Skip to main content
ConductScienceScienceDex
Powered by ShareScore

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.

35

datasets available to search

ShareScore release 0.9.0

Reset

Dataset results

35 results for “PERSONAL PROTECTIVE EQUIPMENT”

Learn how ShareScore rates datasets ↗
zenodo36/100

Personal Protective Equipment Dataset (PPED)

<p><strong>Personal Protective Equipment Dataset (PPED)</strong></p> <p>This dataset serves as a benchmark for PPE in chemical plants<br> We provide datasets and experimental results.</p> <p><strong>1. The dataset</strong></p> <p>We produced a data set based on the actual needs and relevant regulations in chemical plants.<br> The standard GB 39800.1-2020 formulated by the Ministry of Emergency Management of the People&rsquo;s Republic of China defines the protective requirements for plants and chemical laboratories.<br> The complete dataset is contained in the folder&nbsp;<code>PPED/data</code>.</p> <p><strong>1.1. Image collection</strong></p> <p>We took more than 3300 pictures.<br> We set the following different characteristics, including different environments, different distances, different lighting conditions, different angles, and the diversity of the number of people photographed.</p> <ul> <li>Backgrounds: There are 4 backgrounds, including office, near machines, factory and regular outdoor scenes.</li> <li>Scale: By taking pictures from different distances, the captured PPEs are classified in small, medium and large scales.</li> <li>Light: Good lighting conditions and poor lighting conditions were studied.</li> <li>Diversity: Some images contain a single person, and some contain multiple people.</li> <li>Angle: The pictures we took can be divided into front and side.</li> </ul> <p>A total of more than 3300 photos were taken in the raw data under all conditions.<br> All images are located in the folder &ldquo;PPED/data/JPEGImages&rdquo;.</p> <p><strong>1.2. Label</strong></p> <p>We use Labelimg as the labeling tool, and we use the PASCAL-VOC labelimg format.<br> Yolo use the txt format, we can use&nbsp;<code>trans_voc2yolo.py</code>&nbsp;to convert the XML file in PASCAL-VOC format to txt file.<br> Annotations are stored in the folder&nbsp;<code>PPED/data/Annotations</code></p> <p><strong>1.3. Dataset Features</strong></p> <p>The pictures are made by us according to the different conditions mentioned above.<br> The file&nbsp;<code>PPED/data/feature.csv</code>&nbsp;is a CSV file which notes all the .os of all the image. It records every feature of the picture, including lighting conditions, angles, backgrounds, number of people and scale.</p> <p>1.4. Dataset Division</p> <p>The data set is divided into 9:1 training set and test set.</p> <p><strong>2. Baseline Experiments</strong></p> <p>We provide baseline results with five models, namely Faster R-CNN &reg;, Faster R-CNN (M), SSD, YOLOv3-spp, and YOLOv5.<br> All code and results is given in folder&nbsp;<code>PPED/experiment</code>.</p> <p><strong>2.1. Environment and Configuration:</strong></p> <ul> <li>Intel Core i7-8700 CPU</li> <li>NVIDIA GTX1060 GPU</li> <li>16 GB of RAM</li> <li>Python: 3.8.10</li> <li>pytorch: 1.9.0</li> <li>pycocotools: pycocotools-win</li> <li>Windows 10</li> </ul> <p><strong>2.2. Applied Models</strong></p> <p>The source codes and results of the applied models is given in folder&nbsp;<code>PPED/experiment</code>&nbsp;with sub-folders corresponding to the model names.</p> <p><strong>2.2.1. Faster R-CNN</strong></p> <ul> <li>Faster R-CNN <ul> <li>backbone: resnet50+fpn <ul> <li>We downloaded the pre-training weights from&nbsp;<a href="https://download.pytorch.org/models/fasterrcnn_resnet50_fpn_coco-258fb6c6.pth">https://download.pytorch.org/models/fasterrcnn_resnet50_fpn_coco-258fb6c6.pth</a>.</li> <li>We modified the dataset path, training classes and training parameters including batch size.</li> <li>We run&nbsp;<code>train_res50_fpn.py</code>&nbsp;start training.</li> <li>Then, the weights are trained by the training set.</li> <li>Finally, we validate the results on the test set.</li> </ul> </li> <li>backbone: mobilenetv2 <ul> <li>the same training method as resnet50+fpn, but the effect is not as good as resnet50+fpn, so it is directly discarded.</li> </ul> </li> </ul> </li> </ul> <p>The Faster R-CNN&nbsp;source code used in our experiment is given in folder&nbsp;<code>PPED/experiment/Faster R-CNN</code>.<br> The weights of the fully-trained Faster R-CNN (R), Faster R-CNN (M) model are stored in file&nbsp;<code>PPED/experiment/trained_models/resNetFpn-model-19.pth and&nbsp;</code>mobile-model.pth.<br> The performance measurements of Faster R-CNN (R) Faster R-CNN (M) are stored in folder&nbsp;<code>PPED/experiment/results/Faster RCNN(R)and Faster RCNN(M)</code>.</p> <p><strong>2.2.2. SSD</strong></p> <ul> <li>backbone: resnet50</li> <li>We downloaded pre-training weights from&nbsp;<a href="https://download.pytorch.org/models/resnet50-19c8e357.pth">https://download.pytorch.org/models/resnet50-19c8e357.pth</a>.</li> <li>The same training method as Faster R-CNN is applied.</li> </ul> <p>The SSD source code used in our experiment is given in folder&nbsp;<code>PPED/experiment/ssd</code>.<br> The weights of the fully-trained SSD model are stored in file&nbsp;<code>PPED/experiment/trained_models/SSD_19.pth</code>.<br> The performance measurements of SSD are stored in folder&nbsp;<code>PPED/experiment/results/SSD</code>.</p> <p><strong>2.2.3. YOLOv3-spp</strong></p> <ul> <li>backbone: DarkNet53</li> <li>We modified the type information of the XML file to match our application.</li> <li>We run&nbsp;<code>trans_voc2yolo.py</code>&nbsp;to convert the XML file in VOC format to a txt file.</li> <li>The weights used are: yolov3-spp-ultralytics-608.pt.</li> </ul> <p>The YOLOv3-spp source code used in our experiment is given in folder&nbsp;<code>PPED/experiment/YOLOv3-spp</code>.<br> The weights of the fully-trained YOLOv3-spp model are stored in file&nbsp;<code>PPED/experiment/trained_models/YOLOvspp-19.pt</code>.<br> The performance measurements of YOLOv3-spp are stored in folder&nbsp;<code>PPED/experiment/results/YOLOv3-spp</code>.</p> <p><strong>2.2.4. YOLOv5</strong></p> <ul> <li>backbone: CSP_DarkNet</li> <li>We modified the type information of the XML file to match our application.</li> <li>We run&nbsp;<code>trans_voc2yolo.py</code>&nbsp;to convert the XML file in VOC format to a txt file.</li> <li>The weights used are: yolov5s.</li> </ul> <p>The YOLOv5 source code used in our experiment is given in folder&nbsp;<code>PPED/experiment/yolov5</code>.<br> The weights of the fully-trained YOLOv5 model are stored in file&nbsp;<code>PPED/experiment/trained_models/YOLOv5.pt</code>.<br> The performance measurements of YOLOv5 are stored in folder&nbsp;<code>PPED/experiment/results/YOLOv5</code>.</p> <p>2.3. Evaluation</p> <p>The computed evaluation metrics as well as the code needed to compute them from our dataset are provided in the folder&nbsp;<code>PPED/experiment/eval</code>.</p> <p><strong>3. Code Sources</strong></p> <ol> <li>Faster R-CNN (R and M) <ul> <li>https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_object_detection/faster_rcnn</li> <li>official code:&nbsp;https://github.com/pytorch/vision/blob/main/torchvision/models/detection/faster_rcnn.py</li> </ul> </li> <li>SSD <ul> <li><a href="https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_object_detection/ssd">https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_object_detection/ssd</a></li> <li>official code:&nbsp;<a href="https://github.com/pytorch/vision/blob/main/torchvision/models/detection/ssd.py">https://github.com/pytorch/vision/blob/main/torchvision/models/detection/ssd.py</a></li> </ul> </li> <li>YOLOv3-spp <ul> <li><a href="https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_object_detection/yolov3-spp">https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/tree/master/pytorch_object_detection/yolov3-spp</a></li> </ul> </li> <li>YOLOv5 <ul> <li><a href="https://github.com/ultralytics/yolov5">https://github.com/ultralytics/yolov5</a></li> </ul> </li> </ol>

