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.
61
datasets available to search
ShareScore release 0.9.0
Dataset results
61 results for “learning strategies”
Navigating deep learning strategies for large-area land cover mapping using very-high-resolution imagery in Senegal: Validation Data
<p><span><span>R</span><span>apid</span><span> advances in deep learning</span><span> for</span> <span>land cover </span><span>classification of </span><span>trees, shrubs and </span><span>very small</span> <span>agricultur</span><span>al</span> <span>fields</span> <span>using</span> <span>very high</span><span>-</span><span>resolution satellite </span><span>data </span><span>(< 2 m</span><span>)</span><span>,</span><span> has tremendous potential</span> <span>for resolving </span><span>current</span><span> challenges </span><span>in </span><span>quantifying</span> <span>land cover </span><span>change </span><span>in</span> <span>sub-</span><span>Saharan</span> <span>African (SSA</span><span>)</span><span>,</span> <span>due to</span> <span>growing </span><span>demand for food resources</span><span>.</span> <span>We</span> <span>conducted experiments </span><span>with</span><span> different training strategies for scaling up </span><span>UNet</span> <span>convolutional neural network </span><span>models for regional land cover mapping with multispectral </span><span>WorldView</span><span> (WV</span><span>)</span><span>-2 and –3,</span><span> imagery</span><span> in</span><span> three distinct regions of Senegal </span><span>which</span> <span>has</span><span> complex </span><span>seasonal wet/dry conditions and </span><span>cropland-savanna mosaics. </span></span></p> <p>The validation exercise of this research consisted in validating more than 70,000 km<sup>2</sup> across Senegal. The infrastructure was setup in the NASA SMCE system with a total of twelve George Mason University (GMU) students participating as operators. These operators validated more than 59 WV-2 and -3 images, each consisting of 200 stratified points in 5,000 x 5,000-pixel images. This effort resulted in a total of ~35,000 aggregated observations that are available through the eo-validation API for public consumption. Each validation point from this dataset has three individual observations.</p>
Hackathons as a Pedagogical Strategy to Engage Students to Learn and to Adopt Software Engineering Practices
<p>Teaching Software Engineering is not a trivial duty since several pedagogical strategies can be used and sometimes the impact of these on students is uncertain. Hackathons are similar to marathons, however used to produce solutions to solve a specific problem in a short period of time and based on intense collaboration. Educational hackathons aim to promote learning in such an environment. The Undergraduate computing programs of PUCRS decided to use a hackathon as a pedagogical strategy aiming to motivate the students to practice the adoption of software development practices and to work in groups as a means to practice the development of social skills. Therefore, we conducted a case study to investigate: 1) The motivations to students to attend or not attend an educational hackathon, 2) The students perceptions about this hackathon, 3) The Software Engineering practices adopted by students. In this study, we identified factors that may affect students motivation to participate (e.g., improve the teamwork skills), some students expectations about the hackathon (e.g., work in teams), and the practices adopted by the students (e.g., pair programming). Some of our findings include that students enjoy participating in an informal educational environment (e.g., hackathons) to improve their technical skills and to build network with some colleagues. This study can provide insights to teachers that wants to organize some activity than traditional teaching and the students perspective about this kind of strategy.</p>
Video-based learning of coping strategies for common errors improves laparoscopy training - a randomized study
<p>Instructional video material from the doctoral thesis "Introducing a coping role model to increase the learning efficiency in learning laparoscopic knot tying - a randomised controlled trial" by Ms Annabelle Gerhäuser at Heidelberg University, Medical School.</p> <p>Developing the skills needed to perform minimally invasive procedures requires intensive training of trainee surgeons. Laparoscopic knot tying is a particularly challenging technique. Subjects of the study learned this technique with the help of instructional videos developed specifically for this purpose. These "coping videos" show typical mistakes made by beginners and the corresponding solution strategies. They have been validated before use in the above-mentioned study.</p> <p>Coping Video 1 - Needle Load</p> <p>Coping Video 2 - Handling & Tissue</p> <p>Coping Video 3 - Tail length</p> <p>Coping Video 4 - Difficulties in knot tying</p> <p>Coping Video 5 - Lift & drift</p> <p> </p>
Global perspectives on sand dune patterns: Scale-adaptable classification using Landsat imagery and deep learning strategies
