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.
9
datasets available to search
ShareScore release 0.9.0
Dataset results
9 results for “Data-driven Methods”
Python functions -- cross-validation methods from a data-driven perspective
<p>This is the organized python functions of proposed methods in Yanwen Wang PhD research. Researchers can directly use these functions to conduct spatial+ cross-validation (SP-CV), dissimilarity quantification by adversarial validation (AVD), and dissimilarity-adaptive cross-validation (DA-CV). The description of how to run codes is in Readme.txt. The descriptions of functions are in functions.docx.</p>
Data from: A real data-driven simulation strategy to select an imputation method for mixed-type trait data
<p>Missing observations in trait datasets pose an obstacle for analyses in myriad biological disciplines. Considering the mixed results of imputation, the wide variety of available methods, and the varied structure of real trait datasets, a framework for selecting a suitable imputation method is advantageous. We invoked a real data-driven simulation strategy to select an imputation method for a given mixed-type (categorical, count, continuous) target dataset. Candidate methods included mean/mode imputation, k-nearest neighbour, random forests, and multivariate imputation by chained equations (MICE). Using a trait dataset of squamates (lizards and amphisbaenians; order: Squamata) as a target dataset, a complete-case dataset consisting of species with nearly completed information was formed for the imputation method selection. Missing data were induced by removing values from this dataset under different missingness mechanisms: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). For each method, combinations with and without phylogenetic information from single gene (nuclear and mitochondrial) or multigene trees were used to impute the missing values for five numerical and two categorical traits. The performances of the methods were evaluated under each missing mechanism by determining the mean squared error and proportion falsely classified rates for numerical and categorical traits, respectively. A random forest method supplemented with a nuclear-derived phylogeny resulted in the lowest error rates for the majority of traits, and this method was used to impute missing values in the original dataset. Data with imputed values better reflected the characteristics and distributions of the original data compared to complete-case data. However, caution should be taken when imputing trait data as phylogeny did not always improve performance for every trait and in every scenario. Ultimately, these results support the use of a real data-driven simulation strategy for selecting a suitable imputation method for a given mixed-type trait dataset.</p>
Automatic Featurization Aided Data-Driven Method for Estimating the Presence of Intermetallic Phase in Multi-Principal Element Alloys
<p><strong>Description:</strong></p> <p>There are two folders in the dataset:</p> <p><strong>(A. ) AutomaticFeaturizerMPEA.zip</strong> : </p> <p>AutomaticFeaturizerMPEA.pynb is an interactive computational environment developed in python programming language to compute the properties of Multi Principal-component Element Alloy (MPEA) system .</p> <p>The code present in the .ipynb file is capable of firstly extracting composition feature from the name of MPEA and then compute thermodynamic/physical and chemical properties using these composition features. The properties that can be automatically calculated and featurized by the code are: <br> 1. Valence Electron Concentration<br> 2. Average Melting Temperature<br> 3. Enthalpy of Mixing<br> 4. Entropy of Mixing<br> 5. Electronegativity<br> 6. Atomic size difference<br> 7. Omega parameter <br> 8. 41 elemental composition</p> <p>The primary source used for the calculation of these alloy properties are taken from two python libraries: "pymatgen" and "matminer". </p> <p>The AutomaticFeaturizerMPEA.pynb is not only capable of calculating an alloy's properties but also featurizes them along with the composition and export it as a .csv file for further machine learning training process. The AutomaticFeaturizerMPEA.pynb file consists of two parts:</p> <p>1. "Part 1": A sample set of 25 MPEAs is used to demonstarte how to calculate & featurize the porperties and composition of alloy, save the calculated values in a .csv file.<br> 2. "Part 2": The alloy property of a single MPEA "Ti0.8CoCrFeNiCu" is calculated using the same code, if one needs to calculate them for a single MPEA at a time (as in our GUI application IMCATHEA https://github.com/subediupadesh/IMCATHEA) </p> <p>The repository also consists two "CSV" files:</p> <p>1. "MPEA_data.csv" file is the sample set of 25 collected MEPA observations with their source and phase information in one hot encoding method for which we want to calculate their properties and featurize them.<br> 2. "Featurized_MPEA.csv" file is the processed ready to train file which consists of MPEA, their properties and composition featurized in special order. It is the final file generated by the AutomaticFeaturizerMPEA.pynb python file.</p> <p> </p> <p><strong>(B.) IMCATHEA.zip:</strong> </p> <p>IMCATHEA is a python based Graphical User Interface application capable of detecting the IM phase in a High Entropy Alloy or Multi Principal Element Alloy system using a Neural Network Algorithm.</p> <p>## For Linux User:<br> Python with following libraries are needed to run the GUI application: pymatgen (v2022.0.16), matminer (v0.7.4), tensorflow (v2.2.0), pandas (v1.3.4), numpy (v1.21.2), tkinter (v8.6), sklearn (v1.0.1).</p> <p>"IMCATHEA_GUI.py" also needs 4 extra supporitng files (icon, standardizations, and model) to operate, which will be made available from the author upon reasonable request. </p> <p><br> ## For Windows User:<br> Executable (.exe) file: </p> <p>User can run "IMCATHEA_GUI.exe" wihout any softwares to be installed.