Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
14,079 datasets
93.6% multiclass diagnosis accuracy was achieved by a proposed model using this benchmark data. The dataset describes fault types for the Tennessee Eastman Process, a standard benchmark for industrial fault detection and diagnosis. It was authored by Babar Hayat and last updated on June 2, 2026.
93.6% multiclass diagnosis accuracy and a 94.0% F1 score were achieved by the proposed SAU-PGA-CNN-BiLSTM model on the Tennessee Eastman Process benchmark. The dataset, authored by Babar Hayat and last updated in June 2026, contains ablation performance results for a sensor-aware deep learning framework designed for industrial fault detection and diagnosis.
Ten parametric models investigate the tensile performance of square concrete-filled steel tubular members. The dataset includes results from finite element simulations validated against six experimental specimens, with code comparisons and machine learning predictions. It was authored by Hongtao Zhang and last updated on June 1, 2026.
A 2026 study by Hongtao Zhang presents a finite element model and parametric analysis of square concrete-filled steel tubular members under axial tension. The dataset includes results from six experimental specimens and ten parametric models, analyzing the effects of confinement coefficient and slenderness ratio on tensile load capacity. It also contains results from code comparisons and machine learning predictions using GAN-augmented data.
Six experimental specimens and ten parametric models form the basis for analyzing square concrete-filled steel tubular members under axial tension. A Generative Adversarial Network (GAN) was used to augment the data, improving predictive model accuracy on an augmented test set. The dataset, created by Hongtao Zhang and last updated in June 2026, includes finite element simulation results, parametric analyses, and machine learning predictions.
Six experimental specimens and ten parametric models of square concrete-filled steel tubular members under axial tension form the basis of this dataset. The parametric analysis shows maximum load rising from 182 kN to 895 kN as the confinement coefficient increases from 0 to 0.99. Author Hongtao Zhang published the data on figshare in 2026, which includes results from finite element simulations, code comparisons, and machine learning predictions using a WGAN-GP data augmentation method.
DPEA-Net, a lightweight 3D CNN, achieved mean Dice scores of 90.43%/89.96% for whole tumor, 85.56%/86.52% for tumor core, and 81.89%/80.31% for enhancing tumor on BraTS validation sets. The model, proposed by Caijian Hua, uses a computationally efficient architecture requiring only 17.48 GFLOPs. The results are documented in a PDF file last updated on 2026-05-25.
Emma Gairin's dataset accompanies a 2026 study on temperature's role in thyroid hormone-driven fish metamorphosis. It includes normalised and transformed gene expression data for the Amphiprion ocellaris clownfish, along with gene lists and clustering outputs. The repository is 211.0 MB and was last updated on 2026-05-22.
Monthly and three-monthly water quality measurements from nine Australian coastal sites, with sampling beginning between September 2008 and November 2010. The dataset includes Total Suspended Solids and Secchi Depth data, collected by the Integrated Marine Observing Systems (IMOS) National Mooring Network. Sampling is ongoing at seven sites, having ceased at Ningaloo and Esperance in August/September 2013.
Monthly reported data on civilian staff members working in the United Nations Peace and Security Pillar. The dataset includes staffing levels, level groups, gender, and total staff by duty station, categorized into Professional, General Service, Field Service, and National Professional Officer roles. It is provided by the United Nations Peace and Security Data Hub under a CC-BY-3.0-IGO license.
93 older adults aged 60-89 wore thigh-mounted accelerometers for seven days to measure engagement in sedentary behavior, standing, and physical activity. The dataset includes fasting blood measurements for glucose, triglycerides, cholesterol, HbA1c, LPL, IL-6, and PIIINP, analyzed via isotemporal substitution models. It was authored by Declan Ryan and last updated on 2026-05-28.
Nine Australian coastal stations have collected phytoplankton pigment composition data from water column samples since 2008. Sampling began between September 2008 and November 2010 and is currently ongoing for seven sites, with two sites ceasing in 2013. The Integrated Marine Observing System (IMOS) manages this dataset, which includes historical data from CSIRO's Coastal Monitoring program dating back to 1944 for three locations.
Monthly and three-monthly sampling began between September 2008 and November 2010 and is ongoing for seven of nine Australian coastal stations, with sampling at two sites ceasing in 2013. The dataset contains picoplankton component data analyzed by flow cytometry from the Integrated Marine Observing System's National Reference Station network. Data storage and access is planned to be interoperable with other national and international programs through IMOS Infrastructure.
Integrated Marine Observing Systems (IMOS) data includes salinity, carbon, alkalinity, oxygen, and nutrient levels from water samples collected at nine National Reference Station sites around Australia. Sampling began between September 2008 and November 2010 and is ongoing for seven sites, with monthly collection from small vessels. The dataset incorporates historical coastal monitoring data from CSIRO for three sites, with records dating back to 1944.
Raw and segmented micro-CT scans of Theopropus elegans heads across developmental stages, supporting a manuscript submitted to Proceedings of the Royal Society B. The 8.0 GB dataset includes measured data on eye morphology, ommatidial number, facet size, and spatial acuity in Excel format. Scans were conducted using a ZEISS Versa 620 XRM system and measurements were taken in 3D Slicer.
Data Sheet 1_Instability resistance training in collegiate basketball: a multitheoretical experimental study.xlsx contains the results of an 8-week training intervention study. The dataset, authored by Hengyu Li and last updated in May 2026, compares outcomes for 60 college basketball players split into instability resistance training and traditional strength training groups. It includes measures of static and dynamic balance, core muscle activation, and shooting performance.
A series of halobenzonitrile–carbazoles demonstrates efficient persistent room-temperature phosphorescence with a quantum yield of up to 22% and an excited state lifetime of up to 0.22 seconds. Compounds from laboratory-synthesized carbazole exhibit thermally activated delayed fluorescence with millisecond-range lifetimes. Alexander C. Brannan published this research on figshare in June 2026.
A dataset from a study on metal-free organic phosphors for persistent room-temperature phosphorescence. It likely contains photophysical property data for a series of halobenzonitrile–carbazole compounds, including quantum yields and excited state lifetimes. The dataset was authored by Alexander C. Brannan and last updated on figshare in June 2026.
A 342.8 KB PDF authored by Pascal Benschop, last updated on 2026-06-03, describes a study on action recognition using motion-focused representations. The work evaluates motion-history images and optical flow on datasets including HMDB-51 and UCF-101 to reduce identifiable appearance cues while retaining action recognition accuracy.
Leaf area index (LAI) measurements from the Kataba Local Forest in Zambia, collected to validate satellite products. The dataset contains monthly ground-based sensor readings taken along three transects from 2000 into 2002 to capture seasonal phenology. It was produced by NASA as part of the SAFARI 2000 and EOS Validation Core Site programs.