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.
211
datasets available to search
ShareScore release 0.9.0
Dataset results
211 results for “HAR”
Curated list of HAR datasets
<p>A curated list of <em>preprocessed</em> & <em>ready to use under a minute</em> Human Activity Recognition datasets.</p> <p>All the datasets are preprocessed in <a href="https://www.hdfgroup.org/solutions/hdf5/">HDF5</a> format, created using the <a href="http://www.h5py.org">h5py</a> python library. Scripts used for data preprocessing are provided as well (Load.ipynb and load_jordao.py)</p> <p>Each HDF5 file contains at least the keys:</p> <ul> <li><code>x</code> a single array of size <code>[sample count, temporal length, sensor channel count]</code>, contains the actual sensor data. Metadata contains the names of individual sensor channel count. All samples are zero-padded for constant length in the file, original lengths before padding available under the <code>meta</code> keys.</li> <li><code>y</code> a single array of size <code>[sample count]</code> with integer values for target classes (zero-based). Metadata contains the names of the target classes.</li> <li><code>meta</code> contain various metadata, depends on the dataset (original length before padding, subject no., trial no., etc.)</li> </ul> <p>Usage example</p> <pre><code>import h5py with h5py.File(f'data/waveglove_multi.h5', 'r') as h5f: x = h5f['x'] y = h5f['y']['class'] print(f'WaveGlove-multi: {x.shape[0]} samples') print(f'Sensor channels: {h5f["x"].attrs["channels"]}') print(f'Target classes: {h5f["y"].attrs["labels"]}') first_sample = x[0] # Output: # WaveGlove-multi: 10044 samples # Sensor channels: ['acc1-x' 'acc1-y' 'acc1-z' 'gyro1-x' 'gyro1-y' 'gyro1-z' 'acc2-x' # 'acc2-y' 'acc2-z' 'gyro2-x' 'gyro2-y' 'gyro2-z' 'acc3-x' 'acc3-y' # 'acc3-z' 'gyro3-x' 'gyro3-y' 'gyro3-z' 'acc4-x' 'acc4-y' 'acc4-z' # 'gyro4-x' 'gyro4-y' 'gyro4-z' 'acc5-x' 'acc5-y' 'acc5-z' 'gyro5-x' # 'gyro5-y' 'gyro5-z'] # Target classes: ['null' 'hand swipe left' 'hand swipe right' 'pinch in' 'pinch out' # 'thumb double tap' 'grab' 'ungrab' 'page flip' 'peace' 'metal'] </code></pre> <p>Current list of datasets:</p> <ul> <li>WaveGlove-single (waveglove_single.h5)</li> <li>WaveGlove-multi (waveglove_multi.h5)</li> <li>uWave (uwave.h5)</li> <li>OPPORTUNITY (opportunity.h5)</li> <li>PAMAP2 (pamap2.h5)</li> <li>SKODA (skoda.h5)</li> <li>MHEALTH (non overlapping windows) (mhealth.h5)</li> <li>Six datasets with all four predefined train/test folds<br> as preprocessed by Jordao et al. originally in <a href="https://github.com/arturjordao/WearableSensorData">WearableSensorData</a><br> (FNOW, LOSO, LOTO and SNOW prefixed .h5 files)</li> </ul>
Aboveground Biomass (AGB) measurements at Hartheim Forest Research Site (DE-Har) 2023
<p>Aboveground biomass (AGB) estimated at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site">Hartheim Forest Research Site</a> (ICOS Ecosystem Site “DE-Har”) in Fall 2023 gathered in compliance with ICOS instructions for AGB determination.</p> <p>Associated Ecoystem Site in the Integrated Carbon Observation System (ICOS).</p> <p>Site Metadata:</p> <p>Station Name: Hartheim-DE-HAR<br>Station ID: DE-Har<br>Station Address: Hartheim am Rhein, Germany<br>Station Longitude: 7.59814 deg E<br>Station Latitude: 47.93391 deg N<br>Station Elevation: 201 m</p>
Data from Phenocam (PHE) measurements of above-canopy vegetation (hartheim1) at Hartheim Forest Research Site (DE-Har) from 2023-01-01 to 2023-12-31 [RAW]
<p>Phenocam images from "hartheim1" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2023. </p> <p>Phenocam "hartheim1" shows the view from the main tower at 29.6m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosystem Site DE-Har, Germany</a> recording the phenology and state of the top of the canopy consisting of pinus sylverstris and pinus nigra.</p>
Data from Phenocam (PHE) measurements of above-canopy vegetation (hartheim1) at Hartheim Forest Research Site (DE-Har) from 2022-01-01 to 2022-12-31 [RAW]
<p>Phenocam images from "hartheim1" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2022. </p> <p>Phenocam "hartheim1" shows the view from the main tower at 29.6m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of the top of the canopy consisting of pinus sylverstris and pinus nigra.</p>
Data from Phenocam (PHE) measurements of above-canopy vegetation (hartheim1) at Hartheim Forest Research Site (DE-Har) from 2021-01-01 to 2021-12-31 [RAW]
<div> <p>Phenocam images from "hartheim1" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2021. </p> <p>Phenocam "hartheim1" shows the view from the main tower at 29.6m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of the top of the canopy consisting of pinus sylverstris and pinus nigra.</p> <p> </p> </div>
