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.
7,185
datasets available to search
ShareScore release 0.7.1
Dataset results
7,185 results for “Learning”
LEARN-COVID: Dataset and documentation
<p>The LEARN-COVID pilot study collected data on infants and their parents during the COVID-19 pandemic. Assessments took place between April and July 2021. Predominantly Swiss parents answered a baseline questionnaire on their behaviour related to the pandemic, social support, infant nutrition, and infant regulation. Subsequently, parents answered a 10-day evening diary on daily nutrition, infant regulation, parental mood, and parental soothing behaviour.</p>
Phase Object Reconstruction for 4D-STEM using Deep Learning, (4D-STEM Example Data)
<p><strong>Overview </strong></p> <p>This repository contains 2 example 4D-STEM datasets format from the paper <a href="https://arxiv.org/abs/2202.12611">"Phase Object Reconstruction for 4D-STEM using Deep Learning"</a>. The data was written to hdf5 for compatibility with the python programming language. When reading from these files consider possibly different storage conventions (Row major vs. column major format). Data may need to be transposed accordingly.</p> <p> </p> <p><strong>Parameters</strong></p> <p>The twisted bilayer graphene dataset is simulated. The smaller file is an experimental SrTiO<sub>3</sub> dataset.</p> <table> <thead> <tr> <th scope="row"> </th> <th scope="col">Graphene</th> <th scope="col">STO</th> </tr> </thead> <tbody> <tr> <th scope="row">E0</th> <td>200kV</td> <td>300kV</td> </tr> <tr> <th scope="row">Apeture</th> <td>25 mrad</td> <td>20 mrad</td> </tr> <tr> <th scope="row">Detector Size</th> <td>2.5 Å<sup>-1</sup></td> <td>1.6671 Å<sup>-1</sup></td> </tr> <tr> <th scope="row">Dimensions</th> <td>101x101x128x128</td> <td>60x60x64x64</td> </tr> <tr> <th scope="row">Step Size</th> <td>0.2</td> <td>0.1818</td> </tr> </tbody> </table> <p><br> </p>
Raw data of individuals with Down syndromre, individuals with Williams syndrome, healthy children and adults in a visual learning task, a conditional learning task and a transitive inference task.
<p>Raw data of 17 individuals with Down syndrome (8 girls/women; average age: 17.8 years; range: 7.2-30.8 years at the beginning of the study) in a visual learning task, a 3-item conditional learning task, and a 5-item conditional learning and transitive inference task.</p> <p>Raw data of 27 individuals with Williams syndrome (16 girls/women; average age: 23.7; range: 9.4-43.8 at the beginning of the study) in a visual learning task, a 3-item conditional learning task, and a 5-item conditional learning and transitive inference task.</p> <p>Raw data of 71<strong> </strong>healthy children (31 girls; average age: 6.42 years; range: 2.95-11.64 years at the beginning of the study) in a visual learning task, a 3-item conditional learning task, and a 5-item conditional learning and transitive inference task.</p> <p>Raw data of 22 healthy adults (11 femaleswomen; average age: 26.05 years; range: 20.32-29.76 years at the beginning of the study) in a visual learning task, a 3-item conditional learning task, and a 5-item conditional learning and transitive inference task.</p>
Supplemental Figures for "On the comparative utility of entropic learning versus deep learning for long-range ENSO prediction"
<p>Supplemental figures for the paper "On the comparative utility of entropic learning versus deep learning for long-range ENSO prediction".</p>
Elevating Cybersecurity for Smart Grid Systems—A Container-Based Approach Enhanced by Machine Learning
<p>README<br>Title<br>Elevating Cybersecurity for Smart Grid Systems—A Container-Based Approach Enhanced by Machine Learning</p> <p>Authors<br>Mays Abukeshek, School of Computer Science, Faculty of Technology, University of Sunderland, University of Huddersfield, UK<br>Email: mays.abukeshek@sunderland.ac.uk, Mays.abukeshek@hud.ac.uk<br>Basel Barakat, School of Computer Science, Faculty of Technology, University of Sunderland, UK<br>Email: basel.barakat@sunderland.ac.uk<br>Bamidele Ajayi, School of Computer Science, Faculty of Technology, University of Sunderland, UK<br>Email: bamidele.ajayi@research.sunderland.ac.uk<br>Abstract<br>This dataset supports the paper "Elevating Cybersecurity for Smart Grid Systems—A Container-Based Approach Enhanced by Machine Learning," which presents a comprehensive implementation of a cybersecurity solution for smart grid network containers. The methodology utilizes:</p> <p>Qualys API-based vulnerability scanning and reporting system for vulnerability identification<br>Docker deployment for security and isolation<br>Advanced load balancing techniques for resource optimization<br>Machine learning-powered anomaly detection for threat identification and vulnerability prioritization.