique identifier for a person (anonymous).</p> </td> <td> <p>Categorical. </p> </td> <td> <p>Person unique identifier.</p> </td> </tr> <tr> <td> <p><strong>gender</strong></p> </td> <td> <p>It informs the person's gender.</p> </td> <td> <p>Categorical.</p> </td> <td> <ul> <li> <p>female</p> </li> <li> <p>male</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>age</strong></p> </td> <td> <p>It informs the person's age.</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Integer value for age</p> </td> </tr> <tr> <td> <p><strong>weight</strong></p> </td> <td> <p>Informs the value referring to the person's weight—the unit of mass in kilogram (kg).</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Integer value for weight</p> </td> </tr> <tr> <td> <p><strong>height</strong></p> </td> <td> <p>Informs the value relating to the person's height—the unit of measurement for size in centimeters (cm).</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Integer value for height</p> </td> </tr> <tr> <td> <p><strong>ethnicity</strong></p> </td> <td> <p>Informs the person's ethnicity.</p> </td> <td> <p>Categorical.</p> </td> <td> <ul> <li> <p>black</p> </li> <li> <p>brown</p> </li> <li> <p>white</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>target</strong></p> </td> <td> <p>Describe the person's diagnosis or medical report.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>normal</p> </li> <li> <p>osteoporosis</p> </li> <li> <p>low bone mineral density</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>alcohol</strong></p> </td> <td> <p>It informs whether the person consumes alcoholic beverages.</p> </td> <td> <p>Categorical.</p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>smoking</strong></p> </td> <td> <p>Informs whether the person is a smoker.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>activity</strong></p> </td> <td> <p>It informs whether the person practices physical activities.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>milk</strong></p> </td> <td> <p>It informs whether the person consumes dairy drinks.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>calcium</strong></p> </td> <td> <p>It informs whether the person uses calcium.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>vitamin_d</strong></p> </td> <td> <p>It informs whether the person uses Vitamin D.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>fall</strong></p> </td> <td> <p>It informs whether the person has a history of falling.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>parents_osteoporosis</strong></p> </td> <td> <p>It informs whether the person has a family history of osteoporosis.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>parents_curved</strong></p> </td> <td> <p>It informs whether the person has a family history of "parents curved."</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>corticosteroids</strong></p> </td> <td> <p>It informs whether the person uses corticosteroid-type medications for three months or longer.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>arthritis</strong></p> </td> <td> <p>Informs if the person has arthritis.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>diseases</strong></p> </td> <td> <p>Informs if the person has comorbidities.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>menopause</strong></p> </td> <td> <p>Informs if the person has menopause.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>testosterone</strong></p> </td> <td> <p>It informs whether the person uses testosterone.</p> </td> <td> <p>Categorical. </p> </td> <td> <ul> <li> <p>yes</p> </li> <li> <p>no</p> </li> </ul> </td> </tr> <tr> <td> <p><strong>OSSEUS (Osteoporosis screening based on electromagnetic waves)</strong></p> </td> </tr> <tr> <td> <p><strong>medial_length</strong></p> </td> <td> <p>Length of the medial phalanx in mm.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Integer value for length.</p> </td> </tr> <tr> <td> <p><strong>medial_height</strong></p> </td> <td> <p>Height of the medial phalanx in mm.</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Integer value for height.</p> </td> </tr> <tr> <td> <p><strong>medial_width</strong></p> </td> <td> <p>Width of the medial phalanx in mm.</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Integer value for width.</p> </td> </tr> <tr> <td> <p><strong>calibration</strong></p> </td> <td> <p>Osseus signal strength with no obstacle between the antennas.</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Float value for calibration.</p> </td> </tr> <tr> <td> <p><strong>attenuation</strong></p> </td> <td> <p>Osseus signal strength with obstacles between antennas.</p> </td> <td> <p>Numerical.</p> </td> <td> <p>Float value for attenuation.