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.
519
datasets available to search
ShareScore release 0.9.0
Dataset results
519 results for “Optimisation”
Fig. 1 in An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images
Fig. 1 Comparison of malaria diagnosis using deep learning CNN models and deep learning object detectors. CNN, Convolutional neural network
Fig. 2 in An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images
Fig. 2 Cropping of infected cells using the coordinates of predictions by the object detectors. RBC, Red blood cell; YOLO,You Only Look Once (model)
Fig. 2 in Optimisation Of Dna Extraction And Rapd-Pcr Amplification For Population Genetic Analysis Of Daphnia Cucullata Sars, 1862 (Crustacea: Cladocera)
Fig. 2. RAPD fingerprints results from different samples of Daphnia cucullata with primers OPA-03 and OPA-05 (M- marker, 1-11 runners- different samples of Daphnia cucullata; 12- control) using RAPD-PCR 10 × Taq buffer with (NH4)2SO4.
Fig.1 in Optimisation Of Dna Extraction And Rapd-Pcr Amplification For Population Genetic Analysis Of Daphnia Cucullata Sars, 1862 (Crustacea: Cladocera)
Fig.1. RAPD fingerprints results from different samples of Daphnia cucullata with primers OPA-03 and OPA-05 (M- marker, 1-16 runners- different samples of Daphnia cucullata; 17- control) using RAPD-PCR 10 × Taq buffer with KCl.
Entice Optimisation Data for FlexiOPS Use Case
<p>The optimisation data for the project Entice shows the metrics gathered by FlexiOps in their use case. These measurements were taken in the Flexiant Cloud Orchestrator platform and shows how the Entice software optimises virtual machine images and reduces them considerably in size.</p>
ENTICE VM image analysis and optimised fragmentation frequently built images dataset
<p>As part of the evaluation of ENTICE VM image analysis and optimised fragmentation services we have implemented a simulation environment which analyses online software package repositories (e.g. ones offered by the maintainers of the Ubuntu and Debian Linux distributions) and deduces decomposition options as well as expected fragment sizes based on metadata acquired from these repositories. This dataset contains the collected recipes for several frequently built Ubuntu Linux based VMIs (e.g., LAMP, LAPP, LEMP, LLMP, LYME, MEAN/MERN, LTM, etc.) and the calculated fragments and their relations. The dataset is used to analyse and evaluate the behaviour of the fragmentation services. The dataset is in compressed LRZIP format.</p>
TROTS - The Radiotherapy Optimisation Test Set
<p>The Radiotherapy Optimisation Test Set (TROTS) is an extensive set of problems originating from radiotherapy (radiation therapy) treatment planning. This dataset is created for 2 purposes: (1) to supply a large-scale dense dataset to measure performance and quality of mathematical solvers, and (2) to supply a dataset to investigate the multi-criteria optimisation and decision-making nature of the radiotherapy problem. The dataset contains 120 problems (patients), divided over 6 different treatment protocols/tumour types. Each problem contains numerical data, a configuration for the optimisation problem, and data required to visualise and interpret the results. The data is stored as HDF5 compatible Matlab files, and includes scripts to work with the dataset.</p> <p> </p> <p>The set as present in this version is of date 13 May 2019. Updated versions of the Scripts and other extensions can be found at the following pages:</p> <p> </p> <p>Persistent page with links: <a href="https://hdl.handle.net/1765/116520">Erasmus University Rotterdam Library</a></p> <p>Mirror project page: <a href="http://www.sebastiaanbreedveld.nl/trots">TROTS Mirror</a></p> <p>Main publication: <a href="https://dx.doi.org/10.1016/j.dib.2017.03.037">S. Breedveld & B. Heijmen, Data for TROTS - The Radiotherapy Optimisation Test Set, Data in Brief 12 (2017) 143-149 </a></p>
Datasets to accompany "Evolutionary Dataset Optimisation: learning algorithm quality through evolution"
<p>This archive contains the datasets generated to accompany the work entitled "Evolutionary Dataset Optimisation: learning algorithm quality through evolution". The source code used to generate these datasets is archived <a href="https://doi.org/10.5281/zenodo.3492236">here</a>.</p> <p>Details on how to use this archive are given in the README.</p>
Data and code: Evaluation of the General Practice Pharmacist (GPP) intervention to optimise prescribing in Irish primary care: a non‐randomised pilot study
<p>This is a dataset and Stata analytical code relating to prescribing issues identified in the GPP pilot feasibility study. The paper reporting this study has been published as follows: </p> <p>Cardwell K, Smith SM, Clyne B on behalf of the General Practice Pharmacist (GPP) Study Group, et al. Evaluation of the General Practice Pharmacist (GPP) intervention to optimise prescribing in Irish primary care: a non-randomised pilot study. BMJ Open 2020;10:e035087. doi: 10.1136/bmjopen-2019-035087</p> <p>The abstract of the study is included below:</p> <p><strong>Objective:</strong> Limited evidence suggests integration of pharmacists into the general practice team could improve medicines management for patients, particularly those with multimorbidity and polypharmacy. This study aimed to develop and assess the feasibility of an intervention involving pharmacists, working within general practices, to optimise prescribing in Ireland.