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.
164
datasets available to search
ShareScore release 0.9.0
Dataset results
164 results for “prediction algorithms”
Predicted times of bow Shock crossings at Venus from the ESA/Venus Express mission, using spacecraft ephemerides and magnetic field data, with a predictor-corrector algorithm
<p><strong>CHARACTERISTICS</strong><br> Planet: <strong>Venus</strong><br> Radius: <strong>R<sub>V</sub> = 6051.8 km</strong> (volumetric mean planetary radius)<br> Spacecraft: <strong>ESA/Venus Express</strong><br> Spacecraft coordinates system: <strong>Venus Solar Orbital (VSO)</strong> equivalent to <em>Sun-State </em>coordinate system:</p> <ul> <li>+<em>X<sub>VSO</sub></em> points towards the Sun from the planet’s centre,</li> <li>+<em>Z<sub>VSO</sub></em> towards Venus’ North pole and perpendicular to the orbital plane defined as the <em>X<sub>VSO</sub></em>–<em>Y<sub>VSO</sub></em> plane passing through the centre of Venus,</li> <li><em>Y<sub>VSO</sub></em> completes the orthogonal system.</li> </ul> <p>Time span: <strong>01/04/2006 to 25/11/2014</strong><br> Total number N of candidate bow shock crossings in the database: <strong>N = 4950</strong><br> Number of quasi-parallel bow shock crossings: <strong>N<sub>||</sub> = 844</strong><br> Number of quasi-perpendicular bow shock crossings: <strong>N<sub><span class="math-tex">\(\perp\)</span></sub> = 4106</strong></p> <p><strong>ORIGINAL DATASETS USED</strong><br> The original Venus Express/MAG data repository on which these algorithms were applied is available on ESA's Planetary Science Archive system (PSA) at: https://archives.esac.esa.int/psa/ftp/VENUS-EXPRESS/MAG/. For this study, 1-Hz magnetic field data was used.</p> <p><strong>METHOD</strong><br> To construct this database from the original datasets above, the predictor and predictor-corrector algorithms used are described for the Mars case in:<br> Simon Wedlund, C., Volwerk, M., Beth, A., Mazelle, C., Möstl, C., Halekas, J., Gruesbeck, J. and Rojas-Castillo, D., (2021), A Fast Bow Shock Location Predictor-Estimator From 2D and 3D Analytical Models: Application to Mars and the MAVEN mission, <em>Journal of Geophysical Research</em>, <strong>127</strong>, e2021JA029942. <a href="https://doi.org/10.1029/2021JA029942">https://doi.org/10.1029/2021JA029942</a></p> <p>They consist of two consecutive steps: </p> <ol> <li>Predictor geometric algorithm based on 2D or 3D existing fits for prediction of the Venus bow shock position. The original fits were taken from 2D conic fits in the plane <span class="math-tex">\(\left(X_\text{VSO}, \sqrt{Y_\text{VSO}^2+Z_\text{VSO}^2}\right)\)</span>performed on the datasets of <strong>Persson et al. (2023)</strong>, Venusian bow shock crossings manually identified from measurements by the ASPERA-4 and MAG instruments onboard Venus Express, <em>Zenodo</em> (<a href="http://doi.org/10.5281/zenodo.7679677">https://doi.org/10.5281/zenodo.7679677</a>).</li> <li>Corrector algorithm based on magnetic field measurements.</li> </ol> <p>We also provide the angle between the average Interplanetary Magnetic Field (IMF) vector upstream of the shock and the shock normal, noted <span class="math-tex"><em>θ</em><sub><em>B</em><em>n</em></sub></span> (ThetaBn). Assuming a locally smooth shock surface, this gives a first indication of the geometry of the shock, so that:</p> <ul> <li><span class="math-tex">45<sup>∘</sup><<em>θ</em><sub><em>B</em><em>n</em></sub><135<sup>∘</sup></span>: quasi-perpendicular shock condition</li> <li><span class="math-tex"><em>θ</em><sub><em>B</em><em>n</em></sub>≤45<sup>∘</sup> and <em>θ</em><sub><em>B</em><em>n</em></sub><span class="math-tex">\(\geq\)</span>135<sup>∘</sup></span>: quasi-parallel shock condition</li> </ul> <p>Uncertainty on these angles is estimated to be ± 5º. </p> <p>For details, see <strong>Simon Wedlund et al. (2022)</strong> above, §2.3 pp. 10-12.