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.
44
datasets available to search
ShareScore release 0.9.0
Dataset results
44 results for “predictive power”
Shifts Marine Cargo Vessel Power Consumption Prediction Dataset
<p>This archive contains the data for the Shifts Benchmark on cargo vessel power consumption prediction. This dataset is provided by the Shifts Project to enable assessment of the robustness of models to distributional shift and the quality of their uncertainty estimates. A full description of the benchmark is available in https://arxiv.org/pdf/2206.15407. To find out more about the Shifts Project, please visit https://shifts.ai . </p> <p> </p> <p> </p>
Data from: Exploiting nozzle geometry to predict resolution in extrusion-based bioprinting: mathematical modelling of a power-law fluid
Open the record for dataset details and reuse information.
Data corresponding to the publication "The limited predictive power of the Pauling Rules"
<p>This is the data set corrresponding to the publication "The limited predictive power of the Pauling rules" (see https://onlinelibrary.wiley.com/doi/full/10.1002/anie.202000829). This data can be reproduced with the following code: https://doi.org/10.5281/zenodo.3654428.</p>
Wind farm power short-term prediction using WRF model and Kalman filtering
<p>This repository contains the data used and generated in the paper:</p> <p>Mamani, R., & Hendrick, P. (2019). Wind farm power short-term prediction using WRF model and Kalman filtering. ECOS 2019</p>
Dynamic inferential NOx emission prediction model with delay estimation for SCR de-NOx process in coal-fired power plants
<p><span><span>The selective catalytic reduction (SCR) de</span><span>-</span><span>NO<sub>x</sub> </span><span>process in coal-fired power plants not only displays nonlinearity, large inertia, and time variation but also a lag in NO<sub>x</sub> analysis; </span><span>hence,</span><span> it is difficult to obtain an accurate model </span><span>that </span><span>can be used to control NH<sub>3</sub> injection </span><span>during changes in the </span><span>operating state. </span><span>In this work,</span><span> a novel dynamic inferential model with delay estimation was proposed for NO<sub>x</sub> emission prediction. First, k-nearest neighbour mutual information (knnMI) was used to estimate the time-delay of the descriptor variables, followed by reconstruction of the phase space of the model data. Second, multi-scale wavelet kernel partial least square (mwKPLS) was</span><span> used</span><span> to improve the prediction ability, </span><span>and this was followed by verification using </span><span>benchmark dataset experiments. Finally, the delay-time difference (DTD) method and feedback correction strategy </span><span>were </span><span>proposed to deal with the time variation of the SCR de</span><span>-</span><span>NO<sub>x</sub> process.</span> <span>Through the analysis of the </span><span>experimental field data </span><span>in the</span> <span>steady state, </span><span>the variable</span><span> state and </span><span>the </span>NO<sub>x</sub> analyser blowback process<span>, the results proved that</span><span> this dynamic model has </span><span>high prediction accuracy</span><span> during</span><span> state changes and can </span><span>realize</span><span> advance prediction of the NO<sub>x</sub> emission. </span></span></p>
Data from "Spontaneous alpha power lateralization predicts detection performance in an un-cued signal detection task", PlosOne2016
<p>32-channel(+6) data (Biosemi Active two, 10-20, 2048Hz) unfiltered from the 2016 Plos ONE paper "Spontaneous alpha power lateralization predicts detection performance in an un-cued signal detection task"</p>
Predicting Performance and Power Consumption of Parallel Applications
<p><em><strong>Abstract: </strong>Current architectures provide many control knobs for the reduction of power consumption of applications, like reducing the number of used cores or scaling down their frequency. However, choosing the right values for these knobs in order to satisfy requirements on performance and/or power consumption is a complex task and trying all the possible combinations of these values is an unfeasible solution since it would require too much time. For this reasons, there is the need for techniques that allow an accurate estimation of the performance and power consumption of an application when a specific configuration of the control knobs values is used. Usually, this is done by executing the application with different configurations and by using these information to predict its behaviour when the values of the knobs are changed. However, since this is a time consuming process, we would like to execute the application in the fewest number of configurations possible. In this work, we consider as control knobs the number of cores used by the application and the frequency of these cores. We show that on most Parsec benchmark programs, by executing the application in 1% of the total possible configurations and by applying a multiple linear regression model we are able to achieve an average accuracy of 96% in predicting its execution time and power consumption in all the other possible knobs combinations.</em></p> <p>This dataset includes the raw data of the experiments as well as the scripts used to plot them.</p>
Artifact of the paper: Scheduling with lightweight predictions in power-constrained HPC platforms
<p>Please refer to the <a href="https://zenodo.org/records/13961003/files/artifact-overview.pdf?download=1&preview=1">artifact-overview.pdf</a> file in this dataset for instructions to reproduce the experiments we have conducted for this article, or for more context about the article.</p>
Monitoring of postpartum body condition at the cow and herd levels: assessing explanatory and predictive power of disease risk models
<p>Objectives</p> <p>1- To define the herd threshold for cows with poor body condition based on its predictive capacity for disease risk at the herd level, and</p> <p>2- to estimate the impact measures on disease rates due to body condition indicators in transition period.</p> <p>Two commercial grazing dairy herds (Herd A=5.034 and herd B=7.965 lactations) from Argentinean Pampa region were used to perform a longitudinal retrospective study during a 4-year period (2014 –2017).Health, reproductive and body condition score (BCS) records were gathered. The BCS (5-point scale) was performed at calving and at the time of reproductive release. The difference between both measures of BCS was used to assess the body condition loss (∆BCS). All the cows not bred by 70 DIM were checked for anestrus.Calving cohorts of 21-day were defined at each herd and parity group through the entire study period. The frequency of cows with BCS<3 or ∆BC>-0.5 at each cohort were calculated and used to define quartiles through whole study period. Quartiles were used, one at a time, as threshold to dichotomize the cohorts to predict the risk that a cohort has a frequency of anestrus over the median.The higher AUC was used as selection criterium to determine the herd level threshold at each HERD and PARITY level. The population attributable fraction (AFP) of anestrus rate to body condition indicators at each cohort was calculated, for every HERD and PARITY level. </p>
AI-Powered Fall Risk Prediction in Nursing Care
ClinicalTrials.gov study NCT07000981. IPD Sharing: NO. Countries: 1. Publications: 2.