</p> <p><strong>Design:</strong> Non-randomised pilot study</p> <p><strong>Setting:</strong> Primary care in Ireland</p> <p><strong>Participants:</strong> Four general practices, purposively sampled and recruited to reflect a range of practice sizes and demographic profiles.</p> <p><strong>Intervention:</strong> A pharmacist joined the practice team for six months (10 hours/week) and undertook medication reviews (face-to-face or chart-based) for adult patients, provided prescribing advice, supported clinical audits, and facilitated practice-based education.</p> <p><strong>Outcome measures:</strong> Anonymised practice-level medication (e.g. medication changes) and cost data were collected. Patient-Reported Outcome Measure (PROM) data were collected on a subset of older adults (aged ≥65 years) with polypharmacy using patient questionnaires, before and six weeks after medication review by the pharmacist.</p> <p><strong>Results:</strong> Across four practices, 787 patients were identified as having 1,521 prescribing issues by the pharmacists. Issues relating to potentially inappropriate or high-risk prescribing were addressed most often by the prescriber (51.8%), compared to cost-related issues (7.5%). Medication changes made during the study equated to approximately €57,000 in cost savings assuming they persisted for 12 months. Ninety-six patients aged ≥65 years with polypharmacy were recruited from the four practices for PROM data collection and 64 (66.7%) were followed up. There were no changes in patients’ treatment burden or attitudes to deprescribing following medication review, and there were conflicting changes in patients' self-reported quality of life.</p> <p><strong>Conclusions:</strong> This non-randomised pilot study demonstrated that an intervention involving pharmacists, working within general practices is feasible to implement and has potential to improve prescribing quality. This study provides rationale to conduct a randomised controlled trial to evaluate the clinical and cost-effectiveness of this intervention.</p>
Tutorial Weather Data Cutouts for PyPSA-Eur: An Open Optimisation Model of the European Transmission System
<p><strong>PyPSA-Eur</strong> is an open model dataset of the European power system at the transmission network level that covers the full ENTSO-E area. It can be built using the code provided at <a href="https://github.com/PyPSA/PyPSA-eur">https://github.com/PyPSA/PyPSA-eur</a>.</p> <p><strong>It contains</strong> alternating current lines at and above 220 kV voltage level and all high voltage direct current lines, substations, an open database of conventional power plants, time series for electrical demand and variable renewable generator availability, and geographic potentials for the expansion of wind and solar power.</p> <p><strong>Not all data dependencies</strong> are shipped with the <a href="https://github.com/PyPSA/PyPSA-eur">code repository</a>, since git is not suited for handling large changing files. Instead we provide separate <strong>data bundles and cutouts</strong> to be downloaded and extracted as noted in the <a href="https://pypsa-eur.readthedocs.io/en/latest/installation.html">documentation</a>.</p> <p>The provided lightweight <strong>cutouts </strong>are spatiotemporal subsets of the German weather data from the <a href="https://software.ecmwf.int/wiki/display/CKB/ERA5+data+documentation">ECMWF ERA5</a> reanalysis dataset for March 2013 to be used for the <a href="https://pypsa-eur.readthedocs.io/en/latest/tutorial.html">PyPSA-Eur tutorial</a>. They have been prepared by and are for use with the <a href="https://github.com/PyPSA/atlite">atlite</a> tool (<a href="https://atlite.readthedocs.io/">https://atlite.readthedocs.io/</a>).</p> <p><strong>ECMWF ERA5</strong></p> <ul> <li><strong>Source: </strong><a href="https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=overview">https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=overview</a></li> <li><strong>Terms of Use: </strong><a href="https://cds.climate.copernicus.eu/api/v2/terms/static/20180314_Copernicus_License_V1.1.pdf">https://cds.climate.copernicus.eu/api/v2/terms/static/20180314_Copernicus_License_V1.1.pdf</a></li> </ul>
Raw data for "A Composite Bayesian Optimisation Framework for Material and Structural Design under Uncertainty"
<p>This dataset contains the raw data for the paper "A Composite Bayesian Optimisation Framework for Material and Structural Design under Uncertainty" (submitted) by R. P. Cardoso Coelho, A. F. Carvalho Alves, T. M. Nogueira Pires and F. M. Andrade Pires (INEGI and Faculty of Engineering of the University of Porto, Portugal).</p> <p> </p> <p>The data has been generated with the development branch of piglot - an open-source optimisation toolbox (https://github.com/CM2S/piglot). The numerical simulations have been conducted with both an in-house finite element solver (Links) and with the open-source SCA implementation CRATE (https://github.com/bessagroup/CRATE).</p>
Fig. 2 Optimisation o in Exploring the evolution and terrestrialization of scorpions (Arachnida: Scorpiones) with rocks and clocks
Fig. 2 Optimisation o_ book lung origin(s) on competing phylogenies o_ Chelicerata. a Scorpions as the sister group to other Arachnida (e.g. Weygoldt and Paulus 1979), implying either book lung loss in other Arachnida or book lung convergence between scorpions and tetrapulmonates. b Scorpions as sister group to Eurypterida (e.g. Dunlop and Braddy 2001), implying book lung convergence and