</p> </td> </tr> <tr> <td> <p><strong>DXA (Dual-energy x-ray absorptiometry)</strong></p> </td> </tr> <tr> <td> <p><strong>spine_deviation</strong></p> </td> <td> <p>Reports the spinal standard deviation score that represents the difference between bone density and the expected value.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Float value for deviation.</p> </td> </tr> <tr> <td> <p><strong>femur_deviation</strong></p> </td> <td> <p>Reports the femur standard deviation score that represents the difference between bone density and the expected value.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Float value for deviation.</p> </td> </tr> <tr> <td> <p><strong>body_deviation</strong></p> </td> <td> <p>Reports the full body standard deviation score that represents the difference between bone density and the expected value.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Float value for deviation.</p> </td> </tr> <tr> <td> <p><strong>forearm_deviation</strong></p> </td> <td> <p>Reports the forearm standard deviation score that represents the difference between bone density and the expected value.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Float value for deviation.</p> </td> </tr> <tr> <td> <p><strong>worst_deviation</strong></p> </td> <td> <p>Reports the worst standard deviation score among all deviations obtained from the record.</p> </td> <td> <p>Numerical. </p> </td> <td> <p>Float value for deviation.</p> </td> </tr> </tbody> </table> <p> </p> <p> </p> </div> <p><strong>REFERENCES</strong><br>Albuquerque, G. et al. A method based on non-ionizing microwave radiation for ancillary diagnosis of osteoporosis: a pilot study. BioMedical Eng. OnLine 21, 70, https://doi.org/10.1186/s12938-022-01038-y (2022).</p> <p>Pinheiro, B. d. M. et al. The influence of antenna gain and beamwidth used in osseus in the screening process for osteoporosis. Sci. Reports 11, 19148, https://doi.org/10.1038/s41598-021-98204-4 (2021).</p> <div> <p> </p> </div>
DeepBacs – Artificial labeling of E. coli membranes dataset and fnet/CARE models
<p>Training and test images of <em>E. coli </em>cells for artificial labeling of membranes in brightfield images using fnet or CARE, as well as trained models for prediction of super-resolution membranes.</p> <p>Additional information can be found on this <a href="https://github.com/HenriquesLab/DeepBacs/wiki">github wiki</a>.</p> <p>Example image shows an <em>E. coli</em> bright field image and PAINT membrane image predicted by the neural network (scale bar is 1 µm).</p> <p> </p> <p><strong>Training and testing dataset</strong></p> <p><strong>Data type</strong>: Paired bright field and super-resolution images</p> <p><strong>Microscopy data type</strong>: Bright field and fluorescence microscopy (widefield and point accumulation for imaging in nanoscale topography (PAINT) images)</p> <p><strong>Microscope</strong>: Nikon Eclipse Ti-E equipped with an Apo TIRF 1.49NA 100x oil immersion objective</p> <p><strong>Cell type</strong>: <em>E. coli </em>K12 strain derivatives</p> <p><strong>File format</strong>: .tif (8-bit)</p> <p><strong>Image size</strong>: 512x512 px<sup>2</sup> with different pixel sizes:</p> <p>1x tube lens: 158 nm (raw) and 19.75 nm (8x upscaled for PAINT images)</p> <p>1.5x tube lens: 106 nm (raw) (widefield fluorescence only)</p> <p> </p> <p><strong>fnet model (PAINT membrane images)</strong></p> <p>The fnet 2D model was generated using the ZeroCostDL4Mic platform (Chamier et al., 2021). It was trained for 200,000 steps on 33 paired images (image dimensions: (512 x 512 px²), patch size: (128 x 128 px²)) with a batch size of 4, a learning rate of 0.0004, 10% validation split and 4x data augmentation (flipping and rotation).</p> <p>Model weights can be used with the ZeroCostDL4Mic fnet 2D notebook.</p> <p> </p> <p><strong>CARE model (PAINT membrane images):</strong></p> <p>The CARE 2D model was generated using the ZeroCostDL4Mic platform (Chamier et al., 2021). It was trained for 300 epochs (100 steps/epoch) on 33 paired images (image dimensions: 512 x 512 px², patch size: 256 x 256 px²) with a batch size of 4, a learning rate of 0.0004, 90/10% train/validation split and 4x data augmentation (flipping and rotation).</p> <p>Model weights can be used with the ZeroCostDL4Mic CARE 2D notebook or the CSBDeep Fiji plugin.</p> <p><br> <strong>Author(s)</strong>: Christoph Spahn<sup>1,2</sup>, Mike Heilemann<sup>1,3</sup></p> <p><strong>Contact email</strong>: christoph.spahn@mpi-marburg.mpg.de</p> <p> </p> <p><strong>Affiliation(s)</strong>: </p> <p>1) Institute of Physical and Theoretical Chemistry, Max-von-Laue Str. 7, Goethe-University Frankfurt, 60439 Frankfurt, Germany</p> <p>2) ORCID: 0000-0001-9886-2263 </p> <p>3) ORCID: 0000-0002-9821-3578</p>