</p> <p><strong>VARIABLES DESCRIPTION</strong></p> <p>This database contains the following ASCII variables:</p> <ul> <li>Bow shock times in Venus Express' database (1-s resolution): <em>T</em><sub>bs</sub></li> <li>Venus Solar Orbital coordinates of the shock, in units of Venus radius <em>R</em><sub>V </sub>(<em>R</em><sub>V</sub> = 6051.8 km):<br> <em>X<sub>VSO</sub></em>,<sub> </sub><em>Y<sub>VSO</sub></em>, <em>Z<sub>VSO</sub></em> and Euclidean distance <span class="math-tex">\(R_{VSO} = \sqrt{X_{VSO}^2 + Y_{VSO}^2 + Z_{VSO}^2}\)</span> (in <em>R<sub>V</sub></em>)</li> <li>Solar Zenith angle in degrees: <em>SZA</em> = <span class="math-tex">\(\tan^{-1}{Y_{VSO}^2+Z_{VSO}^2 \over X_{VSO}^2}\)</span> (in º) </li> <li>Angle between average B-field direction and shock normal assuming a smooth shock surface <span class="math-tex">\(\theta_{Bn}\)</span> (ThetaBn, in º, calculated with atan2(norm(cross(<strong>B</strong>,<strong>ñ</strong>),dot(<strong>B</strong>,<strong>ñ</strong>)), with <strong>B</strong> the magnetic field vector and <strong>ñ</strong> the vector normal to the shock surface): <ul> <li>45 < ThetaBn < 135 deg: quasi-<span class="math-tex">\(\perp\)</span> shock</li> <li>ThetaBn <span class="math-tex">\(\leq\)</span> 45 deg & ThetaBn <span class="math-tex">\(\geq\)</span> 135 deg: quasi-|| shock</li> </ul> </li> <li>Interplanetary Magnetic Field (IMF) upstream average vector in VSO coordinates, <em>B<sub>x</sub></em>, <em>B<sub>y</sub></em>, <em>B<sub>z</sub></em> (in nT).</li> <li>Flag for direction of crossing: <ul> <li>flag = 0: magnetosheath <span class="math-tex">\(\longrightarrow\)</span> solar wind (2447 events)</li> <li>flag = 1: solar wind <span class="math-tex">\(\longrightarrow\)</span> magnetosheath (2503 events)</li> </ul> </li> </ul> <p><strong>WARNING</strong></p> <ol> <li>This version of the database is currently in a preliminary stage of application and, as such, is not fully tested. Solar wind upstream magnetic field values (IMF) are given only as a first approximation for each orbit segment. See point 2 for caveats. For carefully manually picked shock crossings, the user is referred to the database of:<br> <strong>Persson et al. (2023)</strong>, Venusian bow shock crossings manually identified from measurements by the ASPERA-4 and MAG instruments onboard Venus Express, <em>Zenodo</em> (<a href="http://doi.org/10.5281/zenodo.7679677">https://doi.org/10.5281/zenodo.7679677</a>)</li> <li>This database is based on an automatic statistical geometrical estimate, further refined by constraints on magnetic fields. This is aimed at giving a first approximation of the shock area times in the Venus Express data. It is particularly suited to statistical studies and region identification in the Venus Express datasets. As such, this database should be used as a <em>first indicator</em> of the shock location, and <em>with</em> <em>caution</em>: it <strong>CANNOT</strong>, and <strong>WILL NOT </strong>substitute, especially in case studies, for a careful analysis of the full magnetometer and plasma bow shock signatures. Moreover, the algorithm is optimised for detecting the first disturbance observed in the magnetic field immediately ahead of the shock's foot (in the foreshock area), and not for the detection of other structures in the shock, such as the shock ramp. The "shock" location is therefore given here with typical uncertainties of about 0.040 R<sub>V</sub> (with R<sub>V</sub> = 6051.8 km, i.e., about 250 km in the radial direction). Finally, for multiple shock crossings, the algorithm chooses the first occurrence of the shock starting from the undisturbed solar wind.</li> </ol> <p>Current formatting optimised for MATLAB.</p> <p><strong>ACKNOWLEDGEMENTS</strong><br> C. Simon Wedlund and M. Volwerk thank the Austrian Science Fund (FWF) project P32035-N36. </p> <p><strong>LICENSE AND RIGHTS</strong><br> This database is shared under a Creative Commons CC-BY-4.0 license.</p> <p>Version 1 (c) Cyril Simon Wedlund @ Space Research Institute of Graz (IWF), <br> Austrian Academy of Sciences, 2022-10-05<br> Contact email: cyril.simon.wedlund@gmail.com</p>