<p><span>Here we generated the global sand dune pattern map at a resolution of 30 m, named GSDP30. The GSDP30 map encompasses 11 types of sand dune patterns (SDPs): simple crescentic dunes, compound-complex crescentic dunes, simple linear dunes, compound-complex linear dunes, dome dunes, star dunes, parabolic dunes, dendritic dunes, network dunes, sand sheets, and others. The map is divided into 331 Tiff tiles, each characterized by a size of 15,360 × 15,360 pixels and named according to the longitude and latitude coordinates of its upper-left corner.</span></p>
Computational Chromatography: A Machine Learning Strategy for Demixing Individual Chemical Components in Complex Mixtures
<p>This repository contains data for "Computational Chromatography: A Machine Learning Strategy for Demixing Individual Chemical Components in Complex Mixtures". </p>
Digging for Decision Trees: A Case Study in Strategy Sampling and Learning (experimental reproduction package)
<p>This artifact permits to reproduce the experimental results obtained with the techniques and algorithms presented in the article "Digging for Decision Trees: A Case Study in Strategy Sampling and Learning" by Carlos E. Budde, Pedro R. D'Argenio, and Arnd Hartmanns (2024).</p> <p>The contents include all data and software (formal models, software tools, Python & bash scripts) used in the experimental evaluation presented in §7 of the article. Detailed instructions on how to reproduce the results are bundled in the artifact. Execution has been tested in the Virtual Machine available at https://zenodo.org/records/7113223.</p> <p> </p>
Slow practice and tempo management strategies in instrumental music learning: Investigating prevalence and cognitive functions
<p>This dataset corresponds to the publication of the same title and the following DOI: <a href="https://doi.org/10.1177%2F03057356211073481">https://doi.org/10.1177/03057356211073481</a></p> <p>The dataset contains 3 excel files. The file named QuantiativeSurveyDataClean_withKey contains all collected, unprocessed, cleaned data variables from the quantitative questionnaire. This includes all variables used for the principle components analysis. The file named ANOVA_data contains the variables used for the ANOVA analyses, and the file named regression_data contains the variables used for the regressions analyses. In all three files, descriptions of the variables can be found in the sheet titled "key", and the data can be found in the sheet titled "data".</p>
Supplementary File S2 for the publication 'Predicting Bacterial Virulence Factors - Evaluation of Machine Learning and Negative Data Strategies' by Rentzsch, R et al.
<p>Supplementary File S2 for the publication 'Predicting Bacterial Virulence Factors - Evaluation of Machine Learning and Negative Data Strategies' by Robert Rentzsch, Carlus Deneke, Andreas Nitsche, and Bernhard Y. Renard</p>
Apple orchard production estimation using deep learning strategies: a comparison of tracking-by-detection algorithms - CaseStudy
<p>The dataset "Case Study" consists of image sequences (videos) for apple detection and tracking and its corresponding ground truth. The ground truth is presented in MOT format. This dataset is part of the paper:</p> <p>Villacrés, J., Viscaino, M., Delpiano, J., Vougioukas, S. & Cheein, F. A. (2022). Apple orchard production estimation using deep learning strategies: a comparison of tracking-by-detection algorithms. <em>Computers and Electronics in Agriculture</em>.</p> <p>The article is currently accepted. For a better reference format, please refer to the journal's official website.</p> <p>If you have used the material presented in this data set, please cite the previous article.</p> <p>For more information regarding the dataset, please refer to the paper mentioned below.</p>
Grammar learning strategies: Hungary & Poland: Pawlak & Csizér (2022)
<p>Dataset for the study investigating the use of grammar learning strategies by Polish and Hungarian university students majoring in English.</p>
Strategy-based motor learning decreases the post-movement β power
<p>This publication contains the following data, in connection with the manuscript entitled <em>"Strategy-based motor learning decreases the post-movement </em><em>β</em><em> power"</em>, by <em>Korka et al. (2023)</em>:</p> <p>1- raw EEG and kinematics data files (for these, please see Version 1);</p> <p>2 - task and stimulation files;</p> <p>3 - analysis files.</p> <p><strong>Task and stimulation files</strong>:</p> <p>- 2 experimental file formats, each corresponding to one condition: .exp</p> <p>- each .exp file calls on different scenarios (.sce) files:</p> <ul> <li>“train1” and “train2” correspond to task instructions regarding the experimental set-up and the general task (please see instructions in the <em>Supplementary Material</em> associated with the paper).</li> <li>“COMPENSATE_DEMO” and “IGNORE_DEMO” correspond to demonstrating the rotation in each condition; the rotation is constantly switched on for the duration of these training blocks.</li> <li>“COMPENSATE_TRAIN” and “IGNORE_TRAIN” correspond to training for the actual experiment including a probabilistic rotation (i.e., same as in the experimental blocks, but fewer trials).