Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
6
datasets available to search
ShareScore release 0.9.0
Dataset results
6 results for “hand kinematics”
RPC-Net Dataset. Simultaneous HD-sEMG Recordings on the Forearm and angles of a 29-DOF Hand Kinematic Model
<p>The dataset in this repository comprises data acquired during the doctoral research project of Giovanni Rolandino at the Nuffield Department of Surgical Sciences, University of Oxford. Five sub-datasets make up the repository:</p> <p>DS1: Simultaneous acquisition of high-density surface electromyography (HD-sEMG) signals from the forearm and hand position kinematics. Data were recorded from 12 healthy subjects while they cycled through 16 hand poses. HD-sEMG was acquired with traditional gel electrode arrays.</p> <p>DS2: A similar protocol to DS1 was followed, but the HD-sEMG was acquired using a novel dry-electrode array. This dataset includes 16 subjects. Whereas DS1 included data from a single session for each subject, DS2 includes two sessions, acquired hours to days apart; these sessions are identified as s1 and s2.</p> <p>DS3: This subset consists of two parts. DS3.a repeats the protocol used in DS2 with 4 subjects, introducing repositioning between trials. DS3.b includes the results of the real-time assessment of RPC-Net, a shallow neural network trained with data from DS3.a to estimate hand position from HD-sEMG activity. DS3.b contains the real-time output recorded during prompt-matching tasks and the corresponding targets.</p> <p>DS4: This subset includes data related to the assessment of RFC-Net, a shallow neural network designed to estimate hand position from neck muscle activation. Experiments were performed on 8 healthy participants and 8 participants with tetraplegia. DS4.a includes the data used for training the network, while DS4.b includes data from the testing phase of the algorithm. DS4.b.s1 includes results from a cursor control task, and DS4.b.s2 includes results from a virtual hand control task.</p> <p>AD1: Additional data related to the electrical validation of the dry-electrode array.</p> <p>Code for processing the data in this repository is available on Dropbox:<br>https://www.dropbox.com/scl/fo/nkvbse7evo0k8ou1utn7i/AMDh_MOZQJ6gCwDXGPadmZ0?rlkey=ynoix3anpc81v24hogn3fymb4&st=xrqx07q2&dl=0</p> <p>For additional information, readers are referred to the original papers detailing acquisition protocols and processing procedures:</p> <p>1) G. Rolandino, M. Gagliardi, T. Martins, G. L. Cerone, B. Andrews, J. J. FitzGerald. Developing RPC-Net: Leveraging High-Density Electromyography and Machine Learning for Improved Hand Position Estimation. IEEE Transactions on Biomedical Engineering, 71(5):1617-1627, May 2024. doi:10.1109/TBME.2023.3346192.</p> <p>2) G. Rolandino, C. Zangrandi, T. Vieira, G. L. Cerone, B. Andrews, J. J. FitzGerald. HDE-Array: Development and Validation of a New Dry Electrode Array Design to Acquire HD-sEMG for Hand Position Estimation. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32:4004-4013, 2024. doi:10.1109/TNSRE.2024.3490796.</p> <p>3) G. Rolandino, T. Vieira, G. L. Cerone, B. Andrews, J. J. FitzGerald. Performance of a ML-Based 3-DoF Kinematic Model in Estimating Hand Position from High-Density EMG. Presented at IFESS Conference, Bath, UK, September 2024.</p> <p>4) G. Rolandino, L. Lion, T. Vieira, G. L. Cerone, B. Andrews, J. J. FitzGerald. Artificial Neural Networks for HD-sEMG-Based Hand Position Estimation: Addressing Inter- and Intra-Subject Variability. Submitted to IEEE Transactions on Neural Systems and Rehabilitation Engineering, July 2025.</p> <p>5) G. Rolandino, G. Parisi, T. Vieira, G. L. Cerone, B. Andrews, J. J. FitzGerald. Real-Time Hand Kinematic Estimation with HD-sEMG and Artificial Neural Networks: Feasibility and Effects of Multi-Subject Training and Visual Feedback. Submitted to IEEE Transactions on Neural Systems and Rehabilitation Engineering, July 2025.</p> <p>6) G. Rolandino, V. Taboni Lisboa, T. Vieira, A. Cliquet Jr., B. Andrews, J. J. FitzGerald. HD-sEMG-Based Control Using Neck Muscles and Shallow Neural Networks: Assessing Performance in Rehabilitation-Oriented Tasks. Submitted to IEEE Transactions on Neural Systems and Rehabilitation Engineering, July 2025.</p> <p>This dataset benefited from the support of all listed authors and arose from collaborations between the Oxford Neural Interfacing Group; LISiN (Politecnico di Torino, Turin, Italy); the Department of Orthopedics, Rheumatology and Traumatology (University of Campinas, SP, Brazil); and the Oxford Robotics Institute (University of Oxford, Oxford, UK). Part of this work was funded by the John Fell Oxford University Press Research Fund.</p> <p>The corresponding author is available for questions or clarification at g.rolandino@protonmail.com.</p>
