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.
58
datasets available to search
ShareScore release 0.7.1
Dataset results
58 results for “Feature Extraction”
BRAIN Journal-Motor Imagery signal Classification for BCI System Using Empirical Mode Décomposition and Bandpower Feature Extraction-Figure 3. Hybrid EMD-BP approach for one trail feature extraction
<p>In this work, we propose a direct nonlinear approach to extract the more relevant IMFs corresponding to the different frequency components in the and bands and then obtain the BP in order to use them as features for mental task classification (see Fig. 3). The feature vector pi used for the demonstration in this paper is composed, for each sample I, 1 < i < 2048, in a given trial (among a total of 160 trials) of four bandpower, calculated of the rhythms and in positions C3 and C4 (Trad et al., 2011).</p>
BRAIN Journal-Motor Imagery signal Classification for BCI System Using Empirical Mode Décomposition and Bandpower Feature Extraction-Figure 2. Timing of one trial of the experiment with continuous feedback (Guger et al, 2001)
<p>At the beginning of each trial (t = 0 s), a fixation cross appeared on the black screen. After two seconds a warning stimulus was given in the form of a beep. From 3 to 4.25s, an arrow (cue stimulus), pointing to the left or right, was shown on the screen. The subject was instructed to imagine a left or right hand movement until the end of the trial, depending on the direction of the arrow. The EEG was sampled and classified on line throughout the session. Between 4.25 and 8s, the classification result was used to give a continuously updated feedback stimulus in the form of a horizontal bar that appeared in the center of the screen. The paradigm is illustrated in fig (2).</p>
BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 2. A Sample Image from extracted feature
<p>Using these data, it creates a new picture and uses these data as a starting point for drawing. By using the data, it gets a model and shape of face without color and facial expression (Gourier et al.; 2004), such as Figure 2. It got a model of faces using these features. </p>
BRAIN Journal-A Robust Approach of Facial Orientation Recognition from Facial Features-Figure 2. A Sample Image from extracted feature
<p>Using these data, it creates a new picture and uses these data as a starting point for drawing. By using the data, it gets a model and shape of face without color and facial expression (Gourier et al.; 2004), such as Figure 2. It got a model of faces using these features.</p>
Multiscale Spatial Patterns in Giant Dike Swarms Identified through Objective Feature Extraction Datasets
<p>S1 - Linked dike clusters for the Columbia River Flood Basalt group including the four identified subswarms: Chief Joseph, Monument, Ice Harbor, and Steens as compiled in Morriss et al., 2020. This dataset uses the a UTM Zone 11N projection (EPSG:26911).</p> <p>S2 - Linked dike clusters for the Deccan Traps including the four identified subswarms: Saurashtra, Narmada-Tapi, Central and Coastal. Due to their overlap Central and Coastal Swarms have been combined in this dataset into the Central Swarm. This dataset uses the a WGS 84 projection (EPSG:3857). </p> <p>S3 - Dike segment data for Spanish Peaks and Dike Mountain located in the Rio Grande Rift of Colorado. This dataset was digitized using QGIS based on the map by Johnson (1961). This dataset uses the a UTM Zone13N projection (EPSG:32613). The file includes the start, end points, and midpoints of the dikes; segment length; calculated $\rho$ and $\theta$ for the Hough Transform; the origin used for the Hough Transform which is different for each subswarm (xc,yc); dike rock type if known; and a unique identification calculated based on the start and endpoints. This dataset has been preprocessed to remove curving dikes and is the data set used to produce later products (Data set S4). </p> <p>S4 - Linked dike clusters for the Spanish Peaks and Dike Mountain. This dataset was produced using the Agglomerative Clustering algorithms using the parameters set in Table 1. This dataset uses the a UTM Zone 13N projection (EPSG:32613). </p> <p> </p> <p> </p> <p>These datasets were produced using the Agglomerative Clustering algorithms using the parameters set in Table 1. The datasets are in the format of a CSV file but can be read into GIS programs using Well Known Text (WKT) linestring. TThe file includes the start and end points of the average line in the cluster and it's mid points, cluster length and width (Xstart, Xend, Xmid, Ymid, in meters and UTM coordinates, Dike Cluster Width or R\_Width, Dike Cluster Length or R\_Length all in meters); calculated average $\rho$ and $\theta$ for the Hough Transform $\rho$ units measured in meters, $\theta$ units measured in degrees, unless otherwise stated); the origin used for the Hough Transform which is different for each subswarm ($xc$,$yc$, meters in UTM coordinates); average slope and intercept (AvgSlope, AvgIntercept meters); range and standard deviation for $\rho$ and $\theta$ for all objects in the cluster ($\rho$ units measured in meters, $\theta$ units measured in degrees); cluster size (Size); sum of segment lengths in a cluster (SegmentLSum, meters); whether the cluster crosses between negative and positive values (ClusterCrossesZero, boolean); overlap as calculated in the main text where the length of overlap is normalized by the sum of segment lengths in a cluster; maximum number of overlapping segments (nOverlapingSegments); twist angle which is the difference in angle betweeen the average cluster line and the average line formed by cluster midpoints (EnEchelonAngleDiff, degrees); the p-value for the midpoint line fit of the segments where $p<0.05$ is considered to be a significant fit (EEPValue); the maximum, median, and minimum segment nearest neighbors distances in the cluster which is calculated using the cartesian midpoints of each segment and normalized by the Cluster Length (MaxSegNNDist, MedianSegNNDist, MinSegNNDist); characterization of each cluster as filtered or not, filtered clusters are of size greater than $3$ and have a MaxSegNNDist of less than $0.5$ (TrustFilter, boolean); the date edited (Date\_Changed), and the clustering parameters used for each cluster (Rho\_Threshold in meters, Theta\_Threshold in degrees) and a unique identification calculated based on the start and endpoints (ClusterHash). </p>
Data from: How many specimens make a sufficient training set for automated three dimensional feature extraction?
Open the record for dataset details and reuse information.
Custom script for feature extraction from Genbank files
Open the record for dataset details and reuse information.
Retinal status analysis method based on feature extraction and quantitative grading in OCT images
<p>The raw database includes 200 retinal OCT images judged as normal by ophthalmologists and 100 images with various abnormalities. The software includes the main steps for retinal status analysis. The software was carried out in Matlab.</p>
Refined Bathymetric Prediction based on Feature Extraction of Gravity Field Signals: BATHY-FE
<p>BATHY-FE is a refined global seafloor model derived from extraction of learnt bathymetric signatures inherent in gravity field signals. It spans longitudes -180 ~ 180, and latitudes -80 ~ 80. It contains more short-wavelength seafloor features, and is superior to existing bathymetric models in almost all marine regions, especially at regions close to the poles. It is a GMT readable grid file (i.e., a matrix of seafloor model, and vectors of longitudes and latitudes) with a spatial resolution of 15 arc-seconds.</p><p>Included in this repository are a MATLAB livescript and sample data in which a demonstration of the algorithm over a region north of Alaska and Canada is presented.</p>
DSM: Deep Sequential Model for Complete Neuronal Morphology Representation and Feature Extraction
