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.
35
datasets available to search
ShareScore release 0.9.0
Dataset results
35 results for “LSTM”
Dataset for Accuracy of Grid-Connected Photovoltaic Power Plant: A Novel Approach Using Hybrid Variational Mode Decomposition and CNN-LSTM Model
<p>This research paper introduces a deep learning hybrid model employing Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) for short-term photovoltaic (PV) solar energy forecasting.The proposed method integrates the Variational Mode Decomposition (VMD) algo-rithm with the CNN-LSTM model to predict PV power generation from a solar farm in Boussada, Algeria, from January 1, 2019, to December 31, 2020. The performance of the developed model is benchmarked against other deep learning models (VMD-CNN, VMD-LSTM, CNN-LSTM) across various time horizons (15, 30, and 60 minutes) to provide a comprehensive evaluation. Our findings exhibit greater performance of the developed model compared to other architectures, showcasing promising results in solar power forecasting. This research contributes to the main goal of enhancing EMS by providing accurate solar energy forecasts.</p>
Data Sets and Prediction Models Created using MLP, RNN and LSTM
<p>Binary Data Sets</p> <p>- 2018tbi219_shuffled3.csv and 2018tbi219_shuffled5.csv</p> <p>- these are stratified data sets that were able to produce prediction models with high prediction rates.</p> <p>Models.zip</p> <p>- this zip file contains the prediction models created using Keras Deep Learning Algorithms: MLP, RNN and LSTM</p> <p>Model Creation - Python Code Snippets</p> <p>- Code snippets for creating the prediction models</p>
LSTM-REG: regional gridded runoff dataset for northwest Russia based on Long Short-Term Memory (LSTM) networks
<p>LSTM-REG: regional gridded runoff dataset for northwest Russia.</p> <p>Model: LSTM.</p> <p>Geographical domain: 25–57°E; 55–70°N.</p> <p>Spatial resolution: 0.5°x0.5°.</p> <p>Temporal resolution: daily.</p> <p>Period: 1980-2016.</p>
Archival Datasets for SuperNova Artificial Inference by Lstm neural networks (SNAIL)
<p>The spectral-observation dataset (enclosed in the file archival_spec_observations.tar.gz) is comprised of 3091 observed spectra from 361 SNe Ia, largely contributed from CfA (Blondin et al. 2012), BSNIP (Silverman et al. 2012), CSP (Folatelli et al. 2013) and Supernova Polarimetry Program (Wang & Wheeler 2008; Cikota et al. 2019a; Yang et al. 2020).</p> <p>The spectral-template dataset (enclosed in the file archival_spec_templates.tar.gz) includes 361 spectral templates, each of them (covering -15 to +33d with wavelength from 3800 to 7200 A) was generated from the available spectroscopic observations of an individual SN via a LSTM neural network model.</p> <p>The auxiliary photometry dataset (enclosed in the file archival_phot_observations.tar.gz) provides the B & V light curves of these SNe (in total, 196 available SNe Ia), that were used to calibrate the synthetic B-V color of the observed spectra.</p> <p>In additional, the two master catalogs give the detailed information about the 361 SNe and their spectroscopic observations, respectively. </p> <p>These datasets are associated to the paper "Spectroscopic Studies of Type Ia Supernovae Using LSTM Neural Networks" (Hu et al. 2022, ApJ, accepted).</p>
Data for RAPPPID: Towards Generalisable Protein Interaction Prediction with AWD-LSTM Twin Networks
