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.
1,773
datasets available to search
ShareScore release 0.9.0
Dataset results
1,773 results for “mine”
BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 4. Structural Crossover
<p>Guided crossover operator is based on the two point separation from parents are selected<br> Left and right parts of them are related to each other by the condition to be meaningful With this<br> new child of his parents is that. But a new generation of the random choice to have reached this<br> stage. The crossover rate is fixed for our algorithm.</p>
BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 5. Insertion and Deletion Hidden Layer in NN
<p>Change in NN structure is other method that we used to optimization of solution[18].<br> Insertion a hidden layer caused to mutation operator is much natural. As connection with father and<br> mother nodes is easily[20],[21]. Weights of node and errors automatically calculated.<br> For each stage of the implementation of the mutation operator in genetic algorithms, neural<br> networks, only one of the nodes in the hidden layer is selected and inserted. These layers are<br> inserted on condition that the definition does not harm the network structure and the action is<br> meaningful. As an added layer can adjust the weights and the connection to the parent node of a network<br> layer to be removed.</p>
BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 3. The Structure of Neural Network
<p>A neural network (NN), in the case of artificial neurons called artificial neural<br> network (ANN) or simulated neural network (SNN), is an interconnected group of natural<br> or artificial neurons that uses a mathematical or computational model for information<br> processing based on a connectionist approach to computation. In most cases an ANN is an adaptive<br> system that changes its structure based on external or internal information that flows through the<br> network[9].<br> In more practical terms neural networks are nonlinear statistical data modelling or decision<br> making tools. They can be used to model complex relationships between inputs and outputs or<br> to find patterns in data.<br> Two neurons neural network active in memory (ON or 1) or disable (Off or 0), and each<br> edge (synapses or connections between nodes) is a weight. Edges with positive weight, stimulate or<br> activate next active node, and edges with negative weight, disable or inhibit the next connected<br> node (if it is active) ones.</p>
Data Pack fro VirSorter: mining viral signal from microbial genomic data
<p>This is the data pack for VirSorter, the publication of which by Roux et al. titled "<strong>VirSorter: mining viral signal from microbial genomic data</strong>" appeared in PeerJ on 2015-05-28 (<a href="https://doi.org/10.7717/peerj.985">doi:10.7717/peerj.985</a>).</p> <p>Most up-to-date tutorials and the code for VirSorter can be found at the GitHub repository <a href="https://github.com/simroux/VirSorter">https://github.com/simroux/VirSorter</a>.</p> <p>The original source of this data pack was here (last accessed 2018-02-03): <a href="http://datacommons.cyverse.org/browse/iplant/home/shared/imicrobe/VirSorter/virsorter-data.tar.gz">http://datacommons.cyverse.org/browse/iplant/home/shared/imicrobe/VirSorter/virsorter-data.tar.gz</a></p>
BRAIN Journal-Prediction of Thyroid Disease Using Data Mining Techniques-Figure 2. Attributes of the classification models used in the experiments
<p>The authors used for their experiments a data set (UCI, 2016) containing 756 records about persons with thyroid dysfunctions. The classification model has 22 attributes; the class attribute is the target and it has three possible values: hypothyroidism, hyperthyroidism and normal. The current data set was extracted and preprocessed from the original file. A description of the attributes used in the experiments is given in Figure 2 (an extract from thyroid.arff test file). </p>
BRAIN Journal-Prediction of Thyroid Disease Using Data Mining Techniques-Figure 3. KNIME Diagram
<p>The proposed KNIME diagram representing the data mining models is given in Figure 3. The nodes that constitute the model diagram are: ARFF Reader – the input node used to load the data set in arff format, Partitioning – the node with the role of data set partition (for training and for the validation of the classification model), Naive Bayes Learner and Decision Tree Learner – the nodes used to build the classification model, Naive Bayes Predictor and Decision Tree Predictor – the nodes used to validate the model, Scorer – the node reports a confusion matrix and the accompanying quality measures in its view, Normalizer – the data set are normalized to be able to apply the neural network models, Multilayer Perceptron and RBFNetwork – the nodes corresponding to the neural network classification models, Weka Predictor – a node implemented in Weka to validate the models. </p>
BRAIN Journal-Prediction of Thyroid Disease Using Data Mining Techniques-Figure 1. Factors that Affect Thyroid Function (The Institute for Functional Medicine, 2014)