A calibrated database of kinematics and EMG of the forearm and hand during activities of daily living
<p>KIN-MUS UJI Dataset contains 572 recordings with anatomical angles and forearm muscle activity of 22 subjects while performing 26 representative activities of daily living. This dataset is, to our knowledge, the biggest currently available hand kinematics and muscle activity dataset to focus on goal-oriented actions. Data were recorded using a CyberGlove instrumented glove and surface EMG electrodes, both properly synchronised. Eighteen hand anatomical angles were obtained from the glove sensors by a validated calibration procedure. Surface EMG activity was recorded from seven representative forearm areas. The statistics verified that data were not affected by the experimental procedures and were similar to the data acquired under real-life conditions.</p> <p> </p> <p><strong>Data Sets</strong>:</p> <p>Data are presented as a Matlab data structure (<em>.mat</em> file). This structure contains all the recorded kinematic and muscle activity data classified as: ADL, phase (reaching, manipulation or release) and subject. The fields contained in the structure are those detailed in the following scheme:</p> <ul> <li>Subject: subject ID;</li> <li>ADL: ADL ID;</li> <li>Phase: phase of movement. 1 corresponds to reaching; 2 corresponds to manipulation; 3 corresponds to releasing.</li> <li>Time: Time stamp</li> <li>Angles (18 columns): Calibrated anatomical angles</li> <li>Muscle activity (7 columns): Normalised signal for the seven representative spot areas, according to [1].</li> </ul> <p>RAW_EMG struct provides the raw sEMG data, without any filter and not resampled, so that researchers may choose to condition the signals as they please<strong>.</strong> The fields contained in this structure are those detailed in the following scheme:</p> <ul> <li>Subject: subject ID;</li> <li>ADL: ADL ID, according to Table 1;</li> <li>Time: Time stamp; this field corresponds with the time stamp of the previous structure.</li> <li>Raw EMG data (7 columns): Raw sEMG data without any filter and not resampled, for the seven representative spot areas according to [1].</li> </ul> <p>[1] Jarque-Bou, N. J., Vergara, M., Sancho-Bru, J. L., Alba, R.-S. & Gracia-Ibáñez, V. Identification of forearm skin zones with similar muscle activation patterns during activities of daily living. <em>J. NeuroEngineering Rehabil. </em>(2018).</p>
MOVMUS-UJI Dataset & ERGOMOVMUS: EMG and kinematics data of the hand in activities of daily living with special interest for ergonomics
<p>A dataset of <strong>human hand kinematics</strong> and <strong>forearm muscle activation</strong> collected during the performance of a wide variety of activities of daily living (ADLs) is presented, with tagged characteristics of products and tasks. A total of <strong>26 participants</strong> performed <strong>161 ADLs</strong>, selected to be representative of common elementary tasks, grasp types, product orientations and performance heights. 105 products were used, being varied regarding shape, dimensions, weight and type (common products and assistive devices).</p> <p>The data were recorded using CyberGlove instrumented gloves on both hands measuring 18 degrees of freedom on each and seven surface EMG sensors per arm recording muscle activity. The products and their arrangement were the same across subjects, and tasks were performed in a guided way. Data of <strong>more than 4100 ADLs</strong> is presented in this dataset as <strong>Matlab structures</strong> with full continuous recordings, which may be used in applications such as machine learning or to characterize healthy human hand behaviour.</p> <p>The dataset is accompanied with a <strong>custom data visualization application (ERGOMOVMUS)</strong> as a tool for ergonomics applications, allowing visualization and calculation of aggregated data from specific task, product and/or subjects’ characteristics.</p> <p> </p> <p><strong>v3.0 includes the following updates:</strong></p> <p>- Statistical summary of the recordings both in .xlsx and .ods file format (v1.1 only included it in .xlsx file format)</p> <p>- Updated experiment details in "MOVMUS-UJI DATASET GUIDE.pdf".</p>