Code and data archive to accompany "A derivative-free optimisation method for global ocean biogeochemical models", Oliver et. al. 2021
<p>This archive is to accompany the article:</p> <p>A derivative-free optimisation method for global ocean biogeochemical models,<br> Sophy Oliver, Coralia Cartis, Iris Kriest, Simon Tett, and Samar Khatiwala.</p> <p>The optimisation framework used in this study can be found here: https://doi.org/10.5281/zenodo.5517610</p> <p>The original source code of MOPS were from the Supplement of Kriest et al. (2017).<br> The most recent TMM source code is available at https://github.com/samarkhatiwala/tmm.</p> <p>In this archive:</p> <p>Supplement/Configurations/OxfordMOPS_Configs contains:<br> - ReadOnlyFiles (Files and Code specifically used to run the global ocean biogeochemical model MOPS model with<br> the Transport Matrix Method, which have been edited to differ from the versions downloaded from the sources above.)<br> - RunCode (runscripts to run the MOPS model with the TMM)<br> - TWIN_Configs (JSON files required by each optimisation experiment carried out).</p> <p>Supplement/OxfordMOPS_EXP contains data for each iteration of all optimisation experiments carried out.</p> <p>Supplement/OPTCLIMSO_PlottingScripts contains MATLAB plotting scripts used to create results figures of these experiments.</p>
PyPSA-Eur: An Open Optimisation Model of the European Transmission System (Dataset)
<p><strong>PyPSA-Eur</strong> is an open model dataset of the European power system at the transmission network level that covers the full ENTSO-E area. The software pipeline to assemble the model is developed at <a href="https://github.com/PyPSA/PyPSA-eur">https://github.com/PyPSA/PyPSA-eur</a> and documentation is available at <a href="http://pypsa-eur.readthedocs.io">pypsa-eur.readthedocs.io.</a></p> <p><strong>This repository provides pre-built PyPSA networks resulting from corresponding PyPSA-Eur Releases using the default configuration!</strong></p> <p>The model alternating current lines at and above 220 kV voltage level and all high voltage direct current lines, substations, an open database of conventional power plants, time series for electrical demand and variable renewable generator availability, and geographic potentials for the expansion of wind and solar power.</p> <p>It only includes freely available and open data. It provides a fully automated free software pipeline to assemble the load-flow-ready model from the original datasets, which enables easy configuration, replacement and<br> improvement of the individual parts.</p> <p>The model is suitable both for operational studies and generation and transmission expansion planning studies.</p> <p>Some basic validation is provided in a paper describing the dataset:</p> <ul> <li>Jonas Hörsch, Fabian Hofmann, David Schlachtberger, and Tom Brown. PyPSA-Eur: An open optimisation model of the European transmission system. Energy Strategy Reviews, 22:207-215, 2018. <a href="https://arxiv.org/abs/1806.01613">https://arxiv.org/abs/1806.01613</a>, <a href="http://https://doi.org/10.1016/j.esr.2018.08.012">https://doi.org/10.1016/j.esr.2018.08.012</a>.</li> </ul>
GIS Data for Optimising Vaccination Center Placement in Flanders and Brussels
<p>This dataset collection contains geospatial data that was used in a study on optimising vaccination center placement in Flanders and Brussels Capital Region (Belgium). The collection includes five raster datasets, a road network dataset in vector format, and datasets of potential vaccination facilities in vector format.</p> <p>The raster datasets provide information on population density, mean age, proximity to the nearest N-road, travel time to the nearest hospital, and node value of collective transport. These datasets cover the region of Flanders and the Brussels Capital Region, and have been normalised on a scale of 0 to 1. The population density data was sourced from Statbel [1], while the road network and the hospital locations were queried from OpenStreetMap [2]. The node value of collective transport dataset was obtained from a study by Verachtert et al. [3].</p> <p>The road network dataset is a multilinestring vector dataset that includes all of the roads in Belgium. This dataset can be used to analyse traffic flow and identify optimal locations for vaccine centers. The two point vector datasets contain the locations of potential vaccination facilities within the province of Antwerp, with one dataset including 14 facilities and the other including 7 facilities. These datasets can be used to evaluate the effectiveness of different vaccine center placement strategies.</p> <p>The geospatial data in this collection is stored in GeoJSON format for the road network and the potential vaccination facilities and GeoTIFF format for the raster datasets and can be accessed and analyzed using a variety of geospatial tools and software.</p>
Case study for Sustainable agri-food supply chain planning through multi-objective optimisation
<p>Case study used to solve the multi-objective model proposed in: Sustainable agri-food supply chain planning through multi-objective optimisation</p>
Datasets and codes for De Lorm et al. 2023: Optimising the automated recognition of individual animals to support population monitoring