<p> In Figure 1 are presented the main factors that affect the thyroid function. It is obvious that factors such as stress, infection, toxins, trauma and certain medication are directly responsible for the improper production of thyroid hormones. Symptoms identification and the early detection of abnormal values of thyroid hormones after clinical investigation will help in establishing the proper diagnostic and to prescribe the right medication. The patient must periodically evaluate his clinical state in order to receive the treatment as long as he needs it. </p>
BRAIN Journal-A New Challenge for Information Mining-Figure 4. Results of Weka's Clustering
<p>In the Figure 4 we show that, in a particular cluster, attributes are grouped in the "good" attribute of "Expertise with technology” with the "Low" attribute of "Student's performance" together. Thus, we can deduce that the level of Student's Performance is influenced by other factors over "Expertise with technology" of teacher. These factors can be searched inside the cluster, providing useful information to a significant exploration. These aspects are not deducible only by exploration through the portal and, for this reason, the clustering technique allows to user to navigate better during the search. </p>
BRAIN Journal-A New Challenge for Information Mining-Figure 5: New Approach Rich Data Exploration
<p>In the following figure (see Figure 5) it has represented a scheme of the new approach proposed to Rich Data Set's Exploration.</p> <p>Other experiments are running in order to validate our idea, both in order to optimize this clustering model by applying new algorithms and distance measures to the datasets presented here, and both applying these techniques to a different domain from the didactic one. Other experiments are also conducted to improve user exploration by skillfully combining multiple methods and exploration techniques through the application of a variety of models such as the Association Rule to extract hidden relationships and association rules between data and Artificial Neural Network mechanisms of learning applicable to classification and forecasting problems. </p>
BRAIN Journal-A New Challenge for Information Mining-Figure 3: Clustered Instances
<p> We tested the algorithm with different values of K, to find the optimal centroids. In general, as you know, there is no method for determining the exact value of K, but an accurate estimate can be obtained, for example, monitoring the value of the sum of squared error (SSE) for some values of k (for example 2, 4, 6, 8, etc.). The SSE is defined as the sum of the squared distance between each member of the cluster and its centroid. Mathematically, we can write (1): ( , ) (1) 1 2 K i c x i i SSE dist x c In our case we estimated in k = 8 the best number of cluster. We obtained the following clustered instances.</p>
BRAIN Journal-A New Challenge for Information Mining-Figure 2. A ScreenShot of L4All Portal
<p> Simple selection or complex selection operations, with boolean operators, are possible. Each widget shows the value of the attributes for the current state of the dataset with different visualization. The current set of objects is shown on a “canvas” (see Figure 2 - right side of the interface). Thanks to advanced Human-Computer Interaction mechanisms, the portal can support sophisticated exploration activities in the cycle . Based on L4All, a number of scientific investigations by different research groups took place: on the relation between different forms of group-work and inclusion, on digital storytelling and related benefits, etc. (Di Blas, Paolini, 2013; Falcinelli, 2012; Falcinelli, Laici, 2012). </p>
BRAIN Journal-A New Challenge for Information Mining-Figure 1. kinds of information needs (Wildemuth and Freund,2012)
<p>The taxonomy of tasks, related to the two different kinds of information needs is illustrated in Figure 1. </p> <p>In the precision-oriented information needs category, the task’s goal is to locate one resource and get information about its attributes or metadata while in the recall-oriented information needs category the task’s goal is to locate (and get information about) a set of resources. In this category we can distinguish goals that require accessing sets of resources just in groups, or in groups accompanied by count information for getting an overview of a set of resources, e.g. as in Faceted Dynamic Taxonomies (FDT). Furthermore, we may have goals that require more complex aggregated results like those provided by data warehouses. For instance, aggregations of arithmetic (min, max, average) and Boolean functions over the numeric attributes of the documents in the answers of free-text queries. Moreover, counts are computed and displayed over combinations (pairs, triples, quadruplets, etc.) of attributes (of grouping criteria in general). In comparison to OnLine Analytical Processing (OLAP) queries, in exploratory search the information demand in unknown a priori (in OLAP it is known and the schema is fixed) and the objective is not only to compute and see various aggregate values (e.g. sales per month and department), but also to support a flexible process for finding the desired individual resources (Tzitzikas et al., 2016).</p>
Data set for the paper "What are the Effects of History Length and Age on Mining Software Change Impact?"
