Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
14,136 datasets
Raw and processed microscopy images and Excel data files from a study on macromolecular composition at artificial cell-cell interfaces. The dataset, 297.1 MB in size, was published by Erdinc Sezgin and colleagues in 2026. It includes lsm, czi, and tif image files alongside Excel sheets for graph data.
Nine samples of carbonaceous shale and two coquinite samples from the Cretaceous Toolebuc Formation were analyzed using high-energy resolution fluorescence detection x-ray absorption spectroscopy. The results characterize uranium speciation, indicating a significant proportion (~20 to 30%) exists as U(VI) in reducing conditions. This abstract was presented at the 2023 Goldschmidt Conference and is hosted by Geoscience Australia.
NFDH's National Formal Rest Areas dataset harmonizes location and facility information from state and territory governments to support driver fatigue management. The data is sourced from open data published by Australian jurisdictions and is available in PDF, CSV, and API formats. It was last updated on 2026-05-17.
3,772 clinical records with 30 features form a public dataset used to develop a deep learning model for hypothyroidism prediction. The dataset was used by author Divya Kesavulu to train the FusionNet-CXG model, with results published on figshare in April 2026. Performance metrics for the model, including a mean accuracy of 0.9394, were obtained through 50 fold-level evaluations using SMOTE-NC and cross-validation.
Divya Kesavulu's FusionNet-CXG model dataset contains 3,772 records with 30 features for hypothyroidism prediction. The dataset was used to train a hybrid deep-learning model combining CNN, eXtended LSTM, and GRU components, with performance evaluated via 50 fold-level evaluations. The data was last updated on 2026-04-21 and is shared under a CC-BY-4.0 license.
3,772 records with 30 features were used to develop FusionNet-CXG, a hybrid deep-learning model for hypothyroidism prediction. The dataset, shared by Divya Kesavulu on figshare, was last updated in April 2026. Experiments used SMOTE-NC to mitigate class imbalance and 10 repetitions of 5-fold cross-validation for evaluation.
A study from 2023 developed a simplified method for measuring volatile organic chemicals (VOCs) in newly manufactured neonatal incubators. The dataset likely contains measurements of formaldehyde and other VOCs taken from two commercial incubators over a 7-day test duration. The data was authored by Alexander Herman and last updated on 2026-05 15.
A 2026 study by Zhi-Yu Duan presents data on urinary microRNA miR-142-3p as a biomarker for predicting the progression of IgA nephropathy (IgAN). The dataset likely contains expression levels from two independent patient cohorts studied between 2014-2015 and 2018-2022. It was published on figshare under a CC-BY-4.0 license.
New South Wales, Australia, maintains legally binding Water Sharing Plans (WSPs) under the Water Management Act 2000. This dataset provides aggregated geospatial boundaries for in-force Groundwater Sources, Unregulated River Sources, Regulated River Sources, and their Management Zones. The plans establish rules for water extraction and are intended to be updated as plans commence or are amended.
Survey responses from 409 Chinese college students collected via questionnaire. The data likely contains measures of short-form video addiction, bedtime procrastination motivation, derailment, and negative emotional states. Author Xi Chen published the dataset on figshare in May 2026.
MEDISEG contains two subsets for pill recognition: a controlled 3-pill set and a diverse 32-pill set with real-world challenges. The dataset includes 426.5 MB of high-resolution JPG images with COCO-format annotations for segmentation masks, bounding boxes, and class labels. William Chu published this dataset on figshare in May 2026.
Australia's marine margins are covered by digital bathymetry, gravity, and magnetic grids with resolutions of 250-1000 meters. The grids were produced by the Australian Geological Survey Organisation in cooperation with Desmond Fitzgerald and Associates and the Australian Hydrographic Service. They integrate ship-track data with satellite and onshore sources, using leveling techniques to correct errors.
AusSeabed's coverage database contains polygon extents of bathymetry data acquisitions from multiple organizations and countries. It is a live resource updated regularly via the AusSeabed Marine Data Portal, identifying data spanning coastal, continental shelf, and deep sea locations. The database is augmented by collaborators who share knowledge of data availability with the broader marine community.
A 675.9 KB supplementary document details a study on groove and synchronization. The research by Hiroko Tanabe, last updated in May 2026, involved participants rating urge-to-move and pleasure while listening to rhythms with varying syncopation under three movement conditions. Auditory-motor synchronization was quantified using phase-locking values between musical rhythms and head movement.
Saber Sotoodeh's data for the paper 'Automatic Pose Estimation in Newborn Infants: Lessons from the Baby Grow Study'. It includes accuracy, speed, and efficiency metrics for six human pose estimation models across varied video conditions. The dataset was last updated on April 30, 2026, and is licensed under CC-BY-4.0.
Fernando Antunes analyzed 5,671 georeferenced establishments across 20 types of retail and services in Petrópolis, Brazil, using the Colocation Quotient (CLQ) measure. The study reveals three consistent spatial patterns: homotypic concentration, heterotypic associations, and directional asymmetries. This dataset was last updated on 2026-05-11.
Eleanor Harrison's dataset tests the impact of introducing a novel symbiosis plasmid (pJB5JI) into 11 Rhizobium leguminosarum strains. It contains measurements of bacterial growth rates in lab media and plant growth parameters from pea and clover seedling experiments. The data was last updated on 2026-05-06.
Two digitized map plates detail the distribution of permafrost and seasonally frozen ground across Mongolia. The dataset includes a 1:12,000,000 scale map showing four general geocryological zones and a more detailed 1:4,500,000 scale map with 14 terrain classifications based on elevation, temperature, and freeze-thaw depths. It also maps the locations of six specific cryogenic phenomena, derived from the National Atlas of Mongolia by Sodnom and Yanshin in 1990.
Great Lakes Ice Charts, Version 1 contains annotated chart images showing ice extent and concentration three times weekly during the ice season for all lakes except Ontario. The dataset spans 28 ice seasons from 1973/74 through 2001/2002 and was prepared by the National Weather Service Forecast Office and later the National Ice Center. Charts are available as GIF files and include insets for specific areas like the Straits of Mackinac.
Shraddha Jogi's dataset documents the reconstruction of the ACV biosynthesis pathway in Pichia pastoris. It includes LC–MS/MS confirmation of ACV production and transcriptomic analysis of the engineered strain. The data was last updated on 2026-05-18.