Predicted times, spatial coordinates of bow shock crossings and shock geometry at Mars from the NASA/MAVEN mission, using spacecraft ephemerides and magnetic field data, with a predictor-corrector algorithm
<p><strong>CHARACTERISTICS</strong><br>Planet: <strong>Mars</strong><br>Radius: <strong>R<sub>M</sub> = 3389.5 km</strong> (volumetric mean planetary radius)<br>Spacecraft: <strong>NASA/Mars Atmosphere and Volatile Evolution (MAVEN)</strong><br>Spacecraft coordinates system: <strong>Mars Solar Orbital (MSO)</strong> equivalent to <em>Sun-State </em>coordinate system:</p> <ul> <li>+<em>X<sub>MSO</sub></em> points towards the Sun from the planet’s centre,</li> <li>+<em>Z<sub>MSO</sub></em> towards Mars’ North pole and perpendicular to the orbital plane defined as the <em>X<sub>MSO</sub></em>–<em>Y<sub>MSO</sub></em> plane passing through the centre of Mars,</li> <li><em>Y<sub>MSO</sub></em> completes the orthogonal system.</li> </ul> <p>Time span: <strong>01/11/2014 to 30/04/2024</strong> (Mars Years MY32 to MY36 included, part of MY37).<br>Total number N of candidate bow shock crossings in the database: <strong>N = 20107</strong></p> <p><strong>ORIGINAL DATASETS USED</strong><br>The original MAVEN/MAG data repository on which these algorithms were applied is available on NASA's Planetary Data System (PDS) at <a href="https://doi.org/10.17189/1414178">https://doi.org/10.17189/1414178</a>. For this study, 1-Hz magnetic field data was used.</p> <p><strong>METHOD</strong><br>To construct this database from the original datasets above, the predictor and predictor-corrector algorithms used are described in:<br>Simon Wedlund, C., Volwerk, M., Beth, A., Mazelle, C., Möstl, C., Halekas, J., Gruesbeck, J. and Rojas-Castillo, D., (2022), A Fast Bow Shock Location Predictor-Estimator From 2D and 3D Analytical Models: Application to Mars and the MAVEN mission, <em>Journal of Geophysical Research</em>, <strong>127</strong>, 1-33, e2021JA029942, <a href="https://doi. org/10.1029/2021JA029942">https://doi. org/10.1029/2021JA029942</a>. </p> <p>Also available at: <a href="https://doi.org/10.1002/essoar.10507942.1">https://doi.org/10.1002/essoar.10507942.1 </a> and as arXiv e-print: <a href="https://doi.org/10.48550/arXiv.2109.04366">https://doi.org/10.48550/arXiv.2109.04366</a></p> <p>These algorithms consist of two consecutive steps: </p> <ol> <li>Predictor geometric algorithm based on J. Gruesbeck's 3D model (<a href="https://doi.org/10.1029/2018JA025366">Gruesbeck et al. 2018</a>) for prediction of Mars bow shock position</li> <li>Corrector algorithm based on magnetic field measurements (magnitude and fluctuations).</li> </ol> <p><strong>REMARK ON VERSIONS</strong><br>From Version 3 onwards, we also provide the angle between the average Interplanetary Magnetic Field (IMF) vector upstream of the shock and the shock normal, noted \(\theta_{Bn}\)(ThetaBn). Assuming a smooth shock surface and the 3D model of Gruesbeck et al. (2018, all points), this gives a first indication of the geometry of the shock, so that:</p> <ul> <li>45<sup>∘</sup><<em>θ</em><sub><em>B</em><em>n</em></sub><135<sup>∘</sup>: quasi-perpendicular shock condition</li> <li><em>θ</em><sub><em>B</em><em>n</em></sub>≤45<sup>∘</sup> and <em>θ</em><sub><em>B</em><em>n</em></sub>≥135<sup>∘</sup>: quasi-parallel shock condition</li> </ul> <p>Uncertainty on these angles is estimated to be ± 5º. </p> <p>From Version 4 onwards, we also added the solar longitude Ls (in degrees).