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”
The Prediction of the Rate of the Dropout of the Primary Schools Students by Using the Genetic Algorithm-Figure 1. Drawing the time series for males primary stage
<p>After collecting all the students’ dropout proportion for both males and females in the<br> primary stage, the first step of the Box-Jenkins is to draw the time chain data to understand the<br> chain's attitude.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-In Figure 15 we were able to generate the symbol H without any help from a small image we used only for row and column data
<p>In Figure 15 we were able to generate the symbol H without any help from a small image we used only for row and column data.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 14. Symbol 8 regeneration
<p>As we can see, here we were able to recover the lost middle portion of character ‘A’ using our genetic algorithm. If we can apply some noise filtering technique, the result would be far better. In figure 14, 15 there are another two examples.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 11. Initial population
<p>In figure 11 it is the initial population showed and figure 12 the population started to change and figure 13 we reached a convergence.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 10. Block example
<p>First, we have to convert the pixelated small image to the original size image, and then divide these into the blocks as it done in extraction time. Then we have to add or subtract random bits from each of these blocks to equal each block hamming bit to original hamming bit number. And then GA is applied to match these randomness to original image hamming bits in per row and column. In figure 10 there is a 4-block example which regenerates randomly using total block bit count. Now we will try to match their row and column bits of information with the extracted data which is described in later section.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 6. Methodology
<p>Our method will first resize the image using normal image resizing option provided by operating system or standard library and attach the extra 2 array of data which contains no of 1 in original image in each row and column. Also, the total no of 1 in that image will be present too.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 16. Failed Generations
<p>For some images there is a chance to get stuck where fitness function maxed, but we are not near to the original image like in figure 16, both row and column fitness matched. But image lost a key portion from original image, in these cases we should increase the weight of fitness function Fx(X), which will solve the issue.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 2. Image stored in cloud each year (Perret, 2017)
<p>Currently, 4.7 trillion of photos are saved in the cloud (Perret, 2017). And only a few percentage are called to use again. So less used files can be stores in a compression technique which can save more space than time and make the cloud system faster as memory redundancy time will be reduced.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 1. Photo amount by year (Perret, 2017)
<p>Revolution of a portable camera with computer started to produce an exponential rate of media files, and users are sharing these files with everyone. So, using the cloud to store images is becoming a favorite choice for users. But cloud does not only store huge files which are approximately 1.2 trillion in 2017 (Perret, 2017), it also has to transfer these files to a different network to serve users. To reduce load, the cloud system started to use different compression algorithm. These algorithms have a tradeoff between time and space. Most of these have better time complexity than space. But as the cloud has powerful and distributed computing power, it may be better to focus on saving space. As data transfer takes more time than processing same data in the cloud. A perfect use case is a mobile sending the large image to the cloud takes more data transfer time than the compression and decompression process in the cloud. So, in this age of the distributed computer, it is better to reduce size as computation time is less important than network data transfer time.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 9. Resized image and extracted data for a 100*100 size image
<p>For the extraction, our goal is to divide an image into smaller blocks and keep the row and column data for these blocks. But for our experiment we used a single block, which means taking the full image as a single block. For bigger image we should always divide the image in separate blocks and work on them par rally. As in figure 8, after extracting the data we can add the row and column bits information in the resized image or saved in a separate file. For proof of concept we saved it in a text file. And later that file is used to feed GA to make the fitness function, in figure 9 an extraction has been shown. In upper and side textbox containing the information which later is saved in a text file.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 7. Basic Methodology
<p>As in figure 7 we are storing the extra data which is look like figure 8. Where a 20*20 size image of alphabet ‘A’ data has been stored. When we regenerate image, we are using these data.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 5. Image down sample
<p>Our proposal is to store each column and row bits count in a separate file and used that to reproduce the image using genetic algorithm.If we take 10% of an image size and the row and column image hamming bit count our total size will be approximately below 15% of the actual image size. We proposed a method to reproduce original image from using this 15% information.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 8. Sample Data Extraction for a 20*20 size image
<p>As in figure 7 we are storing the extra data which is look like figure 8. Where a 20*20 size image of alphabet ‘A’ data has been stored. When we regenerate image, we are using these data.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 4. Image regeneration using GA
