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.
120
datasets available to search
ShareScore release 0.7.1
Dataset results
120 results for “data augmentation”
The benefit of augmenting open data with clinical data-warehouse EHR for forecasting SARS-CoV-2 hospitalizations in Bordeaux area, France
<p><strong>Objective</strong></p> <p>The aim of this study was to develop an accurate regional forecast algorithm to predict the number of hospitalized patients and to assess the benefit of the Electronic Health Records (EHR) information to perform those predictions. Materials and Methods Aggregated data from SARS-CoV-2 and weather public database and data warehouse of the Bordeaux hospital were extracted from May 16, 2020, to January 17, 2022. The outcomes were the number of hospitalized patients in the Bordeaux Hospital at 7 and 14 days. We compared the performance of different data sources, feature engineering, and machine learning models.</p> <p><strong>Results </strong></p> <p>During the period of 88 weeks, 2561 hospitalizations due to COVID-19 were recorded at the Bordeaux Hospital. The model achieving the best performance was an elastic-net penalized linear regression using all available data with a median relative error at 7 and 14 days of 0.136 [0.063; 0.223] and 0.198 [0.105; 0.302] hospitalizations, respectively. Electronic health records (EHRs) from the hospital data warehouse improved median relative error at 7 and 14 days by 10.9% and 19.8%, respectively. Graphical evaluation showed remaining forecast error was mainly due to delay in slope shift detection.</p> <p><strong>Discussion </strong></p> <p>Forecast models showed overall good performance both at 7 and 14 days which was improved by the addition of the data from Bordeaux Hospital data warehouse.</p> <p><strong>Conclusions </strong></p> <p>The development of hospital data warehouses might help to get more specific and faster information than traditional surveillance systems, which in turn will help to improve epidemic forecasting at a larger and finer scale.</p>
The benefit of augmenting open data with clinical data-warehouse EHR for forecasting SARS-CoV-2 hospitalizations in Bordeaux area, France
Open the record for dataset details and reuse information.
Data from: Immediate genetic augmentation and enhanced habitat connectivity are required to secure the future of an iconic endangered freshwater fish population
Open the record for dataset details and reuse information.
POLAR-Sim: Augmenting NASA's POLAR dataset for data-driven lunar perception and rover simulation
Open the record for dataset details and reuse information.
Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning: W+jet large test dataset
<p>W+jet events at generator and reconstruction level, used to train analysis-specific generative models.</p> <p>Events are represented as an array of relevant high-level features. Reco objects are matched to Gen objects and a minimal selection is applied to define the generator support in the N-dim space identified by the input features.</p> <p>About 2M events, used for large-scale testing</p> <p>Details in https://arxiv.org/abs/2010.01835</p>
Research Data supporting "Linear-Scaling Density Functional Theory using the Projector Augmented Wave Method"
<p>Research Data supporting "Linear-Scaling Density Functional Theory using the Projector Augmented Wave Method" by Nicholas D. M. Hine</p>
Patent data with founding years (augmented)
Open the record for dataset details and reuse information.