<br>The dataset contains details of several simulated attacks enabling effective training and evaluation of a robust machine-learning model.</p> <p>Data Description<br>The dataset includes logs from conducted attacks on containerized nodes, generated to reflect real-world scenarios. The simulated attacks include:</p> <p>Denial of Service (DoS)<br>Remote-to-Local (R2L)<br>User-to-Root (U2R)<br>Probes<br>Contents<br>Csv_file.csv: This file contains the dataset used for training and evaluating the machine learning models. The columns in the dataset represent various features and results of the simulated attacks.<br>Data Columns and Rows<br>Timestamp:</p> <p>Description: The exact date and time when the data was recorded.<br>time: 2023-06-01 12:00:00</p> <p>Attack_Type:</p> <p>Description: The type of cyber-attack conducted.<br>Possible Values: DoS, R2L, U2R, Probe<br>Example: DoS<br>Notes: Categorizes the type of attack, crucial for training classification models.<br>CPU_Utilization (%):</p> <p>Description: The percentage of CPU resources used during the attack.<br>Example: 52.3<br>Notes: Indicates the load on the CPU during the attack, useful for assessing the impact of attacks on system performance.<br>Memory_Utilization (%):</p> <p>Description: The percentage of memory resources used during the attack.<br>Example: 63.4<br>Notes: Shows memory usage which can be a critical factor in understanding system performance under attack conditions.<br>Network_Bandwidth (Mbps):</p> <p>Description: The bandwidth of the network in Megabits per second.<br>Example: 100<br>Notes: Reflects the network load and is essential for analyzing the impact on network performance.<br>Vulnerabilities_Detected:</p> <p>Description: The number of vulnerabilities detected during the attack.<br>Example: 289<br>Notes: Indicates the effectiveness of the vulnerability scanning process and the system's exposure to threats.<br>Mean_Response_Time (ms):</p> <p>Description: The average response time in milliseconds during the attack.<br>Example: 87<br>Notes: Important for evaluating the responsiveness of the system under attack conditions.<br>Throughput (requests/second):</p> <p>Description: The number of requests the system can handle per second during the attack.<br>Example: 1068<br>Notes: Measures the capacity and efficiency of the system under load.<br>Example Row<br>Timestamp Attack_Type CPU_Utilization (%) Memory_Utilization (%) Network_Bandwidth (Mbps) Vulnerabilities_Detected Mean_Response_Time (ms) Throughput (requests/second)<br>2023-06-01 12:00:00 DoS 52.3 63.4 100 289 87 1068<br>Usage<br>This dataset can be used to:</p> <p>Train and evaluate machine learning models for cybersecurity applications in smart grid systems.<br>Analyze the performance of different machine learning models in detecting and prioritizing vulnerabilities.<br>Understand the impact of various types of cyber-attacks on containerized environments.<br>Methodology<br>The dataset was created using a combination of Qualys API-based vulnerability scanning and Docker containerization. Multiple container clusters were subjected to various simulated attacks, and the performance of machine learning models was evaluated based on accuracy, precision, recall, and F1-scores.</p> <p>Acknowledgments<br>This research was supported by the University of Sunderland and the University of Huddersfield.</p> <p>References<br>Please refer to the full paper for detailed methodology, implementation, and analysis:<br>IEEE</p>
Deep learning-based earthquake catalog of the 2022 MW 6.9 Chihshang, Taiwan, earthquake sequence