Data from Phenocam (PHE) measurements of above-canopy vegetation (hartheim1) at Hartheim Forest Research Site (DE-Har) from 2020-01-01 to 2020-12-31 [RAW]
<p>Phenocam images from "hartheim1" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2020. </p> <p>Phenocam "hartheim1" shows the view from the main tower at 29.6m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of the top of the canopy consisting of pinus sylverstris and pinus nigra.</p>
Data from Phenocam (PHE) measurements of above-canopy vegetation (hartheim1) at Hartheim Forest Research Site (DE-Har) from 2019-01-01 to 2019-12-31 [RAW]
<p>Phenocam images from "hartheim1" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2019. </p> <p>Phenocam "hartheim1" shows the view from the main tower at 30m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of the top of the canopy consisting of pinus sylverstris and pinus nigra.</p>
Data from Phenocam (PHE) measurements of in-canopy vegetation (hartheim2) at Hartheim Forest Research Site (DE-Har) from 2018-11-05 to 2018-12-31 [RAW]
<p>Phenocam images from "hartheim2" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2022. The phenocam "hartheim2" was put into operation on November 5, 2018. There are no phenocam images before that date at this site.</p> <p>Phenocam "hartheim2" shows the view from the main tower at 8.4 m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of in-canopy vegetation.</p>
Data from Phenocam (PHE) measurements of in-canopy vegetation (hartheim2) at Hartheim Forest Research Site (DE-Har) from 2020-01-01 to 2020-12-31 [RAW]
<p>Phenocam images from "hartheim2" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2020. </p> <p>Phenocam "hartheim2" shows the view from the main tower at 8.4 m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosyste Site DE-Har, Germany</a> recording the phenology and state of in-canopy vegetation.</p>
Data from Phenocam (PHE) measurements of in-canopy vegetation (hartheim2) at Hartheim Forest Research Site (DE-Har) from 2021-01-01 to 2021-12-31 [RAW]
<div> <p>Phenocam images from "hartheim2" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2021. </p> <p>Phenocam "hartheim2" shows the view from the main tower at 7m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosystem Site DE-Har, Germany</a> recording the phenology and state of in-canopy vegetation.</p> </div>
Data from Phenocam (PHE) measurements of in-canopy vegetation (hartheim2) at Hartheim Forest Research Site (DE-Har) from 2022-01-01 to 2022-12-31 [RAW]
<div> <p>Phenocam images from "hartheim2" at DE-Har separated into near-infrared (NIR) and visible (VIS) for the year 2022. </p> <p>Phenocam "hartheim2" shows the view from the main tower at at 8.4 m height towards N at the <a href="https://www.meteo.uni-freiburg.de/en/infrastructure/hartheim-forest-research-site?set_language=en">ICOS Associate Ecosystem Site DE-Har, Germany</a> recording the phenology and state of in-canopy vegetation.</p> <p> </p> </div>
Dataset of experiment of wire-harness manufacturing framework validation
<p>Dataset created during the validation experiments of the wire harness manufacturing framework developed within the REMODEL European project.</p>
Harnessing the power of digitized natural history collections to visualize spatiotemporal patterns in native and non-native bee flight phenology
<p>What time of year are bees flying, where are they flying, and how do biogeographical factors, sex, and native status affect flight phenology? Consistent monitoring along with creating spatially and temporally explicit visualizations using large openly available data sets enhance our understanding of trends in flight time phenology and shape our understanding of bee-plant interactions, including shifts in the phenology of bee pollinators.</p> <p>Species occurrence data from digitized collection networks (iNaturalist, Global Biodiversity Information Faculty (GBIF), Integrated Digitized Biocollections (iDigBio), Symbiota Collections of Arthropods Network (SCAN), and UC Santa Barbara Collection Network) are part of an effort to improve our understanding of bees in coastal Santa Barbara County, including the California Channel Islands. New inventory collections combined with historical data from over 11 natural history museums and 2 observation networks are used in an effort to examine patterns and changes in phenology of native and non-native bee species, and create updated species inventories.