Replication Package of Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt
<p>Self-Admitted Technical Debt (SATD) refers to circumstances where developers use code comments, issues, pull requests, or other textual artifacts to explain why the existing implementation is not optimal. Past research in detecting SATD has focused on either identifying SATD (classifying SATD instances as SATD or not) or categorizing SATD (labeling instances as SATD that pertain to requirements, design, code, test, etc.). However, the performance of such approaches remains suboptimal, particularly when dealing with specific types of SATD, such as test and requirement debt. This is mostly because the used datasets are extremely imbalanced.</p> <p>In this study, we utilize a data augmentation strategy to address the problem of imbalanced data. We also employ a two-step approach to identify and categorize SATD on various datasets derived from different artifacts. Based on earlier research, a deep learning architecture called BiLSTM is utilized for the binary identification of SATD. The BERT architecture is then utilized to categorize different types of SATD. We provide the dataset of balanced classes as a contribution for future SATD researchers, and we also show that the performance of SATD identification and categorization using deep learning and our two-step approach is significantly better than baseline approaches.</p> <p>Therefore, to showcase the effectiveness of our approach, we compared it against several existing approaches:</p> <ol> <li>Natural Language Processing (NLP) and Matches task Annotation Tags (MAT) [<a href="https://github.com/Naplues/MAT" target="_blank" rel="noopener">Github</a>]</li> <li>eXtreme Gradient Boosting+Synthetic Minority Oversampling Technique (XGBoost+SMOTE) [<a href="https://figshare.com/s/87a4b5002c7488822e60" target="_blank" rel="noopener">Figshare</a>]</li> <li>eXtreme Gradient Boosting+Easy Data Augmentation (XGBoost+EDA) [<a href="https://github.com/shenyuanduanzui/xgboost_satd" target="_blank" rel="noopener">Github</a>]</li> <li>MT-Text-CNN [<a href="https://github.com/yikun-li/satd-different-sources-data" target="_blank" rel="noopener">Github</a>]</li> </ol> <p> </p> <div> <div><strong>Structure of the Replication Package:</strong></div> </div> <p>In accordance with the original dataset, the dataset comprises four distinct CSV files delineated by the artifacts under consideration in this study. Each CSV file encompasses a text column and a class, which indicate classifications denoting specific types of SATD, namely code/design debt (C/D), documentation debt (DOC), test debt (TES), and requirement debt (REQ) or Not-SATD.</p> <div> <div><code>├── SATD Keywords</code></div> <div><code>│ ├── Keywords based on Source of Artifacts</code></div> <div><code>│ │ ├── Code comment.txt</code></div> <div><code>│ │ ├── Commit message.txt</code></div> <div><code>│ │ ├── Issue section.txt</code></div> <div><code>│ │ └── Pull section.txt</code></div> <div><code>│ ├── Keywords based on Types of SATD</code></div> <div><code>│ │ ├── code-design debt.txt</code></div> <div><code>│ │ ├── documentation debt.txt</code></div> <div><code>│ │ ├── requirement debt.txt</code></div> <div><code>│ │ └── test debt.txt</code></div> <div><code>├── src</code></div> <div><code>│ ├── bert.py</code></div> <div><code>│ ├── bilstm.py</code></div> <div><code>│ └── preprocessing.py</code></div> <div><code>├── data-augmentation-code_comments.csv</code></div> <div><code>├── data-augmentation-commit_messages.csv</code></div> <div><code>├── data-augmentation-issues.csv</code></div> <div><code>├── data-augmentation-pull_requests.csv</code></div> <div> <div><code>└── Supplementary Material.docx</code></div> <div> </div> </div> <div> </div> </div> <p><strong>Requirements:</strong></p> <div> <div><a href="https://nlp.stanford.edu/projects/glove/" target="_blank" rel="noopener">glove</a></div> <div>nltk</div> <div>transformers</div> <div>torch</div> <div>tensorflow</div> <div>keras</div> <div>langdetect</div> <div>inflect</div> <div>inflection</div> </div> <div> </div> <div> </div> <div> <div><strong>Project