<p>On 18 September 2022, the MW 6.9 Chihshang earthquake struck the southern Longitudinal Valley, Taiwan. We use SeisBlue, a deep-learning platform/package, to extract the two-month earthquake sequence from September to October 2022, including the MW 6.5 Guanshan foreshock, the MW 6.9 mainshock, over 14,000 aftershocks, and 866 focal mechanisms from two sets of broadband networks. For more details, please refer to our research article published at TAO (Sun et al., 2024; https://doi.org/10.1007/s44195-024-00063-9). The refined SeisBlue earthquake, FMS, and 20-year M3+ relocated CWA earthquake catalogs obtained in this study are listed here.</p> <ol> <li>The refined, deep-learning-based earthquake catalog of the 2022 Mw 6.9 Chihshang, Taiwan, earthquake sequence contains 5,151 seismic events with event time, location and error information, local and moment magnitudes, and hypoDD location. </li> <li>The FMS (focal mechanism solution) catalog is obtained by the P-wave polarities of 14 broadband stations and the FPFIT program (Reasenberg & Oppenheimer, 1985). 865 out of 1629 FMSs with at least six readings of P-wave polarity, F-fator <span>≤ </span>0.1 (F <span>< </span>0.5 for a good fit), and errors of strike, dip, and rake are all <span>< </span>20<span>°</span>, respectively, are listed in the attached FMS catalog.</li> <li>The 2001-2020 3D-hypoDD-relocated M3+ CWA earthquake catalog: We applied the HypoDD program (Waldhauser & Ellsworth, 2000) to the CWA (Central Weather Administration (CWA, Taiwan), 2012) catalog with P- and S-wave arrivals and obtained 5862 M3+ events between 2001 and 2020 for eastern Taiwan. The 3D velocity models used for this catalog are the local models from Kuo-Chen et al. (2012).</li> </ol> <p> </p>
Using machine learning to integrate genetic and environmental data to model genotype-by-environment interactions
<p>Files generated from the study described in <a href="https://doi.org/10.1101/2024.02.08.579534">Fernandes et. al (2024)</a> .</p> <p>The file "cvs_h2s.csv" comprises the coefficient of variation and the Cullis heritability for each environment.</p> <p>The file "all_predictions.csv" contains the predictions from all the models evaluated, in different cross-validation (CV) scenarios.</p> <p>The file "coincidence_index.csv" has the Coincidence Index (CI) for each CV and models evaluated in our study.</p> <p>Our study used the multi-environment maize yield trials data from the Genomes to Fields 2022 initiative (<a href="https://doi.org/10.1186/s13104-023-06421-z">Lima et. al 2024</a>).</p>
Viral Pneumonia Classification Using Machine and Transfer Learning Techniques
<p>Pneumonia is considered a deadly and harmful disease throughout the world. Pneumonia can be lethal if not treated promptly with antibiotics. As a result, early detection of pneumonia increases the likelihood of recovery and lowers mortality. X-rays are one of the most important diagnostic tools for pneumonia. Because of its lower diagnostic costs, the chest X-ray is routinely used to diagnose various lung illnesses. Indeed, diagnosis can be subjective for various reasons, including disease presentation, which might be confusing in chest X-ray images or misdiagnosed as another condition. As a result, the employment of chest X-rays for the diagnoses of pneumonia disease is considered a way forward to fight the challenges being faced with during the examination process and expert readings of results. The dataset comprises 1,067 Pneumonia Chest X-ray images that were curated from the Hopskin Diagnostic Center Nigeria for Research Purposes. This was used to classify Pneumonia disease for pneumonia class encoding. The result yield Pneumonia Disease with High Accuracy, precision and Recall. </p>
A large data-set of CASP protein refinement simulations for machine-learning
<p>The uploaded trajectory data originates from our own laboratory's refinement method in CASP11 and CASP12 for which the reference crystal structure is available in the PDB. In total the trajectory data consists of 904 trajectories with 3419 ns cumulative simulation time and 1,709,704 snapshots with a delta t =2 ps from 42 different protein systems.</p> <p><strong>File Overview</strong></p> <ul> <li><strong>trajectory_data_pdbs.tar.gz :</strong> contains the PDB files of the different trajectories as well as the starting model and reference crystal structure for each target</li> <li><strong>casp_normalized_all_data_final.csv.gz : </strong>contains the trajectory features calculated for each snapshot from the trajectory PDBs</li> <li><strong>cv_folds.csv : </strong>contains the 7 fold cross-validation assignment used to assess the performance of the model<br> </li> </ul> <p> </p> <p> </p> <p> </p>
