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.
89
datasets available to search
ShareScore release 0.7.1
Dataset results
89 results for “Genetic algorithm”
Experimental Data Sets for the study "Benchmarking a $(\mu+\lambda)$ Genetic Algorithm with Configurable Crossover Probability"
<p>This is the experimental result of the study "Benchmarking a (μ+λ) Genetic Algorithm with Configurable Crossover Probability". A novel (μ+λ) GA is proposed and benchmarked, in which we stochastically determine whether to apply the crossover operator either for each individual or generation with a crossover probability <span class="math-tex">\(p_c\)</span>. This data set consists of two parts:</p> <ol> <li>The results of (μ+λ) GA on 25 pseudo-Boolean problems defined in <em>IOHprofiler </em>(<a href="https://iohprofiler.github.io/">https://iohprofiler.github.io/</a>) with the following setup: <span class="math-tex">\(\mu \in \{10, 50, 100\}, \lambda \in \{1, \lceil\mu/2\rceil, \mu\}, p_c\in\{0, 0.5\}.\)</span> <ul> <li>'IOHprofiler_Problems_standard_bit_mutation.csv' --> the (μ+λ) GA with standard bit mutation.</li> <li>'IOHprofiler_Problems_fast_mutation.csv' --> the (μ+λ) GA with fast mutation.</li> </ul> </li> <li>The results of (μ+λ) GA on OneMax and LeadingOnes problems with the following setup: <span class="math-tex">\(n \in \{64,100,150,200,250,500\}, \mu \in \{2,3,5,8,10,20,30,...,100\}, \\ \lambda \in \{1, \lceil \mu/2 \rceil, \mu\}, \text{and }p_c \in \{0.1 k \mid k \in [0..9]\}\cup\{0.95\}.\)</span> <ul> <li>'OneMax_raw.csv' --> the fixed-target running time/first hitting time from 100 independent runs for target values in <span class="math-tex">\([1..n]\)</span>.</li> <li>'OneMax_summary.csv' --> the mean, median, standard deviation, some quantiles, expected running time (ERT), the number of successful runs, and the success rate from 100 independent runs for target values in <span class="math-tex">\([1..n]\)</span>.</li> <li>'LeadingOnes_raw.csv' --> the same with 'OneMax_raw.csv' for LeadingOnes.</li> <li>'LeadingOnes_summary.csv' --> the same with 'OneMax_summary.csv' for LeadingOnes.</li> </ul> </li> </ol> <p><strong>Contact</strong>: if you have any questions or suggestions, please feel free to contact <a href="https://www.universiteitleiden.nl/en/staffmembers/furong-ye#tab-1">Furong Ye</a> or <a href="http://www-ia.lip6.fr/~doerr/">Carola Doerr</a>.</p>
An Experimental Study of Operator Choices in the (1+(λ,λ)) Genetic Algorithm
<p>This dataset contains experimental results that accompanies the same-named paper accepted to the MOTOR conference and scheduled to be published in a CCIS volume.</p> <p>The following data files are a part of this dataset, whose meaning should become clear after reading the paper:</p> <ul> <li>w1-runs.csv: the results of each of the runs, each of the configurations on the OneMax problem;</li> <li>w2-runs.csv: same for the LinInt<sub>2</sub> problem;</li> <li>w5-runs.csv: same for the LinInt<sub>5</sub> problem;</li> <li>ms-runs.csv: same for the easy random MAX-SAT instances;</li> <li>w1-stats.csv: the quartile statistics for the OneMax problem;</li> <li>w2-stats.csv: same for the LinInt<sub>2</sub> problem;</li> <li>w5-stats.csv: same for the LinInt<sub>5</sub> problem;</li> <li>ms-stats.csv: same for the easy random MAX-SAT instances;</li> <li>tunings-static.csv: the outcomes of irace for the static configurations (with fixed λ);</li> <li>tunings-dynamic.csv: the outcomes of irace for the dynamic configurations (with self-adjusting λ).</li> </ul> <p>Apart from that, the file pictures.pdf presents the contents of *-stats.csv files visually in a concide way.</p>
Genetic algorithm-based personalized models of human cardiac action potential