</li> <li>Finally, “COMPENSATE” and “IGNORE” scenarios represent the actual experimental blocks for each condition.</li> </ul> <p><strong>Analysis files</strong></p> <p>-main analysis files:</p> <ul> <li>ecEEG_kinematics – processes the relevant kinematics parameters by reading in the raw kinematics datafiles.</li> <li>ecEEG_eeg_preproc – reads in and preprocesses EEG raw data files; main steps steps include: filtering, segmenting the data into epochs (and matching each epoch with the kinematics data storing movement parameters), rejection of epochs containing artifacts based on visual inspection, rejection of channels containing extreme amplitudes, Independent Component Analysis (ICA) for detecting eye- and muscle-related artifacts, interpolation of channels, automated trial rejection after ICA.</li> <li>ecEEG_eeg_freq and ecEEG_eeg_freq_baseline – computes time-frequency analyses for the PMBR data and baseline (inter-trial-interval) data, respectively + re-references data to a common average.</li> <li>ecEEG_eeg_freq_2 – excludes marked trials based on task performance, kinematics parameters, and EEG rejection criteria + organizes the data from all participants into a unique structure (for PMBR and ITI data, in turn).</li> <li>ecEEG_change_plots – produces the EEG figures displayed in the manuscript + exports data for statistics.</li> </ul> <p>- auxiliary analysis files:</p> <ul> <li>ecEEG_ica – if called on, computes the ICA</li> <li>VMB_neighbours – defines neighbors for each channel, which are necessary for interpolation</li> <li>ecEEG_trialreject – automated trial rejection based on kurtosis</li> <li>topoplotbasic_ml2012_varchans – called on for creating the topographic plots when visualizing the ICA components</li> <li>ecEEG_eeg_trial_rej_15thresh – used to determine the number of trials in which participants did not follow the task instructions (see manuscript for details)</li> </ul>
Developing and Testing an Implementation Strategy for Active Learning to Promote Physical Activity in Children
ClinicalTrials.gov study NCT05048433. IPD Sharing: NO. Countries: 1. Publications: 2.
Merging computational fluid dynamics and machine learning to reveal animal migration strategies
Open the record for dataset details and reuse information.
Data from: Individual-specific strategies inform category learning
Open the record for dataset details and reuse information.
Inverse design of soft materials via a deep-learning-based evolutionary strategy
Open the record for dataset details and reuse information.
Data from: Brain size does not predict learning strategies in a serial reversal learning test
<p><span><span><span><span><span><span><span><span><span><span><span>Reversal learning assays are commonly used across a wide range of taxa to investigate associative learning and behavioural flexibility. In serial reversal learning, the reward contingency in a binary discrimination is reversed multiple times. Performance during serial reversal learning varies greatly at the interspecific level, as some animals adapt a rule-based strategy that enables them to switch quickly between reward contingencies. Enhanced learning ability and increased behavioural flexibility generated by a larger relative brain size has been proposed to be an important factor underlying this variation. Here we experimentally test this hypothesis at the intraspecific level. We use guppies (<i>Poecilia reticulata</i>) artificially selected for small and large relative brain size, with matching differences in neuron number, in a serial reversal learning assay. We tested 96 individuals over ten serial reversals and found that learning performance and memory were predicted by brain size, whereas differences in efficient learning strategies were not. We conclude that variation in brain size and neuron number is important for variation in learning performance and memory, but these differences are not great enough to cause the larger differences in efficient learning strategies observed at higher taxonomic levels. </span></span></span></span></span></span></span></span></span></span></span></p>
Learning strategies and long-term memory in Asian short-clawed otters (Aonyx cinereus) data
<p>Data submitted here, are those used in the writing of our manuscript entitled "Learning strategies and long-term memory in Asian short-clawed otters (<i>Aonyx cinereus</i>)" which has been submitted to Royal Society Open Science for publication. Abstract for that manuscript is below</p> <p>Social learning, namely learning from information acquired from others or their products, is widespread throughout the animal kingdom. There is growing evidence that animals selectively employ 'social learning strategies', which for example, determine when<i> </i>they should copy others instead of learning asocially, and whom they should copy. Furthermore, once animals have acquired new information, it is beneficial for them to commit it to long-term memory, especially when it concerns the discovery of profitable resources. Research into social learning strategies and long-term