ZeroCostDL4Mic / DeepBacs - Multi-label U-Net training dataset (Bacillus subtilis) and pretrained model
<p>Training and test images of live <em>B. subtilis </em>cells expressing FtsZ-GFP for the task of segmentation.</p> <p>Additional information can be found on this <a href="https://github.com/HenriquesLab/DeepBacs/wiki">github wiki</a>.</p> <p>The example shows the fluorescence widefield image of live <em>B. subtilis </em>cells expressing FtsZ-GFP, the manually annotated instance segmentation mask and the corresponding 2-label semantic segmentation mask used for model training.</p> <p> </p> <p><strong>Training and test dataset</strong></p> <p><strong>Data type</strong>: Paired fluorescence and segmented mask images</p> <p><strong>Microscopy data type</strong>: 2D widefield images (fluorescence) </p> <p><strong>Microscope</strong>: Custom-built 100x inverted microscope bearing a 100x TIRF objective (Nikon CFI Apochromat TIRF 100XC Oil); images were captured on a Prime BSI sCMOS camera (Teledyne Photometrics)</p> <p><strong>Cell type</strong>: <em>B. subtilis</em> strain SH130 grown under agarose pads</p> <p><strong>File format</strong>: .tiff (8-bit)</p> <p><strong>Image size</strong>: 1024 x 1024 px² (Pixel size: 65 nm)</p> <p><strong>Image preprocessing</strong>: Images were denoised using PureDenoise and resulting 32-bit images were converted into 8-bit images after normalizing to 1% and 99.98% percentiles. Images were manually annotated using the Labkit Fiji plugin and mask images with labeled cytosol and cell boundaries were created using a custom Fiji macro (see our <a href="https://github.com/HenriquesLab/DeepBacs/tree/main/ImageJ-macros">github repository</a>).</p> <p> </p> <p><strong>Multi-label U-Net model</strong>:</p> <p>The U-Net (2D) multilabel model was generated using the ZeroCostDL4Mic platform (Chamier & Laine et al., 2021). It was trained from scratch for 200 epochs on 733 paired image patches (image dimensions: (1024 x 1024 px²), patch size: (256 x 256 px²)) with a batch size of 8 and a categorical_crossentrop loss function, using the U-Net (2D) multilabel ZeroCostDL4Mic notebook (v 1) (Chamier & Laine et al., 2021). Key python packages used include tensorflow (v 0.1.12), Keras (v 2.3.1), numpy (v 1.19.5), cuda (v 11.1.105). The training was accelerated using a Tesla P100GPU.</p> <p> </p> <p><strong>Author(s)</strong>: Mia Conduit<sup>1,2</sup>, Séamus Holden<sup>1,3</sup></p> <p><strong>Contact email</strong>: <a href="mailto:Seamus.Holden@newcastle.ac.uk">Seamus.Holden@newcastle.ac.uk</a></p> <p> </p> <p><strong>Affiliation</strong>:</p> <p>1) Centre for Bacterial Cell Biology, Biosciences Institute, Newcastle University, NE2 4AX UK</p> <p>2) ORCID: 0000-0002-7169-907X</p> <p> </p> <p> <strong>Associated publications</strong>: Whitley <em>et al</em>., 2021, Nature Communications, https://doi.org/10.15252/embj.201696235</p>
The Large Labelled Logo Dataset (L3D)
<p>Public release of the dataset from the paper: "The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing Dataset"</p> <p>More information: <a href="https://github.com/lhf-labs/tm-dataset">https://github.com/lhf-labs/tm-dataset</a></p> <p>Citing:</p> <pre><code>@misc{gutierrezfandino2021L3D, title={The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing Dataset}, author={Asier Gutiérrez-Fandiño and David Pérez-Fernández and Jordi Armengol-Estapé}, year={2021}, eprint={2112.05404}, archivePrefix={arXiv}, primaryClass={cs.CV} }</code></pre> <p> </p>
VC-SLAM Versatile Corpus for Semantic Labeling And Modeling
<p>Benchmark Corpus for semantic labeling and modeling.</p> <p>This corpus contains 101 data sets from different open data portals.<br> Each data set consists of the following data:</p> <ul> <li>Raw csv data [rawdata_csv]</li> <li>Large json data sample [json_sample_large]</li> <li>Small json data sample [json_sample_small]</li> <li>Raw data in csv format [rawdata_csv]</li> <li>Raw data samples in csv format [rawdata_csv_samples]</li> <li>Mappings to translate between csv and json files [csv_json_mappings]</li> <li>Textual description / Metadata [descriptions]</li> <li>Semantic model as rdf/ttl [semantic_models]</li> <li>Mappings describing mapping between raw data attributes and concepts from the ontology [mappings]</li> <li>List of attributes that have been ignored during modeling [ignored_attributes]</li> </ul> <p>Additionally the corpus contains a target ontology as rdf/ttl [ontology].</p> <p>The individual data sets are licensed by the licenses specified in the attached Excel sheet (DataSetOverview.xlsx)</p> <p> </p> <p>These data are provided "as is", without any warranties of any kind. The data are provided under the Creative Commons Attribution 4.0 International license.</p>
Detection of neurofilament light chain with label-free electrolyte-gated organic field-effect transistors