sources for each artifact are as follows:</strong></div> </div> <div> </div> <div> <table> <tbody> <tr> <td><strong>Source code comment</strong></td> <td><strong>Issue section</strong></td> <td><strong>Pull section</strong></td> <td><strong>Commit message</strong></td> </tr> <tr> <td>ant<br>argouml<br>columba<br>emf<br>hibernate<br>jedit<br>jfreechart<br>jmeter<br>jruby<br>squirrel</td> <td> <div>camel</div> <div>chromium</div> <div>gerrit</div> <div>hadoop</div> <div>hbase</div> <div>impala</div> <div>thrift</div> </td> <td> <div>accumulo</div> <div>activemq</div> <div>activemq-artemis</div> <div>airflow</div> <div>ambari</div> <div>apisix</div> <div>apisix-dashboard</div> <div>arrow</div> <div>attic-apex-core</div> <div>attic-apex-malhar</div> <div>attic-stratos</div> <div>avro</div> <div>beam</div> <div>bigtop</div> <div>bookkeeper</div> <div>brooklyn-server</div> <div>calcite</div> <div>camel</div> <div>camel-k</div> <div>camel-quarkus</div> <div>camel-website</div> <div>carbondata</div> <div>cassandra</div> <div>cloudstack</div> <div>commons-lang</div> <div>couchdb</div> <div>cxf</div> <div>daffodil</div> <div>drill</div> <div>druid</div> <div>dubbo</div> <div>echarts</div> <div>fineract</div> <div>flink</div> <div>fluo</div> <div>geode</div> <div>geode-native</div> <div>gobblin</div> <div>griffin</div> <div>groovy</div> <div>guacamole-client</div> <div>hadoop</div> <div>hawq</div> <div>hbase</div> <div>helix</div> <div>hive</div> <div>hudi</div> <div>iceberg</div> <div>ignite</div> <div>incubator-brooklyn</div> <div>incubator-dolphinscheduler</div> <div>incubator-doris</div> <div>incubator-heron</div> <div>incubator-hop</div> <div>incubator-mxnet</div> <div>incubator-pagespeed-ngx</div> <div>incubator-pinot</div> <div>incubator-weex</div> <div>infrastructure-puppet</div> <div>jena</div> <div>jmeter</div> <div>kafka</div> <div>karaf</div> <div>kylin</div> <div>lucene-solr</div> <div>madlib</div> <div>myfaces-tobago</div> <div>netbeans</div> <div>netbeans-website</div> <div>nifi</div> <div>nifi-minifi-cpp</div> <div>nutch</div> <div>openwhisk</div> <div>openwhisk-wskdeploy</div> <div>orc</div> <div>ozone</div> <div>parquet-mr</div> <div>phoenix</div> <div>pulsar</div> <div>qpid-dispatch</div> <div>reef</div> <div>rocketmq</div> <div>samza</div> <div>servicecomb-java-chassis</div> <div>shardingsphere</div> <div>shardingsphere-elasticjob</div> <div>skywalking</div> <div>spark</div> <div>storm</div> <div>streams</div> <div>superset</div> <div>systemds</div> <div>tajo</div> <div>thrift</div> <div>tinkerpop</div> <div>tomee</div> <div>trafficcontrol</div> <div>trafficserver</div> <div>trafodion</div> <div>tvm</div> <div>usergrid</div> <div>zeppelin</div> <div>zookeeper</div> </td> <td> <div>accumulo</div> <div>activemq</div> <div>activemq-artemis</div> <div>airflow</div> <div>ambari</div> <div>apisix</div> <div>apisix-dashboard</div> <div>arrow</div> <div>attic-apex-core</div> <div>attic-apex-malhar</div> <div>attic-stratos</div> <div>avro</div> <div>beam</div> <div>bigtop</div> <div>bookkeeper</div> <div>brooklyn-server</div> <div>calcite</div> <div>camel</div> <div>camel-k</div> <div>camel-quarkus</div> <div>camel-website</div> <div>carbondata</div> <div>cassandra</div> <div>cloudstack</div> <div>commons-lang</div> <div>couchdb</div> <div>cxf</div> <div>daffodil</div> <div>drill</div> <div>druid</div> <div>dubbo</div> <div>echarts</div> <div>fineract</div> <div>flink</div> <div>fluo</div> <div>geode</div> <div>geode-native</div> <div>gobblin</div> <div>griffin</div> <div>groovy</div> <div>guacamole-client</div> <div>hadoop</div> <div>hawq</div> <div>hbase</div> <div>helix</div> <div>hive</div> <div>hudi</div> <div>iceberg</div> <div>ignite</div> <div>incubator-brooklyn</div> <div>incubator-dolphinscheduler</div> <div>incubator-doris</div> <div>incubator-heron</div> <div>incubator-hop</div> <div>incubator-mxnet</div> <div>incubator-pagespeed-ngx</div> <div>incubator-pinot</div> <div>incubator-weex</div> <div>infrastructure-puppet</div> <div>jena</div> <div>jmeter</div> <div>kafka</div> <div>karaf</div> <div>kylin</div> <div>lucene-solr</div> <div>madlib</div> <div>myfaces-tobago</div> <div>netbeans</div> <div>netbeans-website</div> <div>nifi</div> <div>nifi-minifi-cpp</div> <div>nutch</div> <div>openwhisk</div> <div>openwhisk-wskdeploy</div> <div>orc</div> <div>ozone</div> <div>parquet-mr</div> <div>phoenix</div> <div>pulsar</div> <div>qpid-dispatch</div> <div>reef</div> <div>rocketmq</div> <div>samza</div> <div>servicecomb-java-chassis</div> <div>shardingsphere</div> <div>shardingsphere-elasticjob</div> <div>skywalking</div> <div>spark</div> <div>storm</div> <div>streams</div> <div>superset</div> <div>systemds</div> <div>tajo</div> <div>thrift</div> <div>tinkerpop</div> <div>tomee</div> <div>trafficcontrol</div> <div>trafficserver</div> <div>trafodion</div> <div>tvm</div> <div>usergrid</div> <div>zeppelin</div> <div>zookeeper</div> </td> </tr> </tbody> </table> </div> <div> <div> </div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <p>This dataset has undergone a data augmentation process using the <a href="https://arxiv.org/abs/2302.13007" target="_blank" rel="noopener">AugGPT</a> technique. Meanwhile, the original dataset can be downloaded via the following link: <a href="https://github.com/yikun-li/satd-different-sources-data">https://github.com/yikun-li/satd-different-sources-data</a></p> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> <div> </div> </div> </div> </div> </div> </div>
Data of "Sustainable and imperceptible augmentation of living structures with organic bioelectronic fibres"
<p>Functional and sensory augmentation of living structures, such as the human skin and plant epidermis, offers vast opportunities for biology-machine interface, wearable health, and environmental monitoring. However, current sensor and electronic formats could be obstructive to their hosts’ inherent sensations or physiological changes. Challenges are also faced in widening the augmentation of living structures without drastically increasing the global environmental and ecological burdens. Here, we demonstrate imperceptibly augmented living systems, through in situ tethering of poly (3,4-ethylenedioxythiophene) : polystyrene sulfonate (PEDOT:PSS)-based organic bioelectronic fibres. Customising fibre tether patterns and modalities enable applications from biopotential acquisition and skin-gated organic electrochemical transistors, to augmented touch and plant interfaces. The open networks formed by the intrinsically substrate-free fibres provide a biomorphic interface, while supporting direct rigid-to-flexible coupling with microelectronics and e-textiles. We further demonstrate conceptual fibre formats for on-demand device repair, upgrade, and recycle, or for enhancing electromechanical stability against touch. Our work may unfold bioelectronic interfaces that are simultaneously biologically-adaptable, sustainable, and created with unprecedented freedom.</p>
Data and code for: Assessing the Reliability of Point Mutation as Data Augmentation for Deep Learning with Genomic Data
<p>Data and code for the paper "Assessing the Reliability of Point Mutation as Data Augmentation for Deep Learning with Genomic Data".</p>
Data for: A comprehensive dataset of forest above-ground biomass from field observations, machine learning and topographically augmented allometric models over the Kashmir Himalaya
<p>The repository contains observed Above Ground Biomass (AGB) estimates at about 275 sample plots chosen for AGB assessment in the forests of Kashmir Himalaya. The AGB is assessed as a fucntion of dbh using various allometric equations developed specifically for the region. It also contains the AGB for years 1978, 1990, 2000, 2010 and 2021 predicted using topographcally augmeneted multivariate regression model. The extent of forest, delineated using on-screen digitization using Landsat and Sentinel image collection at decadal scale is also provided for the years 1978, 1990, 2000, 2010 and 2021.</p>