Calibrated kinematic Ninapro hand movements data
<p>The kinematic data of the Ninapro (Non Invasive Adaptive Prosthetics) database includes calibrated kinematic data from 77 subjects, performing 40 hand movements and grasps. The whole database aims at allowing worldwide research groups to study hand kinematics. As well the dataset allows also to study the relationship between hand kinematics and muscle activity, since it is linked to sEMG datasets. The final goal of this work is to aid the progress in rehabilitation, physiotherapy, medicine, neuroscience and prosthetics. Therefore, the kinematic database improves the state of the art, being the most accurate, comprehensive and advanced reference for the largest kinematic database existing at the time of writing. <br> <br> <strong>Acquisition protocol</strong>:<br> Hand kinematics was measured using a 22-sensor CyberGlove II dataglove (CyberGlove Systems LLC, <a href="http://www.cyberglovesystems.com/">www.cyberglovesystems.com</a>). The CyberGlove is a motion capture data glove, instrumented with joint-angle measurements. It uses proprietary resistive bend-sensing technology to transform hand and finger motions into real-time digital joint-angle data.<br> <br> The calibrated kinematic Ninapro database includes 40 different movements of 77 intact subjects.<br> The subjects have to repeat several movement represented by movies that are shown on the screen of a laptop.<br> The experiment is divided in two exercises:<br> • Isometric, isotonic hand configurations and basic wrist movements<br> • Grasping and functional movements<br> Joint angles from raw data were calculated according to a very detailed calibration protocol. The protocol was previously applied to 10 different intact subjects and consists in recording 64 different poses or guided movements to obtain the gains and also some corrections because of cross-coupling effects for specific anatomical angles.</p> <p>Gracia-Ibáñez, V., Vergara, M., Buffi, J. H., Murray, W. M. & Sancho-Bru, J. L. Across-subject calibration of an instrumented glove to measure hand movement for clinical purposes. C. Comput. Methods Biomech. Biomed. Eng. 20, 587–597 (2017).<br> <br> <strong>Data Sets</strong>:<br> For each subject and exercise, the database contains one file in Matlab format (<a href="http://www.mathworks.com/">www.mathworks.com</a>) with synchronized variables. The variables included are the following ones:<br> • subject: subject number;<br> • exercise: exercise number;<br> • glove (22 columns): uncalibrated signal from the 22 sensors of the Cyberglove. Details on the location of the sensors are available at the link: <a href="http://ninapro.hevs.ch/node/123">ninapro.hevs.ch/node/123</a>;<br> • angles(22 columns): calibrated signal from the 22 sensors of the Cyberglove by applying an across-subject calibration<br> • re-stimulus (1 column): the a-posteriori refined label of the movement;<br> • re-repetition (1 column): re-stimulus repetition index;</p> <p> • stimulus (1 column): the label of the movement;<br> • repetition (1 column): stimulus repetition index;<br> • order of angles (22 columns) : name of the angles corresponding to variable “angles”.</p> <p>Raw glove data are also included in the folder "Raw data".</p>
Finger kinematics of natural hand movements recorded by an exoskeleton data glove in younger and elderly persons
<p>The data set provides measurements using a SenseGlove DK1.3 exoskeleton data glove while healthy younger and elderly participants performed natural hand movements. Specifically, participants were asked to perform six types of hand-movements where each finger (index to little, i.e., D2-D5) was used once per trial to perform a grip movement together with the thumb (D1) resulting in a sequence of four finger movements per trial.</p>
Kinematics of Silastic Joint Replacements in the Hand
ClinicalTrials.gov study NCT05441462. IPD Sharing: NO. Countries: 1. Publications: 0.
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.