</p> <p>Synthesizing species observation data from digitized natural history collections makes use of a wealth of existing data and multiplies the analytical power of isolated observations, but it is not without limitations and challenges. By exploring novel techniques to generate clear and accurate visualizations to communicate bee flight time, we present our key initial findings and identify geographic, temporal, and taxonomic gaps, which will lead to further focused inventory projects of coastal Santa Barbara County, improved data quality for phenological analyses, and reusable methods for visualizing insect phenology data across taxa or geography.</p> <p><strong>The attached files include the R code and some of the .csv files used to produce the figures in my poster that was available on demand at the Entomology Society of America 2020 virtual meeting. </strong></p>
Bath Natural Environment HAR Data Set
<p>The data set contains recording from 5 9-axis IMU (MARG) sensors. Attached to ankles, hips and chest. The sensors were sampled at 100Hz. The experiment involved 22 subjects walking around natural environments wearing the five sensors. Though a BLE<br> connections the sensors streamed data to an app on an android phone. The subjects labeled data in real time using buttons in the app. The data was collected in an unsupervised manner and shared with the researchers anonymously.</p> <p>The following activities were recorded; Walking, Ramp Ascent, Ramp Descent, Stair Ascent, Stair Descent, Stopped</p> <p>Please Cite</p> <p>Sherratt, F.; Plummer, A.; Iravani, P. Understanding LSTM Network Behaviour of IMU-Based Locomotion Mode Recognition for Applications in Prostheses and Wearables. <em>Sensors</em> <strong>2021</strong>, <em>21</em>, 1264. https://doi.org/10.3390/s21041264</p>
IAS-Lab Collaborative Draping HAR dataset
<h2>Description</h2> <p>This dataset contains movement data for several subjects performing actions related to human-robot collaboration in an industrial carbon fiber draping process, such as draping and collaborative transport of carbon fiber plies. The collected dataset has been used to train and evaluate skeleton-based Human Action Recognition (HAR) models developed to provide a simple and intuitive way for the human operator to interact with the robot, such as signaling start and stop of the process or requesting robot’s assistance with specific tasks (e.g., inspection of specific parts).</p> <h2><br>Actions of interest</h2> <p>The dataset includes gestures designed to provide a simple and intuitive way for the operator to interact with the robot (e.g., “OK/NEXT” and “POINT” actions), short duration actions related to the beginning and end of collaborative transport operations (e.g., “PICK” and “PLACE” actions), and long duration actions related to the draping process (e.g., “TRANSPORT” and “DRAPING” actions) or general movements of the operator (e.g., “REST” and “WALK”). <br>The dataset also includes an additional unknown class (“UNKWN”) which represents various random movements that the operator might make during the collaborative process but that do not correspond to any of the actions of interest.</p> <table> <tbody> <tr> <td><strong>Action ID</strong></td> <td><strong>Action Name</strong></td> <td><strong>Description</strong></td> </tr> <tr> <td>A001</td> <td>OK/NEXT</td> <td>Raise one arm to signal the robot to continue the draping process</td> </tr> <tr> <td>A002</td> <td>POINT</td> <td>Point at a desired location with a straight right arm to trigger inspection</td> </tr> <tr> <td>A003</td> <td>PICK</td> <td>Raise the ply to trigger the collaborative transport</td> </tr> <tr> <td>A004</td> <td>PLACE</td> <td>Place the ply on the mold</td> </tr> <tr> <td>A005</td> <td>TRANSPORT</td> <td>Collaborative transportation</td> </tr> <tr> <td>A006</td> <td>DRAPE</td> <td>Manual draping of a ply</td> </tr> <tr> <td>A007</td> <td>REST</td> <td>Resting position, mainly waiting for the robot to complete its task</td> </tr> <tr> <td>A008</td> <td>WALK</td> <td>Walking across the workcell</td> </tr> <tr> <td>A009</td> <td>UNKWN</td> <td>Operator movements not related to the draping process</td> </tr> </tbody> </table> <h2> </h2> <h2>Dataset</h2> <p>Data has been collected from 7 participants, 2 female and 5 male, average age 27 (SD=3.0). Each participant performed 6 repetitions of each of the 8 actions considered for a collaborative draping process, and 18 repetitions of random movements for the unknow class. This results in a collected dataset containing 462 trimmed samples, where each sample is a sequence of 3D skeletons lasting approximately 3 seconds, containing only one action being performed. For all samples, 3D skeletons were obtained by means of the camera network installed in the laboratory, providing: (i) 3D skeletons from each camera in the network and (ii) 3D skeletons obtained by fusing the detections from each camera with a tracking algorithm; the output of the tracking algorithm provides a 3D skeleton representation robust to occlusions. All the 3D skeletons acquired are composed of 15 joints, with 3D coordinates expressed with respect to the camera network reference frame.