</p> <p><br> ## Procedure for using "IMCATHEA" GUI Application:</p> <p>Step 0. Open / Run "IMCATHEA_GUI.py" (for Linux users) & "IMCATHEA_GUI.exe" (for Windows users) file to open the GUI application</p> <p>Step 1. User need to select the No. of Elements/Components in the HEA where IM phase is to be detected, from the dropdown menu at the top left corner.<br> After selection of element size/number (from 2 to 10),<br> <br> Step 2. User can select each element of HEA, one at a time from the drop down menu generated just below "No. of Component" tab</p> <p>Step 3. After selection of each element a blank space is provided just at the right side of selected element tab where user need to enter the corresponding composition/elemental fraction of the element.</p> <p>Step 4. Repeat Step 2-3 until the last element of the HEA and it's composition/elemental fraction is entered.</p> <p>Step 5. Press "Detect IMC" tab to get the prediction if IM is present in the provided HEA or not along with the physical properties of the entered HEA displayed in the right side of the GUI application.</p> <p>Step 6. If user wants to detect the presence or absence of IM phase for another HEA, user can click on "Restart" tab at the right top side of GUI application to restart the application instantly.</p> <p><br> If the user makes errors while selecting any options from dropdown menu as suggested in Step 1,2,3,4 user can click on "Restart" tab at the right top side of GUI application to restart the application instantly and start the process for prediction again from Step 1.</p> <p>## Video (YouTube) Tutorial for using IMCATHEA:<br> The stepwise process to predict the phase for an example case of "CrNbTiZr" MPEA is shown in the YouTube video tutorial at: https://youtu.be/G3aHE1Wsmgk</p>
Data from: A real data-driven simulation strategy to select an imputation method for mixed-type trait data
Open the record for dataset details and reuse information.
Data from: Hierarchical power control of a large-scale wind farm by using a data-driven optimization method
<p><span>With the participation in automatic generation control (AGC), a large-scale wind farm should distribute the real-time AGC signal to numerous wind turbines (WTs). This easily leads to an expensive computation for a high-quality dispatch scheme, especially considering the wake effect among WTs. To address this problem, a hierarchical power control (HPC) is constructed based on the geographical layout and electrical connection of all the WTs. Firstly, the real-time AGC signal of the whole wind farm is distributed to multiple decoupled groups in proportion of their regulation capacities. Secondly, the AGC signal of each group is distributed to multiple WTs via the data-driven surrogate-assisted optimization, which can dramatically reduce the computation time with a small number of time-consuming objective evaluations. Besides, a high-quality dispatch scheme can be acquired by the efficient local search based on the dynamic surrogate. The effectiveness of the proposed technique is thoroughly verified with different AGC signals under different wind speeds and directions.</span></p>
Data from: Hierarchical power control of a large-scale wind farm by using a data-driven optimization method
Open the record for dataset details and reuse information.
Data-Driven Extract Method Recommendations: A Study at ING: Appendix
<p>The appendix of our FSE 2021 industry track paper.</p>
Comparative Analysis of Data-Driven Anomaly Detection Methods
This paper provides a review of three different advanced machine learning algorithms for anomaly detection in continuous data streams from a ground-test firing of a subscale Solid Rocket Motor (SRM). This study compares Orca, one-class support vector machines, and the Inductive Monitoring System (IMS) for anomaly detection on the data streams. We measure the performance of the algorithm with respect to the detection horizon for situations where fault information is available. These algorithms have been also studied by the present authors (and other co-authors) as applied to liquid propulsion systems. The trade space will be explored between these algorithms for both types of propulsion systems.
Rotor health monitoring combining spin tests and data-driven anomaly detection methods
Health monitoring is highly dependent on sensor systems that are capable of performing in various engine environmental conditions and able to transmit a signal upon a predetermined crack length, while acting in a neutral form upon the overall performance of the engine system. Efforts are under way at NASA Glenn Research Center through support of the Intelligent Vehicle Health Management Project (IVHM) to develop and implement such sensor technology for a wide variety of applications. These efforts are focused on developing high temperature, wireless, low cost, and durable products. In an effort to address technical issues concerning health monitoring, this article considers data collected from an experimental study using high frequency capacitive sensor technology to capture blade tip clearance and tip timing measurements in a rotating turbine engine-like-disk to detect the disk faults and assess its structural integrity. The experimental results composed at a range of rotational speeds from tests conducted at the NASA Glenn Research Center’s Rotordynamics Laboratory are evaluated and integrated into multiple data-driven anomaly detection techniques to identify faults and anomalies in the disk. In summary, this study presents a select evaluation of online health monitoring of a rotating disk using high caliber capacitive sensors and demonstrates the capability of the in-house spin system.
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.