<p>Data for RAPPPID, a method for the Regularised Automative Prediction of Protein-Protein Interactions using Deep Learning.</p> <p>These datasets are in a format that RAPPPID is ready to read.<br> <br> <strong>Comparatives Dataset</strong><br> These datasets were derived from the STRING v11 <em>H. sapiens</em> dataset, according to the C1, C2, and C3 procedures outlined by Park and Marcotte, 2012. Negative samples are sampled randomly from the space of proteins not known to interact. See <a href="https://doi.org/10.1101/2021.08.13.456309">Szymborski & Emad</a> for details.<br> <br> <strong>Repeatability Datasets</strong><br> The following datasets are all derived from STRING in the manner as the comparatives dataset, but three different random seeds are used for drawing proteins.<br> <br> <strong>References</strong><br> Park,Y. and Marcotte,E.M. (2012) Flaws in evaluation schemes for pair-input computational predictions. Nat Methods, 9, 1134–1136.</p> <p>Szklarczyk, D., Gable, A. L., Lyon, D., Junge, A., Wyder, S., Huerta-Cepas, J., Simonovic, M., Doncheva, N. T., Morris, J. H., Bork, P., Jensen, L. J., and Mering, C. (2019). String v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Research, 47(D1), D607–D613.<br> <br> Szymborski,J. and Emad,A. (2021) RAPPPID: Towards Generalisable Protein Interaction Prediction with AWD-LSTM Twin Networks. bioRxiv https://doi.org/10.1101/2021.08.13.456309</p>
PREDICTING THE PERFORMANCE OF GREEN STORMWATER INFRASTRUCTURE USING MULTIVARIATE LONG SHORT-TERM MEMORY (LSTM) NEURAL NETWORK
<p>The expected performance of Green Stormwater Infrastructure (GSI) is typically quantified through numerical models based on hydrologic parameters and physics-based equations. With numerical models, the choice of a spatio-temporal discretization scheme for the computational domain is a strenuous task that requires extensive calibration and potentially lab-based parameters and experimentation. The performance of GSI has high temporal dynamics due to natural, anthropogenic, and climatic processes that are not well represented by the traditional physics-based hydrologic models, which are calibrated against only a few historical observations and have a user-defined and constrained set of computational outcomes. Deep learning-based predictive models, such as Long Short-Term Memory (LSTM) neural networks, offer an exciting opportunity to quantify GSI performance, accounting for its highly dynamic and constantly evolving nature by leveraging advancements in observational data. A LSTM regression can overcome some of the limitations associated with traditional hydrological models to aid the development of a fully data-informed GSI performance predictor. To demonstrate the LSTM and traditional model outcomes, both methods were applied to a rain garden in Villanova, PA, USA. Specifically, a LSTM model was used to predict the recession of ponded water depth in the rain garden using five years of observed data.</p>
Long short-term memory (LSTM) recurrent neural network for muscle activity detection
<p><strong>Background: </strong>The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning<br> from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological<br> patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors<br> is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to<br> detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle<br> activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.<br> </p> <p><strong>Methods: </strong>First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied<br> through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches,<br> i.e., the standard approach based on Teager–Kaiser Energy Operator (TKEO) and the traditional approach, used in<br> clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise<br> Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR<br> values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological<br> and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic<br> patients, and 6 neurological patients) were included in the analysis.</p> <p><strong>Results</strong>: The proposed algorithm overcomes the main limitations of the other tested approaches and it works<br> directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate<br> that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard<br> similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated<br> and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for<br> signals featuring a low to medium SNR.</p> <p><strong>Conclusions</strong>: The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The<br> validation carried out both on simulated and real signals, considering normal as well as pathological motor function<br> during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/<br> distinction of muscle activity from background noise in sEMG signals.</p> <p> </p>