Machine learning for Gravity Spy: Glitch classification and dataset
<p>We present the first version of the training set used in the Gravity Spy citizen science project. This training set, discussed in detail <a href="https://www.sciencedirect.com/science/article/pii/S0020025518301634">here</a>, was utilized to train the convolutional neural network employed in the Gravity Spy project. We anticipate moving forward to release more labelled Gravity Spy data sets, including a refined version of this training set which can be found here <a href="https://doi.org/10.5281/zenodo.1476551">10.5281/zenodo.1476551</a>, and data sets containing the annotations provided by our citizen science volunteers.</p> <p><strong>Data Set Information</strong></p> <p>There are three files provided in this data set</p> <ul> <li><strong>trainingset_v1d0_metadata.csv</strong> <ul> <li>This file has three columns, <em>gravityspy_id, label, </em>and <em>sample_type.</em><em> gravityspy_id </em>is the unique 10 character hash given to every Gravity Spy sample. <em>label</em> is the string label of the sample. <em>sample_type </em>indicates whether this sample was used in the paper for testing training or validating the models. This is provided for those who would like to do direct comparisons to the network described in the paper.</li> </ul> </li> <li><strong>trainingsetv1d0.h5</strong> <ul> <li>This file contains the exact arrays used in the paper for every Gravity Spy sample. Each Gravity Spy sample is defined by four different images with varying temporal duration, <em>0.5, 1.0, 2.0, and 4.0</em> second, respectively. This also determines the naming conventions of the PNGs: <em>interferometer_gravityspyid_spectrogram_duration.png (e.g. H1_Fv3p6eROvA_spectrogram_0.5.png, H1_Fv3p6eROvA_spectrogram_1.0.png, H1_Fv3p6eROvA_spectrogram_2.0.png, H1_Fv3p6eROvA_spectrogram_4.0.png</em>).</li> <li>This file contains all the information needed for each sample in the Gravity Spy dataset (i.e. the label, the sample type of the sample, the unique id of the sample, and the image data for that sample. <ul> <li>/1080Lines/validation/xUEyaWr34c Group<br> /1080Lines/validation/xUEyaWr34c/0.5.png Dataset {1, 140, 170}<br> /1080Lines/validation/xUEyaWr34c/1.0.png Dataset {1, 140, 170}<br> /1080Lines/validation/xUEyaWr34c/2.0.png Dataset {1, 140, 170}<br> /1080Lines/validation/xUEyaWr34c/4.0.png Dataset {1, 140, 170}</li> </ul> </li> </ul> </li> <li><strong>trainingsetv1d0.tar.gz</strong> <ul> <li>Contains the raw PNGs of the Gravity Spy training set.</li> <li>The structure of the folder is <em>/"label"/"sample_type"/"pngs"</em></li> </ul> </li> </ul> <p><strong>Data Set Parsing Information</strong></p> <p>To read and crop out the plot axis and labels of the provided PNGs, the following small python code using scikit-image should work.</p> <p>from skimage import io</p> <p>image_data = io.imread("filename_of_image")</p> <p>x=[66, 532]; y=[105, 671]</p> <p>image_data = image_data[x[0]:x[1], y[0]:y[1], :3]</p>
Transfer of sensorimotor learning reveals phoneme representations in preliterate children - Dataset
<p>This file provides formants values in each speaker and for each trial of the experiment described in the article : Transfer of sensorimotor learning reveals phoneme representations in preliterate children.</p> <p> </p>
ALICE machine learning image set
<p>Pinned insect images and corresponding label outlines in JSON format. This image set is used for machine learning of label identification and segmentation for the ALICE project. https://doi.org/10.31219/osf.io/s2p73</p> <p> </p>
PsPM-DoxMem2: Pupil, SCR, ECG, EMG and respiration measurement in a classical pavlovian discriminant delay fear conditioning task, reminder under doxycycline/placebo, retention and re-learning