</p> <p>For details, see Simon Wedlund et al. (2022) above, §2.3 pp. 10-12. Note that due to minor adjustments in the code, some of the ThetaBn angles calculated here for the examples of Fig. 6 in Simon Wedlund et al. (2022) may slightly differ from the values quoted in the paper.</p> <p><strong>VARIABLES DESCRIPTION</strong><br>This database contains the following ASCII variables:</p> <ul> <li>Bow shock times in MAVEN's database (1-s resolution): <em>T</em><sub>bs</sub></li> <li>Mars Solar Orbital coordinates of the shock, in units of Mars radius <em>R</em><sub><em>M</em> </sub>(<em>R<sub>M</sub></em> = 3389.5 km):<br><em>X<sub>MSO</sub></em>,<sub> </sub><em>Y<sub>MSO</sub></em>, <em>Z<sub>MSO</sub></em> and Euclidean distance \(R_{MSO} = \sqrt{X_{MSO}^2 + Y_{MSO}^2 + Z_{MSO}^2}\) (in <em>R<sub>M</sub></em>)</li> <li>Solar Zenith angle in degrees: <em>SZA</em> = \(\tan^{-1}{Y_{MSO}^2+Z_{MSO}^2 \over X_{MSO}^2}\) (in º) </li> <li>Angle between average B-field direction and shock normal assuming a smooth shock surface \(\theta_{Bn}\) (ThetaBn, in º) <ul> <li>45 < ThetaBn < 135 deg: quasi-⊥ shock</li> <li>ThetaBn ≤45 deg & ThetaBn ≥ 135 deg: quasi-|| shock</li> </ul> </li> <li>Solar longitude Ls, in degrees.</li> <li>Flag for crossing: <ul> <li>sheath \(\longrightarrow\) solar wind, flag = 0.</li> <li>solar wind \(\longrightarrow\) sheath, flag = 1.</li> </ul> </li> </ul> <p><strong>WARNING</strong><br>This database is based on an automatic statistical geometrical estimate, further refined by constraints on magnetic field. It is aimed at giving a first approximation of the shock area times in the MAVEN data. It is particularly suited to statistical studies and region identification in the MAVEN datasets. As such, this database should be used as a <em>first indicator</em> of the shock location, and <em>with</em> <em>caution</em>: it <strong>CANNOT</strong>, and <strong>WILL NOT </strong>substitute, especially in case studies, for a careful analysis of the full magnetometer and plasma suite bow shock signatures. Moreover, the algorithm is optimised for detecting the first disturbance observed in the magnetic field immediately ahead of the shock's foot (in the foreshock area), and not for the detection of other structures in the shock, such as the shock ramp. The "shock" location is therefore given here with typical uncertainties of about 0.075 R<sub>M</sub> (with R<sub>M</sub> = 3389.5 km, i.e., about 250 km in the radial direction). Finally, for multiple shock crossings, the algorithm chooses the first occurrence of the shock starting from the undisturbed solar wind.</p> <p>Current formatting optimised for MATLAB.</p> <p><strong>ACKNOWLEDGEMENTS</strong><br>C. Simon Wedlund and M. Volwerk thank the Austrian Science Fund (FWF) project P32035-N36. C. Möstl thanks the Austrian Science Fund FWF projects P31659-N27, P31521-N27. A. Beth thanks the Swedish National Space Agency (SNSA) and its support with the grant 108/18. This database was notably used to add to the Helio4Cast database which monitors solar wind parameters in the solar system (<a href="https://doi.org/10.6084/m9.figshare.6356420">https://doi.org/10.6084/m9.figshare.6356420</a>). Helio4Cast is available at <a href="http://www.helioforecast.space/icmecat">www.helioforecast.space/icmeca</a>t and <a href="http://www.helioforecast.space/sircat">www.helioforecast.space/sircat</a>. </p> <p><strong>LICENSE AND RIGHTS</strong><br>This database is shared under a Creative Commons CC-BY-4.0 license.</p> <p>Version 1 (c) Cyril Simon Wedlund @ Space Research Institute of Graz (IWF), <br> Austrian Academy of Sciences (ÖAW), 2021-09-08<br>Version 2 (c) CSW @ ÖAW/IWF, 2021-11-30 -- Addition of R_MSO and SZA<br>Version 3 (c) CSW @ ÖAW/IWF, 2022-02-09 -- Addition of ThetaBn<br>Version 4 (c) CSW @ ÖAW/IWF, 2025-03-20 -- Addition of Ls, Bx, By, Bz and Bt.</p> <p> </p> <p><br>Contact email: cyril.simon.wedlund@gmail.com</p>
Chromatin accessibility data for the CRISPRai prediction algorithm implemented in crisprScore