<p>Reliable estimates of population size and demographic rates are central to assessing the status of threatened species. However, obtaining individual-based demographic rates requires long-term data, which is often costly and difficult to collect. Photographic data offer an inexpensive, non-invasive method for individual-based monitoring of species with unique markings, and could therefore increase available demographic data for many species. However, selecting suitable images and identifying individuals from photographic catalogues is prohibitively time-consuming. Automated identification software can significantly speed up this process. Nevertheless, automated methods for selecting suitable images are lacking, as are studies comparing the performance of the most prominent identification software packages.</p> <p> </p> <p>In this study, we develop a framework that automatically selects images suitable for individual identification, and compare the performance of three commonly used identification software packages; Hotspotter, I<sup>3</sup>S-Pattern, and WildID. As a case study, we consider the African wild dog <em>Lycaon pictus</em>, a species whose conservation is limited by a lack of cost-effective large-scale monitoring. To evaluate intra-specific variation in the performance of software packages, we compare identification accuracy between two populations (in Kenya and Zimbabwe) that have markedly different coat colouration patterns. </p> <p> </p> <p>The process of selecting suitable images was automated using Convolutional Neural Nets that crop individuals from images, filter out unsuitable images, separate left and right flanks, and remove image backgrounds. Hotspotter had the highest image-matching accuracy for both populations. However, the accuracy was significantly lower for the Kenyan population (62%), compared to the Zimbabwean population (88%). </p> <p> </p> <p>Our automated image pre-processing has immediate application for expanding monitoring based on image-matching. However, the difference in accuracy between populations highlights that population-specific detection rates are likely and may influence certainty in derived statistics. For species such as the African wild dog, where monitoring is both challenging and expensive, automated individual recognition could greatly expand and expedite conservation efforts. </p>
Learning to Do or Learning While Doing: Reinforcement Learning and Bayesian Optimisation for Online Continuous Tuning
<p>Dataset of optimisation runs performed for a study comparing reinforcement learning and Bayesian optimisation for online continuous tuning at the example of a linear particle accelerator tuning task.</p> <p> </p> <p><strong>Abstract of the Paper on the Study</strong></p> <p>Online tuning of real-world plants is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods, such as Reinforcement Learning-trained Optimisation (RLO) and Bayesian optimisation (BO), hold great promise for achieving outstanding plant performance and reducing tuning times. Which algorithm to choose in different scenarios, however, remains an open question. Here we present a comparative study at the example of a routine task on a real particle accelerator, showing that RLO generally outperforms BO, but is not always the best choice. Based on the study’s results, we provide a clear set of criteria to guide the choice of algorithm for a given tuning task. These can ease the adoption of learning-based autonomous tuning solutions to the operation of complex real-world plants, ultimately improving the availability and pushing the limits of operability of these facilities, thereby enabling scientific and engineering<br> advancements.</p>
Machine Learning-based Energy Optimisation in Smart City Internet of Things
<p>Dataset for the paper Machine Learning-based Energy Optimisation in Smart City Internet of Things accepted for publication at The First International Workshop on the Integration between Distributed Machine Learning and the Internet of Things, ACM MobiHoc 2023.</p> <p>The dataset is collected from a real-world deployment of environmental sensors in the city of Bern, Switzerland. Our proposed approach can be applied to determine the tradeoff between the accuracy of temperature measurements and reducing the energy consumption for a single sensor; hence, without loss of generality, the evaluation is conducted on a dataset from a single sensor. Overall, we acquired 3697 measurements, each long 138 seconds. To correct the measurements, we set the maximum ventilation duration of 138 seconds, during which the multivariate time series of humidity and temperature sensor values are recorded together with their corresponding timestamps. The sensor values are recorded at a fixed frequency.</p> <p>From this raw data, we created the training and test sets through data augmentation to simulate time series of different lengths. Namely, for each measurement, we generated 136 samples with the increasing length of measurement time-series, padding the residual time-series length with zeros until reaching a time-series length of 137.</p> <p>We released the source code and trained models on the following GitHub repository https://www.github.com/ricsamikwa/ml-iot-smartcitytemp</p>
Data and codes: Who is calling? Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers
<p>Data and codes that accompany the article titled "Who is calling? Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers".</p>
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.