<p>This is an open-source repository for hosting codes and data files from research, "DSM: Deep Sequential Model for Complete Neuronal Morphology Representation and Feature Extraction". We also provided a web service based on our methods, please go to http://114.117.165.134:8501/.</p><p>(1)raw_dataset.zip: </p><ol><li>1,282 neuron reconstructions from SEU-Allen dataset;</li><li>1,002 neuron reconstructions from Janelia dataset;</li><li>1,100 neuron reconstructions from ION dataset.</li></ol><p>(2)Supplementary.zip: Supplementary information, including tables and figures;</p><p>(3)DSM-tools.zip: A python package for converting neuron morphology into sequences and implementing DSM models.</p><ol><li>NeuronSequenceDataset class: to transform SWC files to sequence dataframes by binary tree traversals, and prepare for the input of DSM networks.</li><li>DSMDataConverter class: a helper to convert the sequence dataframes for classification and clustering.</li><li>DSMHierarchicalAttentionNetwork class: classification model, giving a pre-trained DSM-HAN model by default.</li><li>DSMAutoencoder class: clustering model, giving a pre-trained DSM-AE model by default.</li></ol><p>(4)neuron2seq_for_developer.zip: A repository for further development of the models, including source codes and all data files.</p>
Event Registry titles only dataset with multiple extracted features (both sparse and dense)
<p>This is the same content as:</p> <p>Guillaume Bernard. (2022). Event Registry dataset with multiple extracted features (both sparse and dense) (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6630367</p> <p>But with titles of articles only.</p>
CoAID dataset with multiple extracted features (both sparse and dense)
<p>This is a publication of the CoAID dataset originaly dedicated to fake news detection. We changed here the purpose of this dataset in order to use it in the context of event tracking in press documents.</p> <p>Cui, Limeng, et Dongwon Lee. 2020. « CoAID: COVID-19 Healthcare Misinformation Dataset ». <em>ArXiv:2006.00885 [Cs]</em>, novembre. <a href="http://arxiv.org/abs/2006.00885">http://arxiv.org/abs/2006.00885</a>.</p> <p>In this dataset, we provide multiple features extracted from the text itself. <strong>Please note the text is missing from the dataset published in the CSV format for copyright reasons. You can download the original datasets and manually add the missing texts from the original publications.</strong></p> <p>Features are extracted using:</p> <p>- A corpus of reference articles in multiple languages languages for TF-IDF weighting. (<em>features_news</em>) [1]</p> <p>- A corpus of tweets reporting news for TF-IDF weighting. (<em>features_tweets)</em> [1]</p> <p>- A S-BERT model [2] that uses <em>distiluse-base-multilingual-cased-v1 </em>(called <em>features_use</em>) [3]</p> <p>- A S-BERT model [2] that uses <em>paraphrase-multilingual-mpnet-base-v2 </em>(called <em>features_mpnet</em>) [4]</p> <p><strong>References:</strong></p> <p>[1]: Guillaume Bernard. (2022). Resources to compute TF-IDF weightings on press articles and tweets (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6610406</p> <p>[2]: Reimers, Nils, et Iryna Gurevych. 2019. « Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks ». In <em>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</em>, 3982‑92. Hong Kong, China: Association for Computational Linguistics. <a href="https://doi.org/10.18653/v1/D19-1410">https://doi.org/10.18653/v1/D19-1410</a>.</p> <p>[3]: https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v1</p> <p>[4]: https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2</p>
An unsupervised deep learning framework with variational autoencoders for genome-wide DNA methylation analysis and biologic feature extraction applied to breast cancer
<p>Supplemental data for the paper titled "An unsupervised deep learning framework with variational autoencoders for genome-wide DNA methylation analysis and biologic feature extraction applied to breast cancer"</p>
extracted_features
<p>Extracted features from OSTrain, OSValidate, OSTest to be used in SUMo's pipeline.</p>
Materials Datasets with 273 compositional and structural features extracted from Matminer
<p>Materials Datasets with 273 compositional and structural features extracted from <a href="https://github.com/hackingmaterials/matminer">Matminer</a>. Materials datasets are retrieved using the python package <a href="https://github.com/usnistgov/jarvis">jarvis-tools</a>.</p>
Set of extracted feature tracks for the year 2016.