<p>In 2008, Roger Johansson was able to regenerate a Mona Lisa image from random sampling (Roger Johansson, 2017). It uses a genetic algorithm to model a population of individuals, each containing a string of DNA which can be visualized in the form of an image (Grow Your Own Picture Genetic Algorithms & Generative Art, 2017).</p> <p>By starting with a population consisting of a randomly generated gene pool, each individual is compared to the reference image (the one on the left), and the individuals can then be ranked by their likeness to it, known as their "fitness", with the best fit being displayed on the output image (the one on the right) (Grow Your Own Picture Genetic Algorithms & Generative Art, 2017). By breeding the fittest individuals from the population, the DNA which produces the most accurate representation of the reference image is selected over successive generations, effectively demonstrating the power of a natural selection process to produce the best candidate for any given environment (Grow Your Own Picture Genetic Algorithms & Generative Art, 2017).</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 3. Data compression and image reconstruction (55:148 Digital Image Processing, 2017)
<p>There are several techniques which are normally divided into two categories lossy and lossless image compressions. In lossy compression, after recovery there are negligible difference present where lossless gives accurate image. Huffman encoding is very well known, which can provide optimal compression and decompression without error (55:148 Digital Image Processing, 2017). The basic idea of Huffman coding is to represent data by number of variable size, where more frequent info being represented by shorter number (55:148 Digital Image Processing, 2017). Currently the Lempel-Ziv (or Lempel-Ziv-Welch, LZW) algorithm for dictionary-based coding has got attention as a better compression algorithm (55:148 Digital Image Processing, 2017).</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 12. After few generation
<p>In figure 11 it is the initial population showed and figure 12 the population started to change and figure 13 we reached a convergence.</p>
A Genetic Algorithm Approach to Regenerate Image from a Reduce Scaled Image Using Bit Data Count-Figure 13. Reached convergence
<p>In figure 11 it is the initial population showed and figure 12 the population started to change and figure 13 we reached a convergence.</p>
Load Shifting Optimization with Genetic Algorithms for Energy Cost Minimization in Households - Case Study Data2
<p>The case study of this dataset uses real household data, representing five days from 0h00 to 23h59. This dataset uses a period of 15 minutes for all loads execution time and energy data. The case study considers twenty unique houses that can have up to five different shiftable appliances, each executing three process cycles.<br> <br> File Description:</p> <ul> <li>Case_Studies_Data-BAU_and_Load_Shifting - Excel containing appliances energy profile, load execution preferences, BAU consumption, and houses' data</li> <li>Houses_Input_Output_JSONs_and_Statistics - Zip containing the input and output files from the proposed system, as well as their corresponding schedule statistics</li> </ul>
Load Shifting Optimization with Genetic Algorithms for Energy Cost Minimization in Households - Case Study Data
<p>The case study of this dataset uses real household data, representing five days from 0h00 to 23h59. This dataset uses a period of 15 minutes for all loads execution time and energy data. The case study considers twenty unique houses that can have up to five different shiftable appliances, each executing three process cycles.<br> <br> File Description:</p> <ul> <li>Case_Studies_Data-BAU_and_Load_Shifting - Excel containing appliances energy profile, load execution preferences, BAU consumption, and other house data</li> <li>Houses_Input_JSONs - Zip containing the input files, from each house, for the proposed system</li> </ul>
Genetic Algorithm-Based Fuzzy Inference System for Describing Execution Tracing Quality - Collected Data
<p>The deposited data files were used to perform the analysis introduced in the paper: Tamas Galli, Francisco Chiclana and Francois Siewe, "Genetic Algorithm Based Fuzzy Inference System for Describing Execution Tracing Quality", Mathematics, MDPI, 2021.</p> <p>The data were collected through an online questionnaire. The questionnaire has been exported in pdf format and uploaded as file: form_data_collection.pdf. The paper above introduces the steps of analysing, processing the data, constructing, pre-validating the model. The final validation was done over the online questionnaire exported and uploaded in pdf format as form_model_validation.pdf.</p> <p>Questionnaire Part 1, data file: all_usecases_wide.csv</p> <p>The CSV file contains the responses for each use case of part 1 of the online questionnaire enclosed. The columns contain the assigned values from the respondents, on a scale [0; 100]. The following variables are linked to each use case: Accuracy, Legibility, DesignAndImplementation, and Security. These form the input variables of execution tracing quality, while the variable Quality designates the quality of execution tracing. Each fifth column is followed by a column UseCase to designate the use case which is described by the previous five columns. The definitions of the variables can be found in the questionnaire.</p> <p>Questionnaire Part 2, data file: all_real_projects_scores.csv</p> <p>The CSV file contains the responses for real projects in part 2 of the online questionnaire enclosed. The columns contain the assigned values from the respondents, on a scale [0; 100]. Six variables are linked to each response: Accuracy, Legibility, DesignAndImplementation, and Security, which form the input variables of execution tracing quality, while the variable Quality designates the quality of execution tracing. In addition, the variable Type indicates the type of the project, such as server application, desktop application, web UI, mobile application, or embedded application. The definitions of the variables can be found in the questionnaire.</p> <p>Questionnaire Part 3, data file: all_extrem_values_wide.csv</p> <p>The CSV file contains the assigned execution tracing quality value to the provided combination of extreme input values in part 3 of the online questionnaire enclosed. The column IDs represent the question IDs in the survey. The definitions of the variables can be found in the questionnaire.<br> </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.