<p>Data set for the paper What are the Effects of History Length and Age on Mining Software Change Impact?<br> by Leon Moonen, Thomas Rolfsnes, David Binkley and Stefano di Alesio.<br> In Journal of Empirical Software Engineering (EMSE), 2018, Springer. https://doi.org/10.1007/s10664-017-9588-z<br> Available from https://evolveit.bitbucket.io/publications/emse2018/</p> <p>Please cite this work by referring to the corresponding journal publication (a preprint is included in this package).</p> <p>The goal of Software Change Impact Analysis is to identify artifacts (typically source-code files or individual methods therein) potentially affected by a change. Recently, there has been increased interest in <em>mining</em> software change impact based on evolutionary coupling. A particularly promising approach uses association rule mining to uncover potentially affected artifacts from patterns in the system’s change history. Two main considerations when using this approach are the <em>history length</em>, the number of transactions from the change history used to identify the impact of a change, and <em>history age</em>, the number of transactions that have occurred since patterns were last mined from the history. Although history length and age can significantly affect the quality of mining results, few guidelines exist on how to best select appropriate values for these two parameters.</p> <p>In this paper, we empirically investigate the effects of history length and age on the quality of change impact analysis using mined evolutionary coupling. Specifically, we report on a series of systematic experiments using three state-of-the-art mining algorithms that involve the change histories of two large industrial systems and 17 large open source systems. In these experiments, we vary the length and age of the history used to mine software change impact, and assess how this affects precision and applicability. Results from the study are used to derive practical guidelines for choosing history length and age when applying association rule mining to conduct software change impact analysis. </p>
Method to assess the functional role of noisy brain signals by mining envelope dynamics
<p>Preprocessed envelope EEG features based on a spatial filter approach. The features were computed across multiple within-trial SVIPT events for a large hyperparameter space on data of an exemplary subject.</p> <p>The file "components.bsv" contains the preprocessed envelope features of all investigated configurations and provides underlying parameters as well as a relative path for the key ``record_dir'' to additional component information. Specifically, for each configuration the spatial filter, spatial activity pattern and the time-resolved within-trial envelope signal is provided under "records/". </p>
Mining Rule Violations in JavaScript Code Snippets
<p><strong>Content of this repository</strong><br> This is the repository that contains the scripts and dataset for the MSR 2019 mining challenge</p> <p>Github Repository with the software used : <a href="https://github.com/urielfcampos/linting-js-codesnippets">here</a>.<br> =======</p> <p><strong>DATASET</strong><br> The dataset was retrived utilizing google bigquery and dumped to a csv<br> file for further processing, this original file with no treatment is called jsanswers.csv, here we can find the following information :<br> 1. The Id of the question (PostId)<br> 2. The Content (in this case the code block)<br> 3. the lenght of the code block<br> 4. the line count of the code block<br> 5. The score of the post<br> 6. The title</p> <p>A quick look at this files, one can notice that a postID can have multiple rows related to it, that's how multiple codeblocks are saved in the database.</p> <p><strong>Filtered Dataset:</strong></p> <p><strong>Extracting code from CSV</strong><br> We used a python script called "ExtractCodeFromCSV.py" to extract the code from the original csv and merge all the codeblocks in their respective javascript file with the postID as name, this resulted in 336 thousand files.</p> <p><strong>Running ESlint</strong><br> Due to the single threaded nature of ESlint, we needed to create a script to run ESlint because it took a huge toll on the machine to run it on 336 thousand files, this script is named "ESlintRunnerScript.py", it splits the files in 20 evenly distributed parts and runs 20 processes of esLinter to generate the reports, as such it generates 20 json files.