Data for LSTM-certainty as EWS for CT
<p>Data for the paper "LSTM-certainty as EWS for CT"</p>
Prediction Result of Next Monochrome Ionogram frame using LSTM-CNN Model
<p>Video of next frame ionogram prediction result using simple LSTM-CNN model</p> <p>Paper published in The 9Th International Seminar on Aerospace Science and Technology ISAST 2022</p>
Streamflow Prediction in Human-Regulated Catchments Using Multiscale LSTM Modeling with Anthropogenic Similarities
<p>These codes are used in the paper entitled"Streamflow Prediction in Human-Regulated Catchments Using Multiscale LSTM Modeling with Anthropogenic Similarities" which is submitted to the Journal of Water Resources Research. The code for the differentiable parameter learning (DPL) model can be downloaded at https://doi.org/10.5281/zenodo.7091334. The code for LSTM to reproduce our analysis is available at <a href="https://github.com/neuralhydrology/neuralhydrology">https://github.com/neuralhydrology/neuralhydrology</a>. The SWORD database utilized in our study can be accessed at https://zenodo.org/records/10013982. The geometric dataset of the global river attribute information for every river reach, the values of all pressure indicators (DOF, DOR,SED, USE, RDD and URB) and the values for the CSI are available at https://doi.org/10.6084/m9.figshare.7688801.</p>
Smogseer: A Convolutional LSTM for forecasting air quality from Sentinel-5P data
<h1><strong>Training and checkpoint datasets </strong></h1> <h2><a href="#h_1501865622611722161313186" target="_blank" rel="noopener">S5PL2_5D.nc</a></h2> <p>This is the Sentinel-5P traning dataset for the Smogseer ConvLSTM model. The dataset was created using the xcube Sentinel Hub data store from the <a href="https://deepesdl.readthedocs.io/en/latest/datasets/datastores/#xcube-sentinel-hub-data-store">Deep Earth System Data Lab</a>.</p> <p>The dataset has the following characteristics:</p> <ul> <li>bbox= [68.137207,24.886436,84.836426,34.379713] #WGS84 // lon,lat,lon,lat</li> <li>res = (bbox[2]-bbox[0])/512 # ~3629m</li> <li>date_range = ['2019-01-01', '2023-12-31']</li> <li> <div>timesteps = '5D'</div> </li> </ul> <h2><a href="#h_4062378263291722161323566">X_val.npy</a></h2> <p>Validation feature data with shape: (74, 1, 291, 512, 6)</p> <ul> <li>74: dates</li> <li>1: time steps</li> <li>291: latitudes</li> <li>512: longitudes</li> <li>6: Features ['SO2', 'NO2', 'CH4', 'O3', 'CO', 'HCHO']</li> </ul> <h2><a href="#h_9861938573981722161330905">Y_val.npy</a></h2> <p>Validation target data with shape: (74, 1, 291, 512, 1)</p> <ul> <li>74: dates</li> <li>1: time steps</li> <li>291: latitudes</li> <li>512: longitudes</li> <li>6: Features ['SO2', 'NO2', 'CH4', 'O3', 'CO', 'HCHO']</li> </ul> <h2><a href="#h_321677095651722161353847">smogseer50.keras</a></h2> <p>Model weights for training the ConvLSTM with 50 epochs.</p> <h2><a href="#h_5931467847131722161401921">smogseer100.keras</a></h2> <p>Model weights for training the ConvLSTM with 10 epochs.</p>
Indonesian Foreign Policy towards Iran: Shia Hate speech on X social media with LSTM and SVM Analysis
<p>This table and figure are integral components of research on Shia hate speech on social media X, a critical issue in the context of identity politics in Indonesia and globally. This study is of paramount importance as it delves into the identity politics often exploited by politicians in Indonesia and around the world. The Shia community's support for President Jokowi in the first and second stages of the Election was met with hate speech from the opposition group. The study further investigates whether this Shia hate speech is linked to the government's policy towards Iran, a country known for its Shia ideology. The study is presented in three parts:<br>1. Table detailing the sentiment analysis process and results, which were conducted using advanced machine learning techniques such as SVM and LSTM. This approach significantly enhances the accuracy and reliability of the study's findings.<br>2. Figure in the form of a graph related to the study results and the results of comments from the Indonesian public about Shia.<br>3. This research is backed by a comprehensive dataset comprising public comments from Indonesia on Shia. This extensive data collection ensures the study's conclusions are thorough and reliable.</p> <p>4. Processing of machine learning</p>
LSTM
<p>This folder contains the result predicted by LSTM.</p>
Rezultati CNN, LSTM, RF, GRU, XGB modela za modeliranje dnevnih koncentracija čestica u zraku
<p>Rezultati CNN, LSTM, RF, GRU, XGB modela za modeliranje dnevnih koncentracija čestica u zraku u pogleu koeficijenta determinaciej i srednje apsolutne pogreške.</p>
Predicting time series of vegetation leaf area index across North America based on climate variables for land surface modeling using attention-enhanced LSTM
<p>We developed an attention-enhanced long and short memory (AELSTM) model for predicting vegetation LAI time series based on climatic data. The developed AELSTM model establishes the relationships between the time series of vegetation LAI and climatic variables. </p>
Demodulation Combining 1D-CNN and Bi-LSTM Network over Strong Solar Wind Turbulence Channel
<p>The data in this dataset is derived MATLAB simulation dataset by us to illustrate the GMSK signal demodualtion over strong solar wind turbulence using deep learing.<br> Disclaimer<br> The data provided in the files is provided as is. Despite our best efforts at filtering out potential issues, some information could be erroneous.<br> Description of the dataset<br> One file per is provided as a csv file with the following features:<br> train_dataset: Including data_kb2 and data_awgn. data_kb2 is the GMSK modulated fading signal data and lable data under the influence of strong solar wind turbulence, data_awgn is the GMSK modulated signal data and lable data under the influence of Gaussian white noise only.In which per mod_data and lable_data have 21000 csv file, respectively. And per csv file has 800 data. Among them ,the lable is the original binary number. The train_dataset is used to train neural network demodulator model.<br> test_dataset:Including test_data and test_lable.The test_data and test_lable have 6 file respectively. And they are used to test the trained neural network demodulator model.<br> test_data:<br> kb2_Tb0d5_m1d4: GMSK data at the BTb=0.5 , solar wind turbulence scintillation index m=1.4.<br> kb2_Tb0d5_m1d2:GMSK data at the BTb=0.5 , solar wind turbulence scintillation index m=1.2.<br> kb2_Tb0d3_m1d4:GMSK data at the BTb=0.3 , solar wind turbulence scintillation index m=1.4.<br> kb2_Tb0d3_m1d4: GMSK data at the BTb=0.3 , solar wind turbulence scintillation index m=1.2.<br> Awgn_Tb0d5:GMSK at data the BTb=0.5 under the influence of Gaussian white noise only.<br> Awgn_Tb0d5:GMSK data at the BTb=0.3 under the influence of Gaussian white noise only.<br> test_lable:<br> kb2_Tb0d5_m1d4: GMSK lable data at the BTb=0.5 , solar wind turbulence scintillation index m=1.4.<br> kb2_Tb0d5_m1d2:GMSK lable data at the BTb=0.5 , solar wind turbulence scintillation index m=1.2.<br> kb2_Tb0d3_m1d4:GMSK labe data at the BTb=0.3 , solar wind turbulence scintillation index m=1.4.<br> kb2_Tb0d3_m1d4: GMSK labe data at the BTb=0.3 , solar wind turbulence scintillation index m=1.2.<br> awgn_Tb0d5:GMSK lable data at the BTb=0.5 under the influence of Gaussian white noise only.<br> awgn_Tb0d5:GMSK labe data at the BTb=0.3 under the influence of Gaussian white noise only.<br> </p>
End-Century Daily Snow Water Equivalent (SWE) Projections with LSTM model