Data from: Powerful yet challenging: Mechanistic Niche Models for predicting invasive species potential distribution under climate change
Open the record for dataset details and reuse information.
Dynamic inferential NOx emission prediction model with delay estimation for SCR de-NOx process in coal-fired power plants
Open the record for dataset details and reuse information.
Data from: Predictive mapping of the global power system using open data
<p>Three primary global data outputs from the research:</p> <ul> <li><strong>grid.gpkg:</strong> Vectorized predicted distribution and transmission line network, with existing OpenStreetMap lines tagged in the 'source' column</li> <li><strong>targets.tif:</strong> Binary raster showing locations predicted to be connected to distribution grid. </li> <li><strong>lv.tif:</strong> Raster of predicted low-voltage infrastructure in kilometres per cell.</li> </ul> <p>This data was created with code in the following three repositories:</p> <ul> <li>https://github.com/carderne/gridfinder</li> <li>https://github.com/carderne/predictive-mapping-global-power</li> <li>https://github.com/carderne/access-estimator</li> </ul> <p>Full steps to reproduce are contained in this file:</p> <ul> <li>https://github.com/carderne/predictive-mapping-global-power/blob/master/README.md</li> </ul> <p>The data can be visualized at the following location:</p> <ul> <li>https://gridfinder.org</li> </ul>
Data from: Peak vertical jump power predicts radial bone strength better than hand grip strength in healthy individuals
<p>Osteoporosis is considered a pediatric disease with geriatric consequences. However, measuring bone strength in children is complex and creates a practical problem for health professionals, teachers and parents. A non-invasive measure of muscle fitness that correlates to bone strength may provide a means to monitor bone strength throughout the lifespan. Therefore, the purpose of this study was to investigate the relationship between common muscle function tests (relative grip strength (RGS), peak vertical jump power (PP)) and bone strength in the radial diaphysis and epiphysis of a healthy population. Healthy participants (n=147 (81 female)) performed a bilateral grip strength test using a hand dynamometer, and a maximal vertical jump test. Peak vertical jump power was calculated from maximal jump height using the Sayer's equation. Moment of inertia (MoI), cortical area (CoA), cortical bone mineral density (cBMD), and polar strength-strain index (SSIp) were measured using peripheral Quantitative Computed Tomography (pQCT) to determine bone strength parameters at the 66% radial site (predominantly cortical bone). At the 4% site (trabecular bone site), bone mineral content (vBMC.tb), bone mineral density (vBMD.tb), total area (ToA.tb) and bone strength index (BSIc) were measured. Hierarchical multiple regression analyses determined the relationship of each muscle function test for each bone envelope (cortical and trabecular). For the cortical bone measurements:<b> </b>RGS, and PP were both significantly correlated with CoA, MoI, and SSIp. Peak vertical jump power predicted bone strength parameters to a greater extent compared to RGS. For the trabecular bone envelope, RGS was not a predictor of bone strength however peak power was a significant predictor of bone strength parameters. Peak vertical jump power was a significant predictor of bone strength at both trabecular and cortical radial sites. Interestingly PP, a lower limb measurement explained the most variance in the bone strength of the upper limb.</p>
Unlocking the Predictive Power of Quantum-Inspired Representations for Intermolecular Properties in Machine Learning
<p>Dataset associated with the manuscript entitled "Unlocking the Predictive Power of Quantum-Inspired Representations for Intermolecular Properties in Machine Learning". </p> <p>See Readme file (markdown format) for details on how the data is structured in the "database" file.</p>
Prediction-Powered Inference: Data Sets
<p>Data sets used in the paper "Prediction-Powered Inference."</p>
Predictive Power of Share Wave Fibro Scan in HCC After HCV Infection
ClinicalTrials.gov study NCT05105828. IPD Sharing: Not stated. Countries: 1. Publications: 4.
Recurrent Predictive Power of Circulating Tumor Cells for Non Small Cell Lung Cancer Patients
ClinicalTrials.gov study NCT03721133. IPD Sharing: Not stated. Countries: 1. Publications: 23.
Observational Study to Assess Oxygen Saturation Predictive Power Related to Intradialytic Acute Hypotension
ClinicalTrials.gov study NCT01759641. IPD Sharing: Not stated. Countries: 1. Publications: 3.
Data from: Peak vertical jump power predicts radial bone strength better than hand grip strength in healthy individuals
Open the record for dataset details and reuse information.
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.