<p>This dataset includes eyetracker, skin conductance response (SCR), electrocardiogram (ECG), respiration and electromyogram (EMG, only relevant for retention phase) measurements. Also included are CS and US information, keypress responses and keypress response times for 79 healthy participants (40 males and 39 females aged 24.8+/-4.9 years). Participants underwent a classical (Pavlovian) discriminant delay fear conditioning task with 1 CS- and 2 CS+ (50% reinforcement), were reminded of one CS+ one week later under either doxycycline or placebo, and were tested in a retention/extinction and re-learning task another week later. CS were isoluminant coloured triangles. US consisted of 0.5 s square electric pulses with 0.2 ms duration and 500 Hz frequency. SOA between the CS onset and US was 3.5 s. CS and US co-terminated. Before the fear conditioning task, participants completed several questionnaires. During the retention/extinction phase, an auditory startle probe (ST) and no US was delivered 3.5 s after CS onset via headphones (102 dB, 40 ms duration with 2 ms on- and offset ramp). In an immediately following re-learning phase, the ST was omitted and the CS reinforced with the same schedule as during acquisition. The ITI was randomly determined on each trial to be 7, 9, or 11 s.</p> <p> </p>
Ecology and conservation of socially learned foraging tactics in odontocetes
<h3>Overview</h3> <p>This package contains the data and R code to replicate the analyses and figures of the review article, "Ecology and conservation of socially learned foraging tactics in odontocetes", submitted to the special issue of Philosophical Transactions B, "Animal Culture: conservation in a changing world". </p> <p>Metadata for CSV files used for analyses are provided below, and detailed instructions on running code are available at: https://github.com/JoaoVallePereira/Toothed_Whales_Forag_Tactics. For full description of variables, see supplemental material associated with publication. </p> <div> <h3>Main data table - dataTable_Forag_Tactics.csv</h3> </div> <table> <tbody> <tr> <th>Variable</th> <th>Class</th> <th>Description</th> </tr> </tbody> <tbody> <tr> <td>common_name</td> <td>Character</td> <td>The common name of the species exhibiting the foraging tactic</td> </tr> <tr> <td>latin_name</td> <td>Character</td> <td>The Latin name of the species exhibiting the foraging tactic</td> </tr> <tr> <td>country</td> <td>Character</td> <td>The country that has jurisdiction over the region where the foraging tactic occurs</td> </tr> <tr> <td>region</td> <td>Character</td> <td>The region where the foraging tactic occurs</td> </tr> <tr> <td>animal_identity_data</td> <td>Character</td> <td>Whether identity information for the individual(s) exhibiting the foraging tactic is available</td> </tr> <tr> <td>number_of_animals</td> <td>Character</td> <td>The number of different individuals exhibiting the foraging tactic</td> </tr> <tr> <td>foraging_category</td> <td>Character</td> <td>The broad foraging category that the specific foraging tactic most closely aligns with</td> </tr> <tr> <td>foraging_tactic</td> <td>Character</td> <td>The specific foraging tactic</td> </tr> <tr> <td>tactic_driver</td> <td>Character</td> <td>The key factor influencing or determining the observed foraging tactic</td> </tr> <tr> <td>human_induced</td> <td>Character</td> <td>Whether the foraging tactic is human-induced or not</td> </tr> <tr> <td>prey_category</td> <td>Character</td> <td>The type of prey being targeted during the foraging tactic</td> </tr> <tr> <td>habitat</td> <td>Character</td> <td>The type of habitat in which the foraging tactic is exhibited</td> </tr> <tr> <td>prey_category</td> <td>Character</td> <td>The type of prey being targeted during the foraging tactic</td> </tr> <tr> <td>putative_specialised_foraging_tactic</td> <td>Character</td> <td>Foraging tactics having both individual identity information and evidence of being shared among conspecifics</td> </tr> <tr> <td>putative_cultural_foraging_tactic</td> <td>Character</td> <td>Foraging tactics with positive evidence of social learning</td> </tr> <tr> <td>transmission_direction</td> <td>Character</td> <td>How the foraging tactic is transmitted, given positive evidence of social learning</td> </tr> <tr> <td>nature_of_social_learning_evidence</td> <td>Character</td> <td>The type of evidence for social learning</td> </tr> <tr> <td>culture_acknowledgement</td> <td>Character</td> <td>The type of evidence for social learning</td> </tr> <tr> <td>evidence_for_discreteness_significance</td> <td>Character</td> <td>Evidence