Variable Misuse tool: Dataset for data augmentation (6)
<p>Dataset used for data augmentation in the training phase of the Variable Misuse tool. It contains some source code files extracted from third-party repositories.</p>
Variable Misuse tool: Dataset for data augmentation (4)
<p>Dataset used for data augmentation in the training phase of the Variable Misuse tool. It contains some source code files extracted from third-party repositories.</p>
Data Augmentation for learning mechanical digital twins of voids in welding joints
<p>In Source-2_Data_Augmentation:</p> <p>Exercice1_augmentation.ipynb Jupyter Notebook for data warpping of defect images.</p> <p>Exercice2_augmentation_multimodale.ipynb Jupyter Notebook for multimodal data augmentaion (defect images and mechanical fields) via oversampling</p> <p>Exercice3_clustering.ipynb Data clustering using the k-medoids algorithm applied to mechanical dissimilarity of the defects.</p> <p>k_medoids.py is a python code of a kmedoids algorithm.</p> <p>in Data:</p> <p>All_images.npy (numpy file) contains the defect images.</p> <p>All_Stresses.npy (numpy) contains mechanical fields, All_Stresses[k,i,j,ic,it] is the instance number k of the component ic of the Cauchy stress tensor at time it. The mechanical problem is decribed in <a href="https://dx.doi.org/10.5802/crmeca.51">⟨10.5802/crmeca.51⟩</a>. <a href="https://hal.archives-ouvertes.fr/hal-03113503">⟨hal-03113503⟩.</a></p> <p>New_images_1.npy and New_Stresses_1.npy are augmented data for k=1.</p> <p>New_images_87.npy and New_Stresses_87.npy are augmented data for k=87.</p> <p>Dissimilarity_Stress.npy is the Frobenius norm of the distances between stress tensors (All_Stresses.npy).</p> <p> </p>
Training dataset for "A deep learned nanowire segmentation model using synthetic data augmentation"
<p>This image dataset contains synthetic structure images used for training the deep-learning based nanowire segmentation model presented in our work "A deep learned nanowire segmentation model using synthetic data augmentation" to be published in <em>npj Computational materials. </em>Detailed information can be found in the corresponding article.</p>
Replication Data for: ``Impact of Parameterized Isopycnal Diffusivity on Shelf-Ocean Exchanges under Upwelling-Favorable Winds: Offline Tracer Simulations Augmented by Artificial Neural Network''
<p>This dataset contains the modified MAMEBUS source code, configuration files for the MITgcm and MAMEBUS simulations, model diagnostics used in the paper, and scripts to train the Artificial Neural Networks.</p>
Retrieve, Merge, Predict: Augmenting Tables with Data Lakes
<p>Files composing the YADL data lake, for the paper "Retrieve, Merge, Predict: Augmenting Tables with Data Lakes (Experiment, Analysis & Benchmark Paper)"</p> <p>We present an in-depth analysis of data discovery for analytics in data lakes, focusing on table augmentation for given machine learning tasks. We analyze alternative methods used in the three key steps: retrieving joinable tables, merging information, and predicting with the resultant table. As data lakes, the paper uses YADL (Yet Another Data Lake) -- a novel dataset developed as a tool for benchmarking this data discovery task -- and Open Data US, a well-referenced real data lake. Through systematic exploration on both lakes, our study outlines the importance of accurately retrieving join candidates, and the efficiency of simple aggregation methods. We report new insights on the benefits of existing solutions and on the their limitations, aiming at guiding future research in this space.</p> <p>Archives provided here follow the notation used for the experiments, which is different from what is reported in the paper. The four YADL versions available here are:</p> <ul> <li>"binary_update" (YADL Binary)</li> <li>"wordnet_full" (YADL Base)</li> <li>"wordnet_vldb_10" (YADL 10k)</li> <li>"wordnet_vldb_50" (YADL 50k)</li> </ul>
Data from: Trends in plant cover derived from vegetation-plot data using ordinal zero-augmented beta regression