<p>CMIP5 climate models: CESM-CAM5 (CESM), CNRM-CM5 (CNRM), EC-EARTH (EC), HadGEM2-ES (HadGEM), MIROC5, and GFDL-ESM2M (GFDL). LOCA downscaled forcings are used as inputs to the LSTM model. 'RCP' stands for RCP8.5 and 'hist' for historical simulations. </p> <p>Corresponding code repository: https://github.com/ShihengDuan/code-SWE</p>
Predictive Modeling of Bearing Degradation: LSTM Neural Networks for Uncertainty Quantification
<p>These MATLAB codes are part of a research project focused on predicting bearing degradation through vibration measurements. The codes implement LSTM (Long Short-Term Memory) neural network models trained under different objectives, including uncertainty quantification and RMSE (Root Mean Square Error) minimization. The objective of the research is to compare the performance of these models in predicting bearing health and assessing the associated uncertainty.</p> <p><strong>Note:</strong> The current codes are under embargo access as the corresponding paper has been submitted to the ESCA 11 conference. The codes will be made openly accessible upon acceptance of the paper and during the presentation dates. Please cite our paper when using these codes.</p>
Concept Drift Datasets for - LSTM-SCCM: Long Short-Term Memory Stream Cruise Control Method for Automated Drift Adaptation
<p><strong>Datasets Guide:</strong></p> <p><strong>Drift Locations:</strong> Abrupt marks sudden drift onset. Incremental drift recurs every $K$ points. Gradual shows drift as a sequence of concepts c1 and c2.</p> <p><strong>E.D.</strong>: Euclidean distance between coefficients in space. </p> <p><strong>C-Start</strong>: Start Concept.</p> <p><strong>C-End</strong>: End Concept.</p> <p><strong>E.D. (Consec.)</strong>: E.D. between each two consecutive concepts in sequence.</p> <p> </p> <table style="border-collapse: collapse; width: 100.042%; height: 627px;"><colgroup><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"><col style="width: 12.4949%;"></colgroup> <tbody> <tr style="height: 58.7812px;"> <td style="height: 58.7812px;"><strong>Dataset</strong></td> <td style="height: 58.7812px;"><strong>Drift Type</strong></td> <td style="height: 58.7812px;"><strong>Data Points</strong></td> <td style="height: 58.7812px;"><strong>Dimensions</strong></td> <td style="height: 58.7812px;"><strong>Noise</strong></td> <td style="height: 58.7812px;"><strong>Drift Locations</strong></td> <td style="height: 58.7812px;"><strong>E.D</strong><br><strong>(C-Start</strong><br><strong>to C-End)</strong></td> <td style="height: 58.7812px;"><strong>E.D.</strong><br><strong>(Consec.)</strong></td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS1</strong></td> <td style="height: 19.5938px;">Abrupt</td> <td style="height: 19.5938px;">1k</td> <td style="height: 19.5938px;">2</td> <td style="height: 19.5938px;">10</td> <td style="height: 19.5938px;">500</td> <td style="height: 19.5938px;">128.05</td> <td style="height: 19.5938px;">128.05</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS2</strong></td> <td style="height: 19.5938px;">Abrupt</td> <td style="height: 19.5938px;">10k</td> <td style="height: 19.5938px;">10</td> <td style="height: 19.5938px;">20</td> <td style="height: 19.5938px;">5k</td> <td style="height: 19.5938px;">327.23</td> <td style="height: 19.5938px;">327.23</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS3</strong></td> <td style="height: 19.5938px;">Abrupt</td> <td style="height: 19.5938px;">20k</td> <td style="height: 19.5938px;">50</td> <td style="height: 19.5938px;">30</td> <td style="height: 19.5938px;">10k</td> <td style="height: 19.5938px;">344.95</td> <td style="height: 19.5938px;">344.95</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS4</strong></td> <td style="height: 19.5938px;">Abrupt</td> <td style="height: 19.5938px;">100k</td> <td style="height: 19.5938px;">500</td> <td style="height: 19.5938px;">50</td> <td style="height: 19.5938px;">50k</td> <td style="height: 