<p>We present a novel modification of genetic algorithm (GA) which determines personalized parameters of cardiomyocyte electrophysiology model based on set of experimental human action potential (AP) recorded at different heart rates. In order to find the steady state solution, the optimized algorithm performs simultaneous search in the parametric and slow variables spaces. We demonstrate that several GA modifications are required for effective convergence. Firstly, we used a mutation operator, based on Cauchy amplitude distribution along with a random direction in the parametric space. Secondly, relatively large number of elite organisms (6-10 % of the population passed on to new generation) was required for effective convergence. Test runs with synthetic AP as input data indicate that algorithm error is low for high amplitude ionic currents (1.6±1.6% for IKr, 3.2±3.5% for IK1, 3.9±3.5% for INa, 8.2±6.3% for ICaL). Experimental signal-to-noise ratio above 28 dB was required for high quality GA performance. GA was validated against optical mapping recordings of human ventricular AP and mRNA expression profile of donor hearts. In particular, GA output parameters were rescaled proportionally to mRNA levels ratio between patients. We have demonstrated that mRNA-based models predict the AP waveform dependence on heart rate with high precision. The latter also provides a novel technique of model personalization that makes it possible to map gene expression profile to cardiac function. </p>
The Camouflage Machine: Optimising protective colouration using deep learning with genetic algorithms
Evolutionary biologists frequently wish to measure the fitness of alternative phenotypes using behavioural experiments. However, many phenotypes are complex. For example colouration: camouflage aims to make detection harder, while conspicuous signals (e.g. for warning or mate attraction) require the opposite. Identifying the hardest and easiest to find patterns is essential for understanding the evolutionary forces that shape protective colouration, but the parameter space of potential patterns (coloured visual textures) is vast, limiting previous empirical studies to a narrow range of phenotypes. Here we demonstrate how deep learning combined with genetic algorithms can be used to augment behavioural experiments, identifying both the best camouflage and the most conspicuous signal(s) from an arbitrarily vast array of patterns. To show the generality of our approach, we do so for both trichromatic (e.g. human) and dichromat (e.g. typical mammalian) visual systems, in two different habitats. The patterns identified were validated using human participants; those identified as the best for camouflage were significantly harder to find than a tried-and-tested military design, while those identified as most conspicuous were significantly easier than other patterns. More generally, our method, dubbed the 'Camouflage Machine', will be a useful tool for identifying the optimal phenotype in high dimensional state-spaces.
Supporting datasets PubFig05 for: "Heterogeneous Ensemble Combination Search using Genetic Algorithm for Class Imbalanced Data Classification"
<p><strong>Faces Dataset: PubFig05</strong></p> <p>This is a subset of the ''PubFig83'' dataset [1] which provides 100 images each of 5 most difficult celebrities to recognise (referred as class in the classification problem). For each celebrity persons, we took 100 images and separated them into training and testing sets of 90 and 10 images, respectively:</p> <p><strong>Person: </strong>Jenifer Lopez; Katherine Heigl; Scarlett Johansson; Mariah Carey; Jessica Alba</p> <p> </p> <p><strong>Feature Extraction</strong></p> <p>To extract features from images, we have applied the HT-L3-model as described in [2] and obtained 25600 features.</p> <p><strong>Feature Selection</strong></p> <p>Details about feature selection followed in brief as follows:</p> <ol> <li> <p><strong>Entropy Filtering:</strong> First we apply an implementation of Fayyad and Irani's [3] entropy base heuristic to discretise the dataset and discarded features using the minimum description length (MDL) principle and only 4878 passed this entropy based filtering method.