<p>Dataframe composed of a set of trajectories identified and tracked from one yearlong of weather radar composites of the German Weather Service (DWD).</p>
Composer Attribution of Renaissance Motets (Iberian Polyphony around 1500): MIDIs and Extracted Features
<p><br> This distribution includes MIDI files used in the experiments described in the "Composer Attribution of Renaissance Motets: A Case Study Using Statistical Features and Machine Learning" chapter of the book The Anatomy of Iberian Polyphony around 1500. Multi-part motets have been separated out into separate MIDI files. We edited the files for consistency, which included adjusting elements that could interfere with encoding rhythm consistently (e.g. standardized rhythmic value rates, eliminating fermatas, etc.).</p> <p>The MIDI files in the nonIb_noMB group were taken from the Josquin Research Project (JRP), who have kindly granted us permission to re-publish them here with our modifications. These are redistributed with a "CC BY-SA 4.0" license: https://github.com/josquin-research-project/jrp-scores/blob/master/LICENSE.txt. The Iberian MIDI files were produced from editions created by The Anatomy of Late 15th- and Early 16th-Century Iberian Polyphonic Music project (https://iberianpolyphonicmusic.wordpress.com), and are included here after our modifications, with permission. We digitised the nonIb_MBonly MIDI files ourselves using Sibelius. All these files are distributed under a "CC BY-SA 4.0" license" license (https://creativecommons.org/licenses/by-sa/4.0/). The included "Catalogue.pdf" file outlines the contents of this corpus in its entirety.</p> <p>This distribution also includes the "Renaissance-safe" features extracted using jSymbolic 2.2 (http://jmir.sourceforge.net) from the MIDI encodings included here. Details on all the features extracted with the software are available in the jSymbolic manual (http://jmir.sourceforge.net/manuals/jSymbolic_manual/home.html). These are presented as follows:</p> <p>- FeatureDefinitions.xml: Descriptions of all extracted features, encoded in ACE XML 1.0, as output directly by jSymbolic. This file does not include any feature values (these are found in the FeatureValues.xml file).</p> <p>- FeatureValues.xml: Extracted feature values, encoded in ACE XML 1.0, as output directly by jSymbolic. The features are described in the FeatureDefinitions.xml file. Class values are implied by the folder containing each MIDI file.</p> <p>- FeatureValues_BasicCSV: Extracted feature values encoded in a CSV file, as output directly by jSymbolic (with complete file paths truncated). Class values are implied by the folder containing each MIDI file.</p> <p>- FeatureValues_HumanReadable.xlsx: Extracted features formatted into a human-readable Microsoft Excel file. Group averages and standard deviations have been added to the bottom, and the "Length_In_Breves" feature is added in a column at the right (it is included separately because it is not calculated directly by jSymbolic 2.2).</p> <p>- FeatureValues_WekaReady.csv: Extracted feature values encoded in a CSV file in a format readable by Weka (https://www.cs.waikato.ac.nz/ml/weka/). Class values have been added in a column on the right, and file paths have been removed, as required by Weka.</p>
Processed KuaiRand-1K dataset for the paper: Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
<p>The original public dataset is published in https://zenodo.org/records/10439422, we processed the KuaiRand-1K dataset for the paper: Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework.</p>
Selfee: Self-supervised features extraction of animal behaviors
<p class="MsoNormal"><span>Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in laboratories for behavior analysis. However, it has not been achieved to use an end-to-end unsupervised neural network to extract comprehensive and discriminative features directly from social behavior video frames for annotation and analysis purposes. Here, we report a self-supervised feature extraction (Selfee) convolutional neural network with multiple downstream applications to process video frames of animal behavior in an end-to-end way. Visualization and classification of the extracted features (Meta-representations) validate that Selfee processes animal behaviors </span><span>in a way similar to human perception</span><span>. We demonstrate that Meta-representations </span><span>can be efficiently used to detect anomalous behaviors that are indiscernible to human observation and hint in-depth analysis. Furthermore, time-series analyses of Meta-representations reveal the temporal dynamics of animal behaviors. In conclusion, we present a self-supervised learning approach to extract comprehensive and discriminative features directly from raw video recordings of animal behaviors and demonstrate its potential usage for various downstream applications.</span></p>
One million articles from five post socialist countries with extracted features: sentiment, basic emotions, LDA topics and presence of influential domestic politicians