opencc-by-4.0May 2022View details →
ClinicalTrials.gov36/100

The Effectiveness of Health Education Intervention in Enhancing Personal Protective Equipment Use

ClinicalTrials.gov study NCT07087444. IPD Sharing: YES. Countries: 1. Publications: 1.

controlledIPD-YESFeb 2026View details →
ClinicalTrials.gov32/100

Farming, Personal Protective Equipment, Nepal

ClinicalTrials.gov study NCT02137317. IPD Sharing: Not stated. Countries: 1. Publications: 30.

restrictedIPD-UNDECIDEDFeb 2026View details →
ClinicalTrials.gov32/100

Prehospital Intubation of COVID-19 Patient With Personal Protective Equipment

ClinicalTrials.gov study NCT04365608. IPD Sharing: YES. Countries: 1. Publications: 1.

controlledIPD-YESFeb 2026View details →
ClinicalTrials.gov32/100

Personal Protective Equipment Effects

ClinicalTrials.gov study NCT05369663. IPD Sharing: NO. Countries: 1. Publications: 1.

closedIPD-NOFeb 2026View details →
ClinicalTrials.gov32/100

COVID-19 Personal Protective Equipment for Vaccinated Health Workers and Convalescents

ClinicalTrials.gov study NCT06158724. IPD Sharing: UNDECIDED. Countries: 1. Publications: 4.

restrictedIPD-UNDECIDEDFeb 2026View details →
ClinicalTrials.gov32/100

The Rescuer Fatigue During Cardiopulmonary Resuscitation in Manikin by Using Personal Protective Equipment.