</p> <p><strong>Number of Violations per Rule</strong><br> This information was extracted using the script named "parser.py", it generated the file named "NumberofViolationsPerRule.csv" which contains the number of violations per rule used in the linter configuration in the dataset.</p> <p><strong>Number of violations per Category</strong><br> As a way to make relevant statistics of the dataset, we generated the number of violations per rule category as defined in the eslinter website, this information was extracted using the same "parser.py" script.</p> <p><strong>Individual Reports</strong><br> This information was extracted from the json reports, it's a csv file with PostID and violations per rule.</p> <p><strong>Rules</strong><br> The file Rules with categories contains all the rules used and their categories.</p> <p> </p>
Ontology based mining of pathogen-disease associations from literature
<p>This dataset contains a number of manually evaluated text mined pathogen-disease associations for the study described at</p> <p>doi: https://doi.org/10.1101/437558</p>
Webis Simulation Data Mining Bridge Models Corpus 2012 (Webis-SDMbridge-12)
<p>This corpus provides the simulation data mining community with a collection of 14641 bridge models and simulated behavior.</p> <p><strong>1. Folder "1-designs"</strong></p> <p>The text files in this directory should contain all information for the<br> independent variables any machine learning experiment. For reference, all 14641 IFC models are supplied in subfolders 001 to 147.</p> <p><strong>2. Folder "2-simulation"</strong></p> <p>This folder contains samples of the simulation output that may be viewed in Paraview (http://www.paraview.org). The original model contains the "Org" filename fragment, and the maximum and minimum behaviors are indicated with "Max" and "Min" filename fragments. Displacement, strain, and stress behaviors are all given. Only three of the 14641 models are given as the file sizes are<br> around 1.4 to 2.2 megabytes each. The complete data (approximately 81 gigabytes) can be regenerated and provided if necessary on request (email webis@medien.uni-weimar.de).</p> <p><strong>3. Folder "3-aggregation"</strong></p> <p>Maximum displacement, strain, and stress measurements are given in the text files individually, and together in the files with the "vtk" filename fragment. This data should be sufficient for the dependent variables of any machine learning experiment.</p>
Dataset and Data treatment for Data mining Raman Microspectroscopic Responses of Cells to Drugs in Vitro using Multivariate Curve Resolution-Alternating Least Squares
<p><strong>Matlab scripts for the simulation and treatment of Raman datasets obtained from time dependent experiments Using MCR-ALS.</strong></p> <p> </p> <p><strong>- SIMULATED DATA: </strong>Simulated data is obtained by adding spectra of artificially generated responses (weighted considering artificially generated time profiles) to an experimental cell spectrum (Initial component) Three Different Scenarios are generated. </p> <p>Spectral and time profiles are obtained from here: </p> <p> </p> <p><strong>- EXPERIMENTAL DATA: </strong>DOX dataset obtained from here</p> <p>https://doi.org/10.1002/jbio.201800328</p> <p> </p> <p> </p> <p><strong>- DATA ANALYSIS INSTRUCTIONS</strong></p> <p>Run <em>datatreatment.m</em></p>
Supplementary dataset for SRL Data Mine article
<p>Supplementary dataset for SRL Data Mine article by Milliner & Donnellan (2019). Titled: <em>Using Daily Observations from Planet Labs Satellite Imagery to Separate the Surface Deformation Between the July 4<sup>th </sup>M<sub>w</sub> 6.4 Foreshock and July 5<sup>th </sup>M<sub>w</sub> 7.1 Mainshock During the 2019 Ridgecrest Earthquake Sequence.</em></p>
Figure 3 in Effect of reed burning and precipitation on the breeding success of Great Reed Warbler, Acrocephalus arundinaceus, on a mining pond
Figure 3. Correlation between amount of precipitation and breeding success at Bager Pond, 2008–2011. Data points are Early and Late groups in 4 years.
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.