memory has covered a wide range of taxa. However, otters (subfamily Lutrinae), popular in zoos due to their sociability and playfulness, remained neglected until a recent study provided evidence of social learning in captive smooth-coated otters (<i>Lutrogale perspicillata</i>), but not in Asian short-clawed otters (<i>Aonyx cinereus</i>). We investigated Asian short-clawed otters' learning strategies and long-term memory performance in a foraging context. We presented novel extractive foraging tasks twice to captive family groups and used network-based diffusion analysis to provide evidence of social learning and long-term memory in this species. A major cause of wild Asian short-clawed otter declines is prey scarcity. Furthering our understanding of how they learn about and remember novel food sources could inform key conservation strategies.</p>
"An efficient ptychography reconstruction strategy through fine-tuning of large pre-trained deep learning model" train and test data
<ul><li>Model for the article "An efficient ptychography reconstruction strategy through fine-tuning of large pre-trained deep learning model".</li><li>The .pth file is the pre-trained PtyNet-S model and the fine-tuned PtyNet-B model.</li><li>Please contact panxy@ihep.ac.cn if you have any questions.</li></ul>
Innovative Strategies for Blood-Brain Barrier (BBB) Permeability Modeling: Harnessing the Power of Machine Learning-based q-RASAR Approach
<p>In the current research, we have unveiled an advanced technique termed the quantitative Read-Across Structure-Activity Relationship (q-RASAR) framework to harnesses the power of machine learning (ML) for significantly enhancing the precision of predictions related to blood-brain barrier (BBB) permeability. It is important to emphasize that the central objective of this study is not to introduce another model for predicting BBB permeability. Instead, our focus is on highlighting the improvement in predicting the BBB permeability of organic compounds by introducing the q-RASAR approach. This innovative methodology strives to enhance the precision of evaluating neuropharmacological implications and streamline the drug development process. In this investigation, we developed an ML-based q-RASAR PLS model using a dataset comprising 1012 compounds of diverse classes of heterocyclic and aromatic hydrocarbons, obtained from the freely accessible B3DB database (accessible at <a href="https://github.com/theochem/B3DB">https://github.com/theochem/B3DB</a>) to predict BBB permeability during the lead discovery phase for central nervous system (CNS) drugs. The model's predictive capability underwent validation using two external sets, encompassing a total of 1,130,315 compounds, including synthetic compounds and natural products (NPs) for data gap filling and other two external sets comprising 116 drug-like/drug compounds from FDA and ChEMBL databases to assess the model's reliability. This study aimed to bridge the data gap by employing a predictive model to estimate the impact of brain-plasma concentration ratios on BBB permeability for both synthetic compounds and natural products (NPs). To further enhance predictability, we have developed various other ML-based q-RASAR models. The insights from the developed model highlight the pivotal roles played by hydrophobicity, electronic effects, degree of ionization and steric factors as essential features facilitating the traversal of the blood-brain barrier. This research not only advances our understanding of the molecular determinants influencing the permeability of central nervous system drugs but also establishes a versatile computational platform for the rapid assessment of diverse compounds, facilitating informed decision-making in the realms of drug development and design.</p>
Best Practices and Strategies of Teachers in Virtual Learning Instructions Amidst Covid-19 Pandemic
<p><span>This study investigates the demographic profiles, educational backgrounds, and professional development of teachers, alongside their adoption of various teaching strategies in a virtual instructional context. Through analysis of multiple datasets concerning teachers’ age, gender, educational attainment, field of specialization, and the seminars and training they attended, the study evaluates the prevalence of specific teaching practices and their effectiveness. Additionally, using Chi-square tests, the study examines the potential relationships between teacher profiles and the extent of their practice implementations. Findings reveal a workforce characterized by a high level of experience and academic achievement, with a significant gender disparity. Crucially, no significant statistical correlations were found between teacher demographics or professional backgrounds and the teaching practices employed, suggesting a standardized adoption of educational strategies across various teacher profiles. The results emphasize the role of professional development in maintaining teaching efficacy in diverse educational settings, particularly in adapting to virtual platforms.</span></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.