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.
171
datasets available to search
ShareScore release 0.9.0
Dataset results
171 results for “performance prediction”
Human hippocampal replay during rest prioritizes weakly learned information and predicts memory performance
Open the record for dataset details and reuse information.
A Queueing Network Model for Performance Prediction of Apache Cassandra
<p>The dataset consists in several csv files containing Cassandra and ScyllaDB performance.</p> <p>The experiments are organized in folders. There are three main folders containing:<br> - Cassandra 4 nodes: the files related to the Cassandra experiments conducted on a cluster composed of four nodes.<br> - ScyllaDB 4 nodes: The files related to the ScyllaDB experiments conducted on a cluster composed of four nodes. <br> - Cassandra QUORUM variant: the simulation data where a different kind of QUORUM is implemented in Cassandra.<br> <br> "Cassandra 4 nodes" and "ScyllaDB 4 nodes" include some subfolders, each one containing the files of the Consistency Level applied for those experiments. Each experiment is composed by three files (data*.csv) with the data reported by Yahoo! Cloud System Benchmark (YCSB) in the end of the experiment execution. Each folder contains also a sim.csv file with the data gathered from the simulation of the model inside Java Modeling Tool.</p> <p>The data*.csv files are composed by:<br> -Number of threads or clients<br> -Overall Throughput<br> -Number of Read requests<br> -Overall Read Response Time<br> -95 percentile Read Response Time<br> -99 percentile Read Response Time<br> -99.9 percentile Read Response Time<br> <br> Differently, the sim.csv files are composed by:<br> -Number of threads or clients<br> -Overall Throughput<br> -Overall Read Response Time</p>
Generative artificial intelligence predicts human performance
<p>Research data for a study that used generative artificial intelligence (i.e., ChatGPT with the GPT-4 and the Google Gemini 2.0 Flash models) to predict human performance in a language-based memory task. In particular, we studied the effects of context on the relatedness and memorability of garden-path sentences. </p>
Train and Evaluation Code, Road Classification Models and Test set of the paper "Impact of Image Resolution and Image Overlap on the Prediction Performance of Convolutional Neural Networks Trained for Road Classification"
<p>This repository contains the Python scripts built for training and evaluation of the implementation, together with the test data and the resulting road classification models corresponding to the paper "Impact of Image Resolution and Image Overlap on the Prediction Performance of Convolutional Neural Networks Trained for Road Classification". The scripts make use of the Tensorflow with Keras framework and the additional required dependencies.</p> <p>The training and validation set is based on the binary SROADEX dataset (https://zenodo.org/records/6482346) that was re-split into tiles that feature the image resolutions (256 x 256, 512 x 512, and 1024 x 1024 pixels) and image overlaps (0% and 12.5%) considered in this study. The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography that represents the axes of the different types of roads (urban, interurban and rural). This binary road data contains information from 16 full orthoimages (28.5 km * 18.5 km) with spatial resolution of 0.5 m/pixel from the insular and peninsular Spanish territory. Due to the size on disk of approximately 546 gigabytes, this training and validation data is only available upon request from the corresponding author. The test set has been generated from a novel area of 28.5 km * 18.5 km and features binary road labels. The test sets are provided in the repository for each resolution (with no overlap), so that additional DL models can be evaluated on the same data and compared with the results achieved in this study.</p> <p>The structure of the information shared in this repository is as follows:<br>The scripts have been grouped by tile resolution (256, 512 and 1024). First, the test set and the evaluation script can be found. For each tile resolution, there are two subfolders (corresponding to the "no overlap" and "12.5% overlap"). In each case, the Python scripts for training the models in the three repetitions are shared, and the trained models (H5 format) are shared in compressed form. Finally, for each resolution we also share the testing dataset which consists of two folders.</p> <p>The material is distributed under a CC-BY 4.0 license.</p>
Data for: Predictable local adaptation in butterfly photoperiodism but not thermal performance along a latitudinal cline