</p> <p>Skeleton data for all sequences are provided in the `skeleton_data` folder. The dataset consists of a folder for each action of interest, with a subfolder for each participant and an individual text file for each action repetition performed by the participant. The naming convention for these files follows a pattern of the type “AxxxPyyyRzzzCwww.skeleton”, where "Axxx" represents the action id, "Pyyy" represents the id assigned to the participant, "Rzzz" represents the repeat number, and "Cwww" represents the id of the camera from which the 3D skeleton is derived; a network of 4 cameras was used to acquire the data, so “C001” denotes the first camera, “C002” the second, and so on, while “C000” represents the 3D skeletons obtained by merging all views.<br>Each of these files is provided as a “.skeleton” text files, similar to popular human action recognition dataset (e.g., NTU RGB+D and NTU RGB+D 120 action recognition datasets). In particular, each file includes a sequence of 3D skeletons with 25 joints following the OpenPose convention for joint numbering, but only the first 15 joints contain valid values since face keypoints were not considered during the acquisitions.</p> <p>Example python code to read/write and visualize the skeleton data is also provided in the `scripts` folder:<br>```python<br>python3 plot_sequence.py --data_dir ../skeleton_data<br>```</p> <p> </p> <h2>References</h2> <ol> <li>Allegro, D., Terreran, M., & Ghidoni, S. (2023). METRIC—Multi-Eye to Robot Indoor Calibration Dataset. Information, 14(6), 314. https://doi.org/10.3390/info14060314</li> <li>Terreran, M., Barcellona, L., & Ghidoni, S. (2023). A general skeleton-based action and gesture recognition framework for human–robot collaboration. Robotics and Autonomous Systems, 170, 104523. https://doi.org/10.1016/j.robot.2023.104523</li> <li>Terreran, M., Lazzaretto, M., & Ghidoni, S. (2022, June). Skeleton-based action and gesture recognition for human-robot collaboration. In International Conference on Intelligent Autonomous Systems (pp. 29-45). Cham: Springer Nature Switzerland.</li> <li>Carraro, M., Munaro, M., Burke, J., & Menegatti, E. (2019). Real-time marker-less multi-person 3D pose estimation in RGB-depth camera networks. In Intelligent Autonomous Systems 15: Proceedings of the 15th International Conference IAS-15 (pp. 534-545). Springer International Publishing.</li> </ol>
Soil moisture for Har Ha`Negev
<p>Pixel values represent the surface soil moisture content (in m3m-3*100) of, approximately, the top 5 cm of soil. The retrieval was based on Sentinel-1 time-series and a Support Vector Machine based approach. L. Pasolli, C. Notarnicola, G. Bertoldi, L. Bruzzone, R. Remelgado, F. Greifeneder, G. Niedrist, S. Della Chiesa, U. Tappeiner, and M. Zebisch, “Estimation of Soil Moisture in Mountain Areas Using SVR Technique Applied to Multiscale Active Radar Images at C-Band,” Sel. Top. Appl. Earth Obs. Remote Sens., vol. 8, no. 1, pp. 262–283, 2015.</p>
Data From: Harnessing Deep Belief Networks for Selective HDAC6 Inhibitors Identification
<p>This dataset contains the results from virtual screening of SPECS library after predicting the selectivity of molecules against HDAC6 over using a Deep Belief Network model that was trained and tested by the authors.</p> <p>The docking poses of 10 molecules with best docking scores were given along with their MMGBSA scores. </p> <p>The MD trajectory files along with the analysis were also provided for the selected three molecules as well as the reference molecule (co-crystalized ligand).</p>
Data from: harnessing the power of regional baselines for broad-scale genetic stock identification: a multistage, integrated, and cost-effective approach