<p><strong>Questions.</strong> Plant cover values in vegetation-plot data are bounded between 0 and 1, and cover is typically recorded in discrete classes with non-equal intervals. Consequently, cover data are skewed and heteroskedastic, which hampers the application of conventional regression methods. Recently developed ordinal beta regression models consider these statistical difficulties. Our primary question is if we can detect species trends in vegetation-plot time series data with this modelling approach. A second question is whether trends in cover have additional value compared to trends in occurrence, which are easier to assess for practitioners.</p> <p><strong>Location</strong>. The Netherlands, Western Europe.</p> <p><strong>Methods. </strong>We used vegetation-plot data collected from 10.000 fixed plots which were surveyed once every four years during 1999-2022. We used the ordinal zero-augmented beta regression (OZAB) model, a hierarchical model consisting of a logistic regression for presence and an ordinal beta regression for cover. We adapted the OZAB model for longitudinal data and produced estimates of cover and occurrence for each four-year period. Thereafter we assessed trends in cover and in occurrence across all periods.</p> <p><strong>Results.</strong> We found evidence of a trend in cover in 318 out of the 721 species (44%) with sufficient data. Most species showed similar directional trends in occurrence and percent cover. No trend in occurrence was detected for 64 species that had evidence of a trend in cover. Declining species had stronger relative changes in cover than in occurrence.</p> <p><strong>Conclusions. </strong>Our model enables researchers to detect trends in cover using longitudinal vegetation-plot data. Cover trends often corroborated trends in occurrence, but we also regularly found trends in cover even in the absence of evidence for trends in occurrence. Our approach thus contributes to a more complete picture of (changes in) vegetation composition based on large monitoring datasets.</p>
[Data augmentation in a TTL] - Fictive dataset (27.5M) with up to 5k reactions per template // (13'953 template extracted from USPTO-FULL IBM version)
<p>Full generated fictive dataset, containing 27.5M reactions with up to 5000 reactions per radius 1 reaction template (13'953 reaction templates from USPTO-full, IBM version).</p> <p>Title of the manuscript:</p> <p>"Data augmentation in a Triple Transformer Loop retrosynthesis model"</p> <p>Abstract: </p> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div> <div dir="auto"> <div>Reactions in the US Patent Office (USPTO) are biased towards a few over-represented reaction types, which potentially limits its usefulness for computer-assisted synthesis planning (CASP). To obtain an equilibrated dataset, we applied retrosynthesis templates to USPTO molecules as products (P) to generate starting materials (SM). We then used transformer T2 from our recently reported triple transformer loop (TTL) retrosynthesis model to predict reagents (R) for the SM®P reaction. Finally, we validated the prediction by requesting a high confidence prediction (>95%) for the prediction of P from SM+R by TTL transformer T3. We generated up to 5,000 reactions per template, resulting in 27.5 million validated fictive reactions covering the chemical space of the original UPSTO dataset. To exemplify the use of this dataset, we show that a single-step retrosynthesis transformer model trained with a template equilibrated subset of 1,097,374 fictive reactions outperforms the corresponding model trained on USPTO reactions only.</div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> <div></div>
Supplementary Data for "FreeHi-C: high fidelity Hi-C data simulation for benchmarking and data augmentation"
<p>Simulated and processed data utilized in the paper "FreeHi-C: high fidelity Hi-C data simulation for benchmarking and data augmentation" for visualization and further analysis.</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.