for differences in diet or foraging techniques that are stable</td> </tr> <tr> <td>threat_acknowledgement</td> <td>Character</td> <td>Whether the reviewed studies acknowledge anthropogenic threats</td> </tr> <tr> <td>threat_category</td> <td>Character</td> <td>For studies that acknowledge anthropogenic threats and impacts, the type of IUCN-CMP first-level threat classification</td> </tr> <tr> <td>threat_subcategory</td> <td>Character</td> <td>For studies that acknowledge anthropogenic threats and impacts, the type of IUCN-CMP second-level threat classification</td> </tr> <tr> <td>threat_direction</td> <td>Character</td> <td>Whether the acknowledged threats were considered a threat to or a consequence of the foraging tactic</td> </tr> <tr> <td>conservation_actions_acknowledgement</td> <td>Character</td> <td>Whether the reviewed studies acknowledge existing or proposed conservation actions related to the foraging tactic</td> </tr> <tr> <td>existing_conservation_actions_category</td> <td>Character</td> <td>Existing conservation actions related to the foraging tactic, the type of IUCN-CMP first-level action classification</td> </tr> <tr> <td>existing_conservation_actions_subcategory</td> <td>Character</td> <td>Existing conservation actions related to the foraging tactic, the type of IUCN-CMP second-level action classification</td> </tr> <tr> <td>proposed_conservation_actions_category</td> <td>Character</td> <td>Proposed conservation actions related to the foraging tactic, the type of IUCN-CMP first-level action classification</td> </tr> <tr> <td>proposed_conservation_actions_subcategory</td> <td>Character</td> <td>Proposed conservation actions related to the foraging tactic, the type of IUCN-CMP second-level action classification</td> </tr> <tr> <td>references</td> <td>Character</td> <td>Reviewed primary and secondary literature used to fill out metrics for the foraging tactic</td> </tr> </tbody> </table> <div> <h3> </h3> <h3>Maps data table - dataTable_Forag_Tactics_map.csv</h3> </div> <table> <tbody> <tr> <th>Variable</th> <th>Class</th> <th>Description</th> </tr> </tbody> <tbody> <tr> <td>common_name</td> <td>Character</td> <td>The common name of the species exhibiting the foraging tactic</td> </tr> <tr> <td>latin_name</td> <td>Character</td> <td>The Latin name of the species exhibiting the foraging tactic</td> </tr> <tr> <td>orca_ecotype</td> <td>Character</td> <td>The orca ecotypes exhibiting the foraging tactic</td> </tr> <tr> <td>country</td> <td>Character</td> <td>The country that has jurisdiction over the region where the foraging tactic occurs</td> </tr> <tr> <td>region</td> <td>Character</td> <td>The region where the foraging tactic occurs</td> </tr> <tr> <td>latitude</td> <td>Numeric</td> <td>The latitude where the foraging tactic occurs</td> </tr> <tr> <td>longitude</td> <td>Numeric</td> <td>The longitude where the foraging tactic occurs</td> </tr> <tr> <td>putative_specialised_foraging_tactic</td> <td>Character</td> <td>Foraging tactics having both individual identity information and evidence of being shared among conspecifics</td> </tr> <tr> <td>foraging_category</td> <td>Character</td> <td>The broad foraging category that the specific foraging tactic most closely aligns with</td> </tr> <tr> <td>tactic_cat_fact</td> <td>Factor (10 levels)</td> <td>The broad foraging category that the specific foraging tactic most closely aligns with</td> </tr> <tr> <td>evidence_for_discreteness_significance</td> <td>Character</td> <td>Evidence for differences in diet or foraging techniques that are stable</td> </tr> </tbody> </table>
Predictability Limit of the 2021 Pacific Northwest Heatwave from Deep-Learning Sensitivity Analysis
<p>The attached two datasets are the optimized inputs used to analyze predictability limits in the paper Predictability Limit of the 2021 Pacific Northwest Heatwave from Deep-Learning Sensitivity Analysis. Specifically, the datasets correspond to the inputs used to produce the blue (global) and green (regional) loss curves in Figure S2. They are NetCDF files of dimensions batch (1), time (2), latitude (181), longitude (360), pressure levels (13), and may be run as Graphcast model inputs to initiate a forecast at 00 UTC 20 June 2021. Both datasets have been systematically perturbed to reduce the Graphcast model's loss function, which minimizes forecast eror as described in the manuscript. The global input seeks to reduce the loss over the entire globe, while the regional input seeks only to minimize error within the Pacific Northwest (42N to 60N and 130W to 110W). The optimized inputs result in a reduction of the loss by approximately 85% (global) and 93% (regional) when compared to a control Graphcast forecast without perturbations.</p>