<p>This is a replication data for my paper under blind review.<br> <br> This paper develops a new prediction model for media content presence on a website. It analyses a new corpus of one million articles from five countries: Poland, Russia, Belarus, Kazakhstan and Ukraine, in two languages, Polish and Russian. These articles were scraped daily from seventeen websites in 2017-2020 period. The research applies a wide range of natural language processing methods to automatically derive several properties of each article: its topic, sentiment, basic emotions, mentions of influential domestic politicians. The articles’ embeddings and their cosine similarity are used to calculate the news context, such as how an article differs from the daily issue main themes. These features are used to estimate a logistic regression assessing the likelihood that the same or slightly modified, as measured by cosine similarity, article will remain on the main web page the next day. The key, and somewhat unexpected result is that articles with negative sentiment polarity are less likely to be published for more than one day. This result holds for all countries analyzed. It means that the negative news bias documented in the literature is partly offset by their shorter life cycle.<br> <br> Data is in the Python pickle format. Should be read into Python using the pickle.load() function. Each element (row) is the data frames or list represents one news article. Each file has the same format. Loading a pickle file returns a list of four elements:<br> 1. A dummy variable equal to 1 when the article was published the next day, with the text being identical<br> 2. A dummy variable equal to 1 when the article was published the next day, but we allow for small text modifications (cosine similarity > 0.99)<br> 3. Dataframe with extracted features, described below.<br> 4. List with texts of articles in Polish or Russian<br> <br> Ad 3. The columns of the dataframe are as follows (we refer to row number i in description):<br> - pandas index (may appear once or twice in the datafame)<br> - maxcosine: maximum cosine similarity between art i and all articles published next day<br> - cosine_diff: cosine similarity between article i and the elementwise average of embeddings of all articles in the current issue. Measure how similar is the article i to the core narrative of the current issue<br> - cosine_std: std. dev. of cosine similarity measures between all pairs of articles in the current issue. Measures how focused or dispersed is the current issue news coverage<br> - thirteen LDA topic groups: politics, legislation and legal affairs (POL); economy, finance, various sectors of the economy (ECO); military, war, protests, crime, security threats (MIL); international affairs, specific issues concerning foreign countries (INT); technology (TECH); family issues, culture, sport, education (FAM); regional issues and housing (REG); health issues and the Covid-19 pandemic (HEA); media (MED); accidents (ACC); religion (REL); the Soviet Union (USSR); and articles for which no topic could be determined (MISC).<br> - rsent.c: relative sentiment that is dictionary based sentiment of articles i minus the average sentiment of the newspaper. This approach eliminates newspaper or country idiosyncratic sentiment factors. c stands for Covid, the sentiment lexicon was augmented with Covid related terms<br> - dip_*: Variable measuring if influential domestic politicians are mentioned in article i, * represent a country acronym. If N is equal to the number of occurrences of the names of influential domestic politicians in the article i, dip_* = 0 if N=0, dip_* = 1+ log(N) if N>0.<br> - three or four names of news portals from which the data was scraped.<br> - names of six basic emotions and the article i emotion scores calculated using zero-shot learning and the large version of the XLM (Conneau et al., 2019) model from the huggingface transformers library available at https://huggingface.co/vicgalle/xlm-roberta-large-xnli-anli<br> Names of the politicians used to calculate dip variables<br> Russia<br> "putin" "medvedev" "vaino" "shoigu" "bortnikov" "lavrov" "mishustin" "kirienko" "sechin"<br> Ukraine<br> "zelensky" "shmygal" "akhmetov" "avakov" "ermak" "poroshenko" "medvedchuk" "groisman"<br> Kazakhstan<br> "sagyntaev" "mamin" "tokayev" "nnazarbayev" "dnazarbayeva" "kulibayev" "masimov"<br> Belarus<br> "alukashenko" "vakulchik" "vlukashenko" "kobyakov" "makei" "myasnikovich" "rumas" "golovchenko"<br> Poland<br> "kaczynski" "duda" "morawiecki" "ziobro"<br> Data coverage<br> Country, news portal, numbr of articles<br> Russia iz.ru 43,782<br> Russia kommersant.ru 46,070<br> Russia novayagazeta.ru 29,357<br> Russia vedomosti.ru 27,797<br> Kazakhstan informburo.kz 29,375<br> Kazakhstan nur.kz 67,350<br> Kazakhstan tengrinews.kz 44,285<br> Kazakhstan zakon.kz 109,442<br> Belarus bdg.by 33,447<br> Belarus belgazeta.by 21,995<br> Belarus sb.by 83,685<br> Ukraine kp.ua 194,792<br> Ukraine segodnya.ua 45,835<br> Ukraine vesti.ua 90,559<br> Poland gazeta.pl 53,321<br> Poland rp.pl 49,587<br> Poland wpolityce.pl 76,625<br> <br> In the provided dataframes the number of observations is smaller, because the issues for which there was no next day issue, were removed.<br> <br> Data was scraped daily between 2017 or 2018 (depending on the country) and January 2021.</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.