19.5938px;">324.11</td> <td style="height: 19.5938px;">324.11</td> </tr> <tr style="height: 78.375px;"> <td style="height: 78.375px;"><strong>DS5</strong></td> <td style="height: 78.375px;">Incremental</td> <td style="height: 78.375px;">1k</td> <td style="height: 78.375px;">2</td> <td style="height: 78.375px;">10</td> <td style="height: 78.375px;">every 100</td> <td style="height: 78.375px;">399.93</td> <td style="height: 78.375px;">[4.9, 6.1, 7.9,10.5, 14.8, 22.2, 37.0, 74.0, 222.1]</td> </tr> <tr style="height: 97.9688px;"> <td style="height: 97.9688px;"><strong>DS6</strong></td> <td style="height: 97.9688px;">Incremental</td> <td style="height: 97.9688px;">10k</td> <td style="height: 97.9688px;">10</td> <td style="height: 97.9688px;">20</td> <td style="height: 97.9688px;">every 1k</td> <td style="height: 97.9688px;">1205.10</td> <td style="height: 97.9688px;">[14.8, 18.5, 23.9, 31.8, 44.6, 66.9, 111.5, 223.1, 669.5]</td> </tr> <tr style="height: 97.9688px;"> <td style="height: 97.9688px;"><strong>DS7</strong></td> <td style="height: 97.9688px;">Incremental</td> <td style="height: 97.9688px;">20k</td> <td style="height: 97.9688px;">50</td> <td style="height: 97.9688px;">30</td> <td style="height: 97.9688px;">every 2k</td> <td style="height: 97.9688px;">1439.39</td> <td style="height: 97.9688px;">[17.7, 22.2, 28.5, 38.0, 53.3, 79.9, 133.2, 266.5, 799.6]</td> </tr> <tr style="height: 78.375px;"> <td style="height: 78.375px;"><strong>DS8</strong></td> <td style="height: 78.375px;">Incremental</td> <td style="height: 78.375px;">100k</td> <td style="height: 78.375px;">500</td> <td style="height: 78.375px;">50</td> <td style="height: 78.375px;">every 10k</td> <td style="height: 78.375px;">1671.75</td> <td style="height: 78.375px;">[20.6, 25.7, 33.1, 44.2, 61.9, 92.8, 154.7, 309.5]</td> </tr> <tr style="height: 78.375px;"> <td style="height: 78.375px;"><strong>DS9</strong></td> <td style="height: 78.375px;">Gradual</td> <td style="height: 78.375px;">1k</td> <td style="height: 78.375px;">2</td> <td style="height: 78.375px;">10</td> <td style="height: 78.375px;">[250-c1, 100-c2, 100-c1, 200-c2, 100-c1, 250-c2]</td> <td style="height: 78.375px;">601.92</td> <td style="height: 78.375px;">[377.4, 399.9, 829.2, 829.2, 624.36]</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS10</strong></td> <td style="height: 19.5938px;">Gradual</td> <td style="height: 19.5938px;">10k</td> <td style="height: 19.5938px;">10</td> <td style="height: 19.5938px;">20</td> <td style="height: 19.5938px;">[2.5k-c1, 1k-c2, 1k-c1, 2k-c2, 1k-c1, 2.5k-c2]</td> <td style="height: 19.5938px;">2049.14</td> <td style="height: 19.5938px;">[1158.3, 1205.1, 1885.4, 1885.4, 2167.7]</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS11</strong></td> <td style="height: 19.5938px;">Gradual</td> <td style="height: 19.5938px;">20k</td> <td style="height: 19.5938px;">50</td> <td style="height: 19.5938px;">30</td> <td style="height: 19.5938px;">[5k-c1, 2k-c2, 2k-c1, 4k-c2, 2k-c1, 5k-c2]</td> <td style="height: 19.5938px;">1756.43</td> <td style="height: 19.5938px;">[1469.9, 1439.3, 1875.3, 1875.3, 1843.6]</td> </tr> <tr style="height: 19.5938px;"> <td style="height: 19.5938px;"><strong>DS12</strong></td> <td style="height: 19.5938px;">Gradual</td> <td style="height: 19.5938px;">100k</td> <td style="height: 19.5938px;">500</td> <td style="height: 19.5938px;">50</td> <td style="height: 19.5938px;">[25k-c1, 10k-c2, 10k-c1, 20k-c2, 10k-c1, 25k-c2]</td> <td style="height: 19.5938px;">1364.12</td> <td style="height: 19.5938px;">[2126.2, 2032.1, 1238.2, 1238.2, 1322.0]</td> </tr> </tbody> </table> <p> </p>
Wikipedia Dataset for "Structure Tree-LSTM: Structure-aware Attentional Document Encoders"
<p>The Wikipedia dataset collected for the paper "Structure Tree-LSTM: Structure-aware Attentional Document Encoders".</p> <p>Paper link: <a href="https://arxiv.org/abs/1902.09713">https://arxiv.org/abs/1902.09713</a></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.