</p> </li> <li> <p><strong>Class-Distribution Balancing:</strong> Next, we have converted the dataset to binary-class problem by separating into 5 binary-class datasets using one-vs-all setup. Hence, these datasets became <em>imbalanced</em> at a ratio of 1:4. Then we converted them into <em>balanced binary-class</em> datasets using random sub-sampled method. Further processing of the dataset has been described in the paper.</p> </li> <li> <p><strong>(alpha,beta)-k Feature selection:</strong> To get a good feature set for training the classifier, we select the features using the approach based on the (alpha,beta)-k feature selection [4] problem. It selects a minimum subset of features that maximise both within class similarity and dissimilarity in different classes. We applied the entropy filtering and (alpha,beta)-k feature subset selection methods in three ways and obtained different numbers of features (in the Table below) after consolidating them into binary class dataset.</p> </li> </ol> <ul> <li> <p><strong>UAB:</strong> We applied (alpha,beta)-k feature set method on each of the balanced binary-class datasets and we took the <em>union</em> of selected features for each binary-class datasets. Finally, we applied the (alpha,beta)-k feature set selection method on each of the binary-class datasets and get a set of features.</p> </li> <li> <p><strong>IAB:</strong> We applied (alpha,beta)-k feature set method on each of the balanced binary-class datasets and we took the <em>intersection</em> of selected features for each binary-class datasets. Finally, we applied the (alpha,beta)-k feature set selection method on each of the binary-class datasets and get a set of features.</p> </li> <li> <p><strong>UEAB:</strong> We applied (alpha,beta)-k feature set method on each of the balanced binary-class datasets. Then, we applied the entropy filtering and (alpha,beta)-k feature set selection method on each of the balanced binary-class datasets. Finally, we took the <em>union</em> of selected features for each <em>balanced binary-class</em> datasets and get a set of features.</p> </li> </ul> <p>All of these datasets are inside the compressed folder. It also contains the document describing the process detail.</p> <p> </p> <p><strong>References</strong></p> <p>[1] Pinto, N., Stone, Z., Zickler, T., & Cox, D. (2011). Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on facebook. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on (pp. 35–42).</p> <p>[2] Cox, D., & Pinto, N. (2011). Beyond simple features: A large-scale feature search approach to unconstrained face recognition. In Automatic Face Gesture Recognition and Workshops (FG 2011), 2011 IEEE International Conference on (pp. 8–15).</p> <p>[3] Fayyad, U. M., & Irani, K. B. (1993). Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning. In International Joint Conference on Artificial Intelligence (pp. 1022–1029).</p> <p>[4] Berretta, R., Mendes, A., & Moscato, P. (2005). Integer programming models and algorithms for molecular classification of cancer from microarray data. In Proceedings of the Twenty-eighth Australasian conference on Computer Science - Volume 38 (pp. 361–370). 1082201: Australian Computer Society, Inc.</p> <p> </p>
Dataset: A phase field model combined with genetic algorithm for polycrystalline hafnium zirconium oxide ferroelectrics