Auditory stimuli suppress contextual fear responses in safety learning independent of a possible safety meaning
<p>This repository stores the raw data that gave rise to the study by Mombelli et al. (2024) (Title: Auditory stimuli suppress contextual fear responses in safety learning independent of a possible safety meaning; DOI: 10.3389/fnbeh.2024.1415047, Journal: Frontiers in Behavioral Neuroscience). Below we supply information on the provided metadata files which, in turn, refer to individual raw data files.</p> <p><strong>General structure of the repository:</strong></p> <p>· the raw data is organized in 5 subsets defined by the figures or supplementary figures they contribute to. Each subset is documented by its own metadata file. Raw data files were compressed into ZIP archives, one per subset;</p> <p>· the metadata files listing names of the individual data files are provided in “.csv” format, one per data subset. Field separator: comma;</p> <p>· the dataset is accessible at the following doi: 10.5281/zenodo.13524007</p> <p> </p> <p><strong>Description of the non-textual data formats:</strong></p> <p>· video recordings of animal behavior were provided as unmodified ".wmv" files created by the VideoFreeze acquisition software (Med Associates Inc). Video stream parameters: wmv3 codec, color space yuv420p, 320x240 pixels, 30 fps, bitrate 300 kb/s.</p> <p>· movement traces were obtained from the videos, as described in the Methods section (Mombelli et al., 2024).</p>
Docked structures from "Optimizing active learning for free energy calculations"
<p>This archive contains the docked TYK2 structures used in the paper "Optimizing active learning for free energy calculations" (<a title="Persistent link using digital object identifier" href="https://doi.org/10.1016/j.ailsci.2022.100050" target="_blank" rel="noreferrer noopener"><span><span>https://doi.org/10.1016/j.ailsci.2022.100050</span></span></a>). AM1-BCC charges are stored in the field "AM1Cache" in the SD file. The charges can be extracted using the code sample below. </p> <p> </p> <pre><code>from rdkit import Chem import base64 import pickle suppl = Chem.SDMolSupplier("10k_most_similar_tyk2_charged.sdf", removeHs=False) for mol in suppl: am1 = mol.GetProp("AM1Cache") am1_charges = pickle.loads(base64.b64decode(mol.GetProp("AM1Cache"))) assert len(am1_charges) == mol.GetNumAtoms(), "Charge cache has different number of charges than mol atoms"</code></pre>
Attributes: A Curriculum Analytics System for measuring learning outcomes - Overview
<p><span><strong>Link to video </strong><a href="https://vimeo.com/1015456231?share=copy#t=0"><strong>https://vimeo.com/1015456231?share=copy - t=0</strong></a><br><br>The Curriculum Analytics System at the Instituto Tecnológico de Costa Rica, integrated into TEC Digital, supports faculty, coordinators, and students in assessing engineering learning outcomes during accreditation processes. The system offers two key user modules: one for coordinators to map and manage learning outcomes, and another for instructors to conduct assessments through the course portal. Coordinators oversee course and attribute mapping using visual representations of study plans, control points, and outcome visualizations. Instructors configure assignments and evaluate student submissions with standardized rating scales. The system tracks progress in real-time and generates</span> <span>comprehensive reports with performance metrics, facilitating continuous improvement in academic programs.</span></p> <p><strong><span>Key words: </span></strong><span>attributes, learning outcomes, TEC Digital, curriculum analytics, continuous improvement. </span></p>
Navigating deep learning strategies for large-area land cover mapping using very-high-resolution imagery in Senegal: Validation Data