<p>In mixed-stock fishery analyses, genetic stock identification (GSI) estimates the contribution of each population to a mixture and is typically conducted at a regional scale using genetic baselines specific to the stocks expected in that region. Often these regional baselines cannot be combined to produce broader geographical baselines due to non-overlapping populations and genetic markers. In cases where the mixture contains stocks spanning across a wide area, a broad-scale baseline is created, but often at the cost of resolution. Here, we introduce a new GSI method to harness the resolution capabilities of baselines developed for regional applications in the analysis of mixtures containing individuals from a broad geographic range. This method employs a multistage framework that allows disparate baselines to be used in a single integrated process that produces estimates along with the propagated errors from each stage. All individuals in the mixture sample are required to be genotyped for all genetic markers in the baselines used by this model, but the baselines do not require overlap in genetic markers or populations representing the broad-scale or regional baselines.</p> <p>We demonstrate our integrated multistage GSI model using a synthesized data set made up of Chinook salmon, <em>Oncorhynchus tshawytscha</em>, from the North Bering Sea of Alaska. The data set is designed to be run using R package, Ms.GSI, and it does not represent the composition of the real fishery. The results show an improved accuracy for estimates using an integrated multistage framework, compared to the conventional framework of using separate hierarchical steps. The integrated multistage framework allows GSI of a wide geographic area without first developing a large scale, high-resolution genetic baseline or dividing a mixture sample into smaller regions beforehand. This approach is more cost-effective than updating range-wide baselines with all regionally important markers.</p>
Harnessing single cell RNA sequencing to identify dendritic cell types, characterize their biological states and infer their activation trajectory
<p><strong>Summary: </strong>Dendritic cells (DCs) orchestrate innate and adaptive immunity, by translating the sensing of distinct danger signals into the induction of different effector lymphocyte responses, to induce different defense mechanisms suited to face distinct types of threats. Hence, DCs are very plastic, which results from two key characteristics. First, DCs encompass distinct cell types specialized in different functions. Second, each DC type can undergo different activation states, fine-tuning its functions depending on its tissue microenvironment and the pathophysiological context, by adapting the output signals it delivers to the input signals it receives. Hence, to better understand DC biology and harness it in the clinic, we must determine which combinations of DC types and activation states mediate which functions, and how.<br> To decipher the nature, functions and regulation of DC types and their physiological activation states, one of the methods that can be harnessed most successfully is ex vivo single cell RNA sequencing (scRNAseq). However, for new users of this approach, determining which analytics strategy and computational tools to choose can be quite challenging, considering the rapid evolution and broad burgeoning of the field. In addition, awareness must be raised on the need for specific, robust and tractable strategies to annotate cells for cell type identity and activation states. It is also important to emphasize the necessity of examining whether similar cell activation trajectories are inferred by using different, complementary methods. In this chapter, we take these issues into account for providing a pipeline for scRNAseq analysis and illustrating it with a tutorial reanalyzing a public dataset of mononuclear phagocytes isolated from the lungs of naïve or tumor-bearing mice. We describe this pipeline step-by-step, including data quality controls, dimensionality reduction, cell clustering, cell cluster annotation, inference of the cell activation trajectories and investigation of the underpinning molecular regulation. It is accompanied with a more complete tutorial on Github. We anticipate that this method will be helpful for both wet lab and bioinformatics researchers interested in harnessing scRNAseq data for deciphering the biology of DCs or other cell types, and that it will contribute to establishing high standards in the field.</p> <p> </p> <p><strong>Data:</strong></p> <p>1. negative_cDC1_relative_signatures.csv : Negative signatures for performing Connectivity Map (cMAP) Analysis</p> <p>2. positive_cDC1_relative_signatures.csv : Positive signatures for performing Connectivity Map (cMAP) Analysis</p>
Ligustrum delavayanum Har. (BR0000009355750)
Belgium Herbarium image of <a href="https://www.plantentuinmeise.be">Meise Botanic Garden</a>.
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.