<p>The folder includes generated data MATLAB scripts to read/plot the polarization-electric field (PE) hysteresis curves. The dataset contains phase field generated polycrystalline grain structure, simulated domain structures during polarization reversal, and symmetric PE curves (measured and simulated).</p> <p><strong>Polycrystalline grain structures</strong>: The output files are in the *.txt format, readable by MTEX to generate orientation maps.<br> Column(1) Column(2) Column(3) Column(4) Column(5)<br> X Y φ(rad) θ(rad) 𝜓(rad)<br> ... ... ... ... ...<br> ... ... ... ... ...<br> ... ... ... ... ...</p> <p><strong>Domain structures</strong>: The output files are in the *.csv format, which can be visualized by programs like ParaView.<br> Column(1) Column(2) Column(3) Column(4)<br> X Y Z P<br> ... ... ... ...<br> ... ... ... ...<br> ... ... ... ...</p> <p><br> <strong>PE curves</strong>: The output files are in the *.txt format, readable by MATLAB.<br> Column(1) Column(2)<br> E(MV/cm) P(μC/cm²)<br> ... ...<br> ... ...<br> ... ...</p> <p><strong>List of datasets:-</strong><br> Fig. 1: pecurves/calib_func1.txt (Calibrated p(e)), pecurves/measpe_hf50.txt (Measured PE curve), pecurves/simpe_calib.txt (Simulated PE curve).<br> Fig. 2(a): polcr_struc/xy_col.txt (XY top view), polcr_struc/yz_col.txt (YZ side view), polcr_struc/xz_col.txt (ZX side view)<br> Fig. 2(b): pecurves/simpe_gaopt.txt (Simulated PE curve), pecurves/measpe_hf50.txt (Measured PE curve).<br> Fig. 3: pecurves/calib_func.txt (Calibrated p(e)), pecurves/gaopt_func.txt (GA optimized p(e)).<br> Fig. 5: pecurves/simpe_gaopt.txt (Case 1), pecurves/simpe_elast.txt (Case 2).<br> Fig. 4(e): dom_struc/dom_profile1.csv, (f) dom_struc/dom_profile2.csv, (g) dom_struc/dom_profile3.csv, (h) dom_struc/dom_profile4.csv, (m) dom_struc/dom_profile5.csv, (n) dom_struc/dom_profile6.csv, (o) dom_struc/dom_profile7.csv, (p) dom_struc/dom_profile8.csv<br> Fig. 6: pecurves/simpe_gaopt.txt (GA fit coefficients), pecurves/simpe_ldc1.txt (Set 1), pecurves/simpe_ldc2.txt (Set 2).<br> Fig. 7(a): pecurves/simpe_gaopt.txt (𝝂₀ = 1.0), pecurves/simpe_fr80.txt (𝝂₀ = 0.8), pecurves/simpe_fr50.txt (𝝂₀ = 0.5).<br> Fig. 7(b): pecurves/measpe_hf50.txt (Hf₀.₅Zr₀.₅O₂), pecurves/measpe_hf75.txt (Hf₀.₇₅Zr₀.₂₅O₂).<br> Fig. 8: pecurves/simpe_fr38.txt (Simulated PE curve), pecurves/measpe_hf75.txt (Measured PE curve).<br> Fig. 9: pecurves/simpe_gaopt.txt (Random non-textured), pecurves/simpe_tex001.txt ([001] fiber textured), pecurves/simpe_tex111.txt ([111] fiber textured).<br> Fig. 10(a): polcr_struc/xy_equ.txt (XY top view), polcr_struc/yz_equ.txt (YZ side view), polcr_struc/xz_equ.txt (ZX side view)<br> Fig. 10(b): pecurves/simpe_colmor.txt (Columnar grain microstructure), pecurves/simpe_equmor.txt (Equiaxed grain microstructure).</p> <p><strong>List of MATLAB scripts:</strong><br> Fig 1: matlab_scripts/fig1.m<br> Fig 2(b): matlab_scripts/fig2b.m<br> Fig 3: matlab_scripts/fig3.m<br> Fig 5: matlab_scripts/fig5.m<br> Fig 6: matlab_scripts/fig6.m<br> Fig 7(a): matlab_scripts/fig7a.m<br> Fig 7(b): matlab_scripts/fig7b.m<br> Fig 8: matlab_scripts/fig8.m<br> Fig 9: matlab_scripts/fig9.m<br> Fig 10(b): matlab_scripts/fig10b.m<br> </p>
Characterization data for the manuscript: "Using genetic algorithms to systematically improve the synthesis conditions of Al-PMOF"
<p>Visualize the data in this dataset: <a href="https://www.c6h6.org/zenodo/record/?id=7186602">open entry</a>.</p>
Interplay between Genetics, Epigenetics & Exposures- Proposed Algorithm for Pediatric Cancer Development
Interplay between Genetics, Epigenetics & Exposures- Proposed Algorithm for Pediatric Cancer Development
Interpretation of inherited risk signals using genetic algorithms
<p>This tarball contains the pre-processed data in .Rda files and code in .Rmd file required to execute the genetic algorithm model and compile figures in this study.</p>
Reproduction Package for A Partial Reproduction of A Guided Genetic Algorithm for Crash Reproduction
<p>A reproduction package for "A Partial Reproduction of A Guided Genetic Algorithm for Crash Reproduction"</p> <p>Includes datasets and source code for reproducing our results</p>
The Camouflage Machine: Optimising protective colouration using deep learning with genetic algorithms
Open the record for dataset details and reuse information.