<p><span><span>R</span><span>apid</span><span> advances in deep learning</span><span> for</span> <span>land cover </span><span>classification of </span><span>trees, shrubs and </span><span>very small</span> <span>agricultur</span><span>al</span> <span>fields</span> <span>using</span> <span>very high</span><span>-</span><span>resolution satellite </span><span>data </span><span>(< 2 m</span><span>)</span><span>,</span><span> has tremendous potential</span> <span>for resolving </span><span>current</span><span> challenges </span><span>in </span><span>quantifying</span> <span>land cover </span><span>change </span><span>in</span> <span>sub-</span><span>Saharan</span> <span>African (SSA</span><span>)</span><span>,</span> <span>due to</span> <span>growing </span><span>demand for food resources</span><span>.</span> <span>We</span> <span>conducted experiments </span><span>with</span><span> different training strategies for scaling up </span><span>UNet</span> <span>convolutional neural network </span><span>models for regional land cover mapping with multispectral </span><span>WorldView</span><span> (WV</span><span>)</span><span>-2 and –3,</span><span> imagery</span><span> in</span><span> three distinct regions of Senegal </span><span>which</span> <span>has</span><span> complex </span><span>seasonal wet/dry conditions and </span><span>cropland-savanna mosaics. </span></span></p> <p>The validation exercise of this research consisted in validating more than 70,000 km<sup>2</sup> across Senegal. The infrastructure was setup in the NASA SMCE system with a total of twelve George Mason University (GMU) students participating as operators. These operators validated more than 59 WV-2 and -3 images, each consisting of 200 stratified points in 5,000 x 5,000-pixel images. This effort resulted in a total of ~35,000 aggregated observations that are available through the eo-validation API for public consumption. Each validation point from this dataset has three individual observations.</p>
Voxelized fragment dataset for machine learning
<p>One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of sufficient size to facilitate effective training of these networks. This is particularly significant in object detection, shape completion, and fracture assembly. Instead of scanning a large number of real-world fragments, it is possible to generate massive datasets with synthetic pieces. However, realistic fragmentation is computationally intensive in the preparation (e.g., pre-factured models) and generation. Otherwise, simpler algorithms such as Voronoi diagrams provide faster processing speeds at the expense of compromising realism. Hence, it is required to balance computational efficiency and realism for generating large datasets for marching learning.</p> <p>We proposed a GPU-based fragmentation method to improve the baseline Discrete Voronoi Chain aimed at completing this dataset generation task. The dataset in this repository includes voxelized fragments from high-resolution 3D models, curated to be used as training sets for machine learning models. More specifically, these models come from an archaeological dataset, which led to more than 1M fragments from 1,052 Iberian vessels. In this dataset, fragments are not stored individually; instead, the fragmented voxelizations are provided in a compressed binary file (.rle.zip). Once uncompressed, each fragment is represented by a different number in the grid. The class to which each vessel belongs is also included in <em>class.csv</em>. The GPU-based pipeline that generated this dataset is explained at <a title="Persistent link using digital object identifier" href="https://doi.org/10.1016/j.cag.2024.104104" target="_blank" rel="noreferrer noopener">https://doi.org/10.1016/j.cag.2024.104104</a>.</p> <p>Please, note that this dataset originally provided voxel data, point clouds and triangle meshes. However, we opted for including only voxel data because 1) the original dataset is too large to be uploaded to Zenodo and 2) the original intent of our paper is to generate implicit data in the form of voxels. If interested in the whole dataset (450GB), please visit the web page of our <a href="https://s5-ceatic.ujaen.es/fragment-dataset-uja/">research institute</a>.</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.