<p>Chromatin accessibility data for the CRISPRai prediction algorithm implemented in crisprScore; see https://github.com/crisprVerse/crisprScore for more detail.</p> <p> </p>
Datasets for "Advancing Drug-Target Interactions Prediction: Leveraging a Large-Scale Dataset with a Rapid and Robust Chemogenomic Algorithm"
<p>All datasets required to reproduce the results of publication "Drug-Target Interactions Prediction at Scale: the Komet Algorithm with the LCIdb Dataset"</p>
PERFORMANCE OF MACHINE LEARNING ALGORITHMS FOR LUNG CANCER PREDICTION: A COMPARATIVE STUDY
<p>This study compares the performance of five machine learning algorithms—logistic regression, support vector machines, random forests, gradient boosting, and neural networks—for lung cancer prediction using demographic, lifestyle, and medical data from the UCI Machine Learning Repository. Gradient boosting and random forests achieved the highest accuracy (89% and 87%, respectively) and AUC-ROC scores (0.93 and 0.92), while neural networks reached 90% accuracy but presented interpretability limitations. Key predictors included smoking history, chronic disease, and respiratory symptoms, aligning with established risk factors. Ensemble methods, particularly gradient boosting and random forests, provided an optimal balance of accuracy and interpretability, highlighting their potential for clinical applications in early lung cancer detection.</p>
Explaining human mobility predictions through a pattern matching algorithm
<p>The name of the file indicate information:<br> {type of sequence}_{type of measure}_{sequence properites}_{additional information}.csv</p> <p>{type of sequence} - 'synth' for synthetic or 'london' for real mobility data from London, UK.<br> {type of measure} - 'r2' for R-squared measure or 'corr' for Spearman's correlation<br> {sequence properties} - for synthetic data there are three types of sequences, described in the research article (random, markovian, nonstationary). For real mobility data this part includes information about data processing parameters: (...)_london_{type of mobility sequence}_{DBSCAN epsilon value}_{DBSCAN min_pts value}. {type of mobility sequence} is 'seq' for next-place sequences and '30min' or '1H' for the next time-bin sequences and indicate the size of the time-bin.<br> Files with 'predictability' at the end of the file contain R-squared and Spearman's correlation of measures calculated in relation to the predictability measure.</p> <p>R2 files include values of R-squared for all types of modelled regression functions.<br> 'line' indicates {y = ax + b} for single variable and {y = ax + by + c} for two variables.<br> 'expo' indicates {y = a*x^b + c} for single variable and {y = a*x^b + c*y^d + e} for two variables<br> 'log' indicates {y = a*log(x*b) + c} for single variable and {y = a * x + c * log(y) + e + d*x * log(y)} for two variables.<br> 'logf' indicates {y = a*log(x) + c * log(y) + e + b*log(x) * log(y)} for two variables</p>
Figure 5 in Evaluation of geostatistical method and hybrid Artificial Neural Network with imperialist competitive algorithm for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumber field of Behbahan, Iran
Figure 5. Moving colonies to imperialist in culture and language axes (AtashpazGargari et al. 2008).
Figure 2 in Evaluation of geostatistical method and hybrid Artificial Neural Network with imperialist competitive algorithm for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumber field of Behbahan, Iran
Figure 2. Generalized semivariogram showing the range of spatial dependence, nugget effect (C0) variability associated with spatial dependence (C), and sill (C + C0).
Figure 5 in Hybrid neural network with genetic algorithms for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumbers field of Ramhormoz, Iran