Genetic algorithm-based personalized models of human cardiac action potential
Open the record for dataset details and reuse information.
Approximation of a marine ecosystem model by artificial neural networks designed using a genetic algorithm
<p>Data from the Paper: Approximation of a marine ecosystem model by artificial neural networks designed using a genetic algorithm.</p> <p>Abstract: </p> <p>Marine ecosystem models are important to identify the processes that affects for example the global carbon cycle. Computation of an annually periodic solution (i.e., a steady annual cycle) for these models requires a high computational effort. To reduce this effort, we approximated an exemplary marine ecosystem model by different artificial neural networks. We used a fully connected network, then applied the sparse evolutionary training (SET) procedure, and finally applied a genetic algorithm (GA) to optimize both the network topology. With all three approaches, a direct approximation of the steady annual cycle was not sufficiently accurate. However, using the mass-corrected prediction of the ANN as initial concentration for additional model runs, the results were in very good agreement. In this way, we achieved a runtime reduction by about 15 \%. The result from the SET algorithm were comparable to those of the full network. Further application of the GA may lead to an even higher reduction.</p> <p>Content:</p> <p>Database sqlite <a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN_Database.db">ANN_Database.db</a></p> <p>zip-files with data: </p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN-Data.zip">ANN-Data.zip</a> structure and weights of used networks</p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN-Results.zip">ANN-Results.zip</a> results obtained with networks</p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/Reference-Results.zip">Reference-Results.zip</a> reference results and training data</p> <p> </p> <p> </p> <p> </p> <p> </p>
Time-Plan Optimization with Genetic Algorithm for Regain of Energy from Train Tracks
<p>Dataset using for Time-Plan Optimization with Genetic Algorithm for Regain of Energy from Train Tracks</p>
Software for control of autonomous robots using fuzzy logic controllers tuned by genetic algorithms
<p>This software implements the autonomous control of a robot by using a fuzzy logic controller tuned by a genetic algorithm. The software was written in C programming language for Windows (SDK). A description of the software can be found in the research publication "Arsene, C.T.C., & Zalzala, A.M.S., "Control of autonomous robots using fuzzy logic controllers tuned by genetic algorithms", In Proc Congress on Evolutionary Computation, Vol. 1, pp. 428-35, Washington DC, 1999, IEEE Computer Science Press, ISBN 0-7803-5536-9". Possibly the software to be used also for simulation of Nano-robots.</p>
Implementation of Genetic Algorithms to Optimize Metal-Organic Frameworks for CO2 Capture
<p>Dataset associated with the publication "Implementation of Genetic Algorithms to Optimize Metal-Organic Frameworks for CO2 Capture".</p> <p> </p> <p>Changelog:</p> <p>- Include sample input files for GCMC using RASPA2 and geometry optimization using LAMMPS.</p>
Geomagnetic datasets of BJI station reconstructed through Artificial Neural Network improved by Genetic Algorithm in 2021
<p>Beijing station established in 1954 is one of the oldest geomagnetic observatories in China, which plays an important role in data exchange, and further provide data or standardization for satellite observation and geomagnetic model construction. With the development of urbanization, the observed data are greatly disturbed by subways, and data disturbed are almost unavailable. The dataset was reconstructed through Artificial Neural Network improved by Genetic Algorithm, including minutely data of three components (<em>D</em>, <em>H</em> and <em>Z</em>) in 2021. This reconstruction method has been proved to be effective.</p>
A PK/PD Genetic Variation Treatment Algorithm Versus Treatment As Usual for Adolescent Management Of Depression
ClinicalTrials.gov study NCT02286440. IPD Sharing: NO. Countries: 1. Publications: 2.
Development of a Risk Prediction Algorithm Through the Investigation of Genetic Risk Factors and the Complexity of Coronary Artery Disease to Estimate Future Risk of Cardiovascular Events: Angiographi
ClinicalTrials.gov study NCT03150680. IPD Sharing: UNDECIDED. Countries: 1. Publications: 3.
Software for control of autonomous robots using fuzzy logic controllers tuned by genetic algorithms
Open the record for dataset details and reuse information.
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.