<p>The uploaded data include</p> <p>i) transfer curves registered at every NF-L concentration;</p> <p>ii) transfer curves for control experiments;</p> <p>iii) raw AFM data acquired after electrode incubation in 0 M, 1 pM, 100 pM and 10 nM [NF-L].</p> <p>Electrical measurements were acquired in 50 mM PBS, pH 7.4 under static conditions.</p> <p>Anti-NF-L antibodies were immobilized on the gate electrode through cys-Protein G. The gate surface has been subsequently passivated through 11-mercaptoundecyl-triethylene glycol SAM.</p>
Surveyance of apparent unfolding curves via thiol labelling
<p>Dataset contains raw and preprocessed data for fluorescence and proteomic studies respectively. In each case, protein foldedness was probed using thiol reactivity. The raw mass spectrometry proteomics data have also been deposited to the ProteomeXchange Consortium via the PRIDE partner repository, with the dataset identifiers PXD022587, PXD022640 and PXD030567.</p>
Labeled points for four land cover classes referring to the year 2019
<p>This dataset provides hand-labeled points for four different land cover classes in coastal areas (sand, seawater, grass, trees).</p> <p>It was created based on photointerpretation of high-resolution imagery in Google Earth Pro and QGIS, referring to the year 2019.</p> <p>This dataset was used for the random forest classification of satellite imagery in the following manuscript: </p> <p>"<em>Satellite image processing for the coarse-scale investigation of sandy coastal areas</em>".</p> <p>If you use any part of this dataset, please cite as follows:</p>
A Twitter dataset (with labels) for Life-Event detection
<p>The file contains an anonymized version of the dataset collected in the framework of the “Tsundoku” project financed by the Autonomous Province of Trento according to the province law 13 of December 1999, n. 6 (and subsequent modifications), art. 5. - “Aids for promoting research and development”, financing approved with APIAE manager’s provision n. 691. The purpose of this project is training a Deep Learning (DL) model capable of detecting the occurrence of a so-called Life Event - a wedding and/or the birth of a child - in a person’s life on the basis of the contents she shared on social media (Twitter, in this case). </p> <p>More precisely, the dataset consists of the most recent tweets - up to approximately 3200 for each account - of 8 Italian and 27 English-speaking users (all of them randomly picked), totalling 74722 tweets, 20302 written in Italian and 54420 in English.</p> <p>For each user (labelled as ‘user_<em>x</em>’ with <em>x</em> an integer number between 1 and 35), the file includes the language her tweets are written in as well as the list of said tweets. For every one of the latter, the information made available includes the text of the tweet (appropriately modified as explained below), its length, the number of hashtags and of user mentions it featured, the number of retweets and of likes it received, two Boolean flags (“True” or “False”) assessing whether it was a quote or a reply and a label (‘birth’, ‘wedding’ and ‘not Life-Event-related’, depending on whether the tweet refers to a birth/wedding experienced by the user or not). With respect to the label, it is worth stressing that a tweet was labelled as ‘birth’/‘wedding’ only if the event “actively” involved the user (thus, a tweet reading “Today I get married” is labelled as ‘wedding’, while the label ‘not Life-Event-related’ is associated with ‘Today my sister gets married’) and if the tweet is <strong>by itself</strong> unambiguous (in other words, a tweet reading ‘My wife is pregnant’ is labelled as ‘birth’, while ‘Josephine is pregnant’ does not, since the tweet alone does not allow to determine who Josephine exactly is - this could perhaps be inferred from other tweets but this kind of contextualization is very hard to be carried out and was out of the scope of this project.).</p> <p>In order to comply with GDPR, each one of the texts included in the file was obtained from the original text after taking the following anonymization steps:</p> <p> </p> <ul> <li> <p>every web link got replaced by the ‘WEBLINK’ string;</p> </li> <li> <p>every mention to another Twitter user (for instance, “@joedoe”) got replaced by the “OTHERUSER” string;</p> </li> <li> <p>every hashtag got replaced by the “HASHTAG” string;</p> </li> <li> <p>every name and surname detected by the spaCy library (see <a href="https://spacy.io/">https://spacy.io</a> for more info) got replaced by the “NAME/SURNAME” string;</p> </li> <li> <p>10% of the available words got randomly picked and erased. </p> </li> </ul> <p> </p> <p> </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.