ClinicalTrials.gov study NCT04802109. IPD Sharing: NO. Countries: 1. Publications: 1.

closedIPD-NOFeb 2026View details →
ClinicalTrials.gov32/100

Electronic Stethoscope Use During Intubation in Full Personal Protective Equipment

ClinicalTrials.gov study NCT04507958. IPD Sharing: NO. Countries: 1. Publications: 1.

closedIPD-NOFeb 2026View details →
ClinicalTrials.gov32/100

Testing of Personal Protective Equipment (PPE)

ClinicalTrials.gov study NCT03004690. IPD Sharing: NO. Countries: 1. Publications: 1.

closedIPD-NOFeb 2026View details →
ClinicalTrials.gov32/100

Personal Protective Equipment for the Prevention of SARS-Cov-2 During Neonatal Resuscitation

ClinicalTrials.gov study NCT04666233. IPD Sharing: UNDECIDED. Countries: 1. Publications: 4.

restrictedIPD-UNDECIDEDFeb 2026View details →
ClinicalTrials.gov32/100

Intravascular Access of COVID-19 Patient Under Personal Protective Equipment

ClinicalTrials.gov study NCT04366297. IPD Sharing: UNDECIDED. Countries: 1. Publications: 1.

restrictedIPD-UNDECIDEDFeb 2026View details →
ClinicalTrials.gov32/100

Assessment of N-95 Facemask for Use in COVID-19 Pandemic in Case of Shortage of Personal Protective Equipment

ClinicalTrials.gov study NCT04416919. IPD Sharing: NO. Countries: 1. Publications: 2.

closedIPD-NOFeb 2026View details →
zenodo28/100

COVID-19 Personal Protective Equipment by Patient Flow

<p>This process flow map outlines the Personal Protective Equipment usage rates per provider, per patient, and per procedure for all patients presenting for medical care.</p>

opencc-by-4.0Apr 2020View details →
zenodo28/100

TECHNICAL ASPECTS OF OPERATION OF PERSONAL PROTECTION EQUIPMENT FOR MILITARY SERVICEMEN

Open the record for dataset details and reuse information.

opencc-by-4.0Dec 2023View details →
zenodo28/100

Covid-19 pandemic management in a construction alliance project in Finland – experiences on the personal protective equipment protocols

<p>Material is supplementary data for article &#39;Covid-19 pandemic management in a construction alliance project in Finland &ndash; experiences on the personal protective equipment protocols&#39;. It includes Covid-19 timeline gathered from public sources,&nbsp;by information requests from Finnish officials and Raide-Jokeri Light Rail Alliance internal and parent organization data. Timeline includes legizlation, orders, recommendations and instructions from different organizations as well as anonymous list of Covid-19 incidents in Raide-Jokeri.&nbsp;<br> Data also includes first instructions and exit strategy from Raide-Jokeri</p>

opencc-by-4.0Sep 2022View details →
ClinicalTrials.gov28/100

Personal Protective Equipment Affect Team Performance During Medical Emergencies

ClinicalTrials.gov study NCT04742426. IPD Sharing: NO. Countries: 0. Publications: 2.

closedIPD-NOFeb 2026View details →
ClinicalTrials.gov28/100

SARS-CoV 2 in Personal Protective Equipment

ClinicalTrials.gov study NCT04398043. IPD Sharing: UNDECIDED. Countries: 0. Publications: 5.

restrictedIPD-UNDECIDEDFeb 2026View details →
zenodo24/100

R2PPE: Resuscitation Room Personal Protective Equipment Dataset

Open the record for dataset details and reuse information.

opencc-by-nc-4.0Sep 2024View details →
ClinicalTrials.gov24/100

Alternative Doffing Strategies to Prevent Healthcare Worker Self-Contamination When Using Personal Protective Equipment (PPE)

ClinicalTrials.gov study NCT03192553. IPD Sharing: Not stated. Countries: 1. Publications: 0.

restrictedIPD-UNDECIDEDFeb 2026View details →
ClinicalTrials.gov24/100

Effect of Wearing Personal Protective Equipment (PPE) on CPR Quality in Times of the COVID-19-pandemic

ClinicalTrials.gov study NCT04548934. IPD Sharing: NO. Countries: 1. Publications: 0.

closedIPD-NOFeb 2026View details →

ScienceDex guides

Understand access before you commit

These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.

Compare curated 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.

allen-brain-atlas
neuroscienceopenDocumentation, web resources, and API references are available online.
Last verified 2026-04-30Open record

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.

abode-home-cage
behavioral-neuroscienceopenThe DataShare record exposes download links for annotations, documentation, license text, and the zipped per-snippet data directory.
Last verified 2026-04-30Open record

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.

dandi-nwb
electrophysiologyopenPublished Dandiset metadata and archive endpoints are available through the production DANDI API.
Last verified 2026-04-30Open record

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.

ibl
behavioral-neuroscienceopenPublic sessions can be searched and loaded from the IBL public data server through ONE.
Last verified 2026-04-29Open record

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.

openneuro
neuroscienceopenPublished datasets are available on demand over the internet.
Last verified 2026-04-29Open record

ScienceDex for faculty

Your academic CV and NIH biosketch

Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.