<p>In seasonal environments, organisms must synchronize their life cycles to conditions favorable for growth and reproduction. Because season length varies geographically, local adaptation should arise in traits that regulate phenological responses. Geographic photoperiodism clines are well-known, but comparable studies on thermal performance are equivocal and often overlook non-linear responses. Therefore, we examined local adaptation in plastic responses to both photoperiod and temperature along a 752 km latitudinal cline, by comparing four Swedish populations of the butterfly <em>Pieris napi</em>. Using a common garden design, we estimated (1) photoperiod response curves for diapause induction and (2) thermal performance curves for development and growth rates. We show that differences in photoperiodism follow the expected geographical pattern, where diapause is induced at longer daylengths in northern populations (where growth seasons are short and summer days long). However, population differences in thermal performance curves were small and seemingly idiosyncratic, without clear clinal patterns. Photoperiodic responses appear to evolve more readily than thermal responses, highlighting photoperiodism as a key driver of local life cycle synchronization.</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>
High Performance Predictable Quantum Efficient Detector Based on Induced-Junction Photodiodes Passivated with SiO2/SiNx
<p>This page contains selected data from the peer-reviewed paper "High Performance Predictable Quantum Efficient Detector Based on Induced-Junction Photodiodes Passivated with SiO2/SiNx" published in Sensors by Ozhan Koybasi.</p> <p>Description of attached files:</p> <p>Figure 5. Simulated p-polarization reflectance as a function of wavelength for PQEDs mounted in trap configuration with an angle of 15° between the diodes. In this configuration the light beam undergoes 7 reflections: one at 0° degree and two reflections at 15°, 30°, and 45°. The reflectance is reported for six different thicknesses of the SiNx.</p> <p>Figure 6. Maximum and mean values evaluated in the wavelength interval 400–850 nm of the p-polarization reflectance as a function of SiNx thickness for PQEDs mounted in trap configuration with an angle of 15° between the diodes.</p> <p>Figure 7. Maximum and mean values evaluated in the wavelength interval 400–850 nm of the p-polarization reflectance as a function of SiNx thickness, when a buffer layer of 6 nm SiO2 is depos-ited before SiNx, for PQEDs mounted in trap configuration with an angle of 15° between the di-odes.</p> <p>Figure 8. Effective lifetime τeff vs. excess carrier density (Δn) for samples prepared with passivation processes described in Table 1.</p> <p>Figure 9. Photoluminescence (PL) lifetime images of samples prepared with the passivation processes described in Table 1.</p> <p>Figure 10. Capacitance—voltage (C—V) measurement results of MIS capacitors prepared with the passivation processes E2 (6 nm SiO2+ 65 nm SiNx) and E6 (65 nm SiNx) as described in Table 1, at a frequency of 1 kHz.</p> <p>Figure 11. Injection dependent effective minority carrier lifetime τeff (Δn) of test samples passivated with processes E2 (6 nm SiO2+ 65 nm SiNx) and E6 (65 nm SiNx) as described in Table 1 with simu-lation fits to extract SRV and τbulk.</p> <p>Figure 12. Simulated IQD as a function of reverse bias voltage for p-type inversion-layer photodi-ode that would be fabricated with passivation E2 (6 nm SiO2+ 65 nm SiNx) and E6 (65 nm SiNx) as described in Table I. The simulations were performed at a wavelength of 488 nm.</p> <p>Figure 13. Simulated IQD as a function of wavelength for p-type inversion-layer photodiode that would be fabricated with passivation E2 (6 nm SiO2+ 65 nm SiNx) and E6 (65 nm SiNx) as described in Table I. The simulations were performed at a reverse bias voltage of 5 V.</p> <p>Figure 16. Spatial uniformity of optical power responsivity of the PQEDs with SiO2/SiNx stack photodiodes P18-55-45 (a) and P18-54-44 (b).</p> <p> </p>
Performance Prediction of Deep Learning Applications
<p>The repository includes the source code and the datasets used to predict the performance of Deep Learning applications executed on different environments. The results are included in the AI-SPRINT project deliverable "D2.1 - First release and evaluation of the AI-SPRINT design tools".</p>
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>
Dataset: Predictive Oncology Inc. (POAI) Stock Performance
This dataset provides historical stock market performance data for specific companies. It enables users to analyze and understand the past trends and fluctuations in stock prices over time. This information can be utilized for various purposes such as investment analysis, financial research, and market trend forecasting.