Figure 5. Tetranychus urticae distribution maps in actual (b, d and f) and classified conditions by MLPNN (c, e and a). The maps of a, c, e and b, d, f have been drawn according to economic threshold of 4, 8 and 12, respectively.
Assessing predictive performance of supervised machine learning algorithms for a diamond pricing model
<p>The diamond is 58 times harder than any other mineral in the world, and its elegance as a jewel has long been appreciated. Forecasting diamond prices is challenging due to nonlinearity in important features such as carat, cut, clarity, table, and depth. Against this backdrop, the study conducted a comparative analysis of the performance of multiple supervised machine learning models (regressors and classifiers) in predicting diamond prices. Eight supervised machine learning algorithms were evaluated in this work including Multiple Linear Regression, Linear Discriminant Analysis, eXtreme Gradient Boosting, Random Forest, k-Nearest Neighbors, Support Vector Machines, Boosted Regression and Classification Trees, and Multi-Layer Perceptron. The analysis is based on data preprocessing, exploratory data analysis (EDA), training the aforementioned models, assessing their accuracy, and interpreting their results. Based on the performance metrics values and analysis, it was discovered that eXtreme Gradient Boosting was the most optimal algorithm in both classification and regression, with a R<sup>2</sup> score of 97.45% and an Accuracy value of 74.28%. As a result, eXtreme Gradient Boosting was recommended as the optimal regressor and classifier for forecasting the price of a diamond specimen.</p>
Figure 3. Distribution of Q3 values-Secondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm
<p>The estimated accuracy for the α- helices (QH), β- strands (QE), C-coil states (QC), and three<br> state together (Q3) for the system is shown in Figure 3.</p>
Figure 2. PAM250 matrix for the encoded sequence-Secondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm
<p>The PAM matrix (Dayhoff et al., 1978) describes the probability that original amino acid<br> will be replaced by another amino acid over a defined evolutionary interval. The unit of<br> evolutionary divergence is defined as the interval in which 1% of the amino acids have been<br> changed between two sequences. The work uses PAM250, which assumes the occurrence of 250-<br> point mutations per 100 amino acids.<br> So, for the given the protein sequence GIVEQCCASVCSLYQLENYCN, A will be replaced<br> by 1 -3 0 1 -3 -1 0 5 -2 -3 -4 -2 -3 -5 0 1 0 -7 -5 -1 as shown in Figure 2.</p>
Figure 1: Snapshot of the CB396 dataset-Secondary Structure Prediction of Protein using Resilient Back Propagation Learning AlgorithmSecondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm
<p>The dataset used for this work is CB396. This dataset contains 396 non-redundant sequences<br> derived from the 3Dee database created by Cuff and Barton (Cuff & Barton, 1999). It contains 396<br> proteins with their respective secondary structure as shown in Figure 1.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 18. Drawing of the time series for males and females of primary stage students and its prediction)
<p>Note that the Tabulated value equals 3.841 while the Q value is less than Tabulated value, so it takes the Null Hypothesis which manifests that the emptiness of the evaluated model out of the contrast in accordance trouble. It's possible to notice that the two parameters functions (Autocorrelation and Partial correlation Functions) of the residues for male females primary stage, in which the residues value is located within confidence interval limits, which means the residues series is random and the evaluated model is good and convenient as it is presented.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 17. Drawing of the time series for females of primary stage students and its prediction