Figure 6. Performance plot for NASDAQ index (RNN)-Comparative study of Financial Time Series Prediction by Artificial Neural Network with Gradient Descent Learning
<p>Figure 5 we can see that the mse curve reaches the In performance goal but it does not<br> decrease in that good manner,but in Figure 6 the mse is reduces widely. By analyzing all these<br> results one can say that RNN is better choice than Feedforward MLP in prediction purpose.</p>
Figure 5. Performance plot for NASDAQ index (MLP)-Comparative study of Financial Time Series Prediction by Artificial Neural Network with Gradient Descent Learning
<p>Figure 5 we can see that the mse curve reaches the In performance goal but it does not<br> decrease in that good manner,but in Figure 6 the mse is reduces widely. By analyzing all these<br> results one can say that RNN is better choice than Feedforward MLP in prediction purpose.</p>
On the Performance of Method-Level Bug Prediction: A Negative Result
<p>Bug prediction is aimed at identifying software artifacts that are more likely to be defective in the future. Most approaches defined so far target the prediction of bugs at class/file level. Nevertheless, past research has provided evidence that this granularity is too coarse-grained for its use in practice. As a consequence, researchers have started proposing defect prediction models targeting a finer granularity (particularly method-level granularity), providing promising evidence that it is possible to operate at this level. Particularly, models mixing product and process metrics provided the best results.</p> <p>We present a study in which we first replicate previous research on method-level bug-prediction, by using different systems and timespans. Afterward, based on the limitations of existing research, we (1) re-evaluate method-level bug prediction models more realistically and (2) analyze whether alternative features based on textual aspects, code smells, and developer-related factors can be exploited to improve method-level bug prediction abilities. Key results of our study include that (1) the performance of the previously proposed models, tested using the same strategy but on different systems/timespans, is confirmed; but, (2) when evaluated with a more practical strategy, all the models show a dramatic drop in performance, with results close to that of a random classifier. Finally, we find that (3) the contribution of alternative features within such models is limited and unable to improve the prediction capabilities significantly. As a consequence, our replication and negative results indicate that method-level bug prediction is still an open challenge.</p>
Figure 6 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 6. Total cross-validation AUC (CV-AUC) and spatial congruence AUC (SC- AUC) for a range of grain sizes.
Figure 4 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 4. Divergence between the uncorrelated and pruned models estimated through Parolo divergence index at 250-m resolution. As is shown, there was little divergence (0– 0.2) between models in most of the study area.
Figure 1 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 1. The location of the study area on a map of western Asia (right). Inset shows DEM of study area with polygons indicating the protected areas where populations of goitered gazelle occur.
Figure 5 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 5. The change in performance index (AUC, left) and habitat suitability area (right) of the output model with increasing extent size (open circles) and grain size (filled circles) from 250 to 3000 m.
Figure 3 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 3. Goitered gazelle distribution maps based on the uncorrelated model (left) and the pruned model (right) for the 250-m grid size.
On the Performance of Method-Level Bug Prediction: A Negative Result. Appendix
<p>Abstract Bug prediction is aimed at identifying software artifacts that are more likely to be defective. Most approaches defined so far target the prediction of bugs at class/file level. Nevertheless, past research has provided evidence that this granularity might be too coarse-grained, thus reducing the usability of bug prediction in practice. As a consequence, researchers have started proposing defect prediction models targeting a finer granularity, particularly targeting methods, providing promising evidence that it is possible to operate at this granularity. Particularly, models based on a mixture of product and process metrics provided the best results. </p> <p>In this paper, we first replicate previous research on method-level bug- prediction using different systems and timespans. Afterward, based on the limitations of existing research, we (1) re-evaluate method-level bug prediction models more realistically and (2) analyze the whether textual features— previously shown as valuable sources of information for the evaluation of software quality (yet surprisingly unexplored in this research field)—can be exploited to improve method-level bug prediction abilities. Key results of our study include that (1) the performance of the previously proposed models, tested using the same strategy but with different systems/timespans, is con- firmed. However, (2) when evaluated with a more realistic strategy all the models show a dramatic drop in performance exhibiting results close to that of a random classifier. In addition, we find that (3) the contribution of textual features within such models is limited and unable to improve the prediction capabilities significantly. As a consequence, our replication and negative results indicate that method-level bug prediction is still an open challenge.</p>
Predicting mobility and research performance of the faculty members in the economics departments at Turkish public universities
<p>The data used for the regression analysis is in Table 5 on page 17 of the paper. </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.