<p>It's possible to notice that the two parameters functions (Autocorrelation and Partial correlation Functions) of the residues for male females primary stage, in which the residues value is located within confidence interval limits, which means the residues series is random and the evaluated model is good and convenient as it is presented.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 16. Drawing of the time series for males of primary stage students and its prediction
<p>It's possible to notice that the two parameters functions (Autocorrelation and Partial correlation Functions) of the residues for male females primary stage, in which the residues value is located within confidence interval limits, which means the residues series is random and the evaluated model is good and convenient as it is presented.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 15. Drawing of autocorrelation function and partial correlation of the residues for males and females primary stage students
<p>After diagnosing and evaluating the models, the accommodating and the sufficiency of the models must be checked for males and females of primary stage students, through applying the compute (Ljung-Box Q) to check the model accommodation on the Function level 0.05 so the Q value occurs of males and females of primary stage students: Ljung-Box Q' = 1.10306, With p-value = P(Chi-square(1) > 1.10306) = 0.2936 Note that the Tabulated value equals 3.841 while the Q value is less than Tabulated value, so it takes the Null Hypothesis which manifests that the emptiness of the evaluated model out of the contrast in accordance trouble. It's possible to notice that the two parameters functions (Autocorrelation and Partial correlation Functions) of the residues for male females primary stage, in which the residues value is located within confidence interval limits, which means the residues series is random and the evaluated model is good and convenient as it is presented.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 13. Drawing of autocorrelation Function and partial correlation of the residues for primary stage males students
<p>It's possible to notice the two parameters functions (Autocorrelation and Partial correlation Functions) of the residues for males primary stage, in which the residues value is located within the confidence interval limits which means the residues series is random and the Evaluated Model is good and convenient as it is presented.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm- Figure 12. Drawing of autocorrelation function and partial correlation for females primary stage students
<p>We use the Unit Radix Dickey-Fuller Test to ensure the series’ stability. The results are: Dickey-Fuller Test Estimated Value = 0.369693, Statistic Test =1.01829, P-Value=0.9194 We notice from the values above P-Value = 0.9194 on the abstract level of 0.05 which leads to accepting the Null Hypothesis and refusing the Alternative Hypothesis (Existence of a Radix Unit) implies that the time series is instable. By taking the first difference, we notice that the stability of the time series has been achieved. See Figure 11.</p>
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 11. Drawing the time series for males and females primary stage after the First difference
<p>We use the Unit Radix Dickey-Fuller Test to ensure the series’ stability. The results are: Dickey-Fuller Test Estimated Value = 0.369693, Statistic Test =1.01829, P-Value=0.9194 We notice from the values above P-Value = 0.9194 on the abstract level of 0.05 which leads to accepting the Null Hypothesis and refusing the Alternative Hypothesis (Existence of a Radix Unit) implies that the time series is instable. By taking the first difference, we notice that the stability of the time series has been achieved. See Figure 11.</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.