Find research datasets worth reusing

Figure 6 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 6. Motion of colonies toward their relevant imperialist (AtashpazGargari 2009).

Figure 4 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 4. Flowchart of Imperialist Competitive Algorithm (AtashpazGargari 2009).

Figure 7 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 7. Distribution of T. urticae in different stages of sampling.

opencc-by-4.0Jul 2022View details →

Dataset for "Towards Better Evaluation for Dynamic Link Prediction"

These are the datasets used in Towards Better Evaluation for Dynamic Link Prediction For preparing the datasets, we closely follow the baseline methods' data preparation strategy. The original networks are saved as <network>.csv. The networks are formatted as follows:     * Each edge is denoted in one line.     * Each line has the following format: source_node, destination_node, timestamp, edge_label, comma-separated arrays of edge features.         * Please note that if there is no edge label available, the edge_label column will be filled with 0s only for loading purpose; these labels are not used in the link prediction task.     * The first line denotes the network format.     * Edge features should include at least one feature. If there is no edge feature available, a 0 value is used for all the edges. The network edge-lists are pre-processed for different methods to use them (Specifically, for preprocessing the data, we use the scripts available in "preprocess_data.py" file of the corresponding baseline). Ater preprocessing the network edge-list, there are three files that are used by the models:     * <ml_network>.csv: this file contains the timestamp edge-list.     * <ml_network>.npy: this file contains the edge features in the dense `npy` format that has the features in binary format.     * <ml_network_node>.npy: this file contains the node features in the dense `npy` format that contains the node features in binary format. Please note that when the edge features or node features are absent, we use a vector of zeros is used as the node/edge features in line with the baseline methods.

dryad36/100

Data from: Sex differences in the predictability of risk-taking behaviour

Recent research has found that individuals often vary in how consistently they express their behaviour over time (i.e. behavioural predictability) and suggested that these individual differences may be heritable. However, little is known about the intrinsic factors that drive variation in the predictability of behaviour. Indeed, whether variation in behavioural predictability is sex-specific is not clear. This is important, as behavioural predictability has been associated with vulnerability to predation, suggesting that the predictability of behavioural traits may have key fitness implications. We investigated whether male and female eastern mosquitofish (Gambusia holbrooki) differed in the predictability of their risk-taking behaviour. Specifically, over a total of 954 behavioural trials, we repeatedly measured risk-taking behaviour with three commonly used assays—refuge-use, thigmotaxis, and foraging latency. We predicted that there would be consistent sex differences in both mean-level risk-taking behaviour and behavioural predictability across the assays. We found that risk-taking behaviour was repeatable within each assay, and that some individuals were consistently bolder than others across all three assays. There were also consistent sex differences in mean-level risk-taking behaviour, with males being bolder across all three assays compared to females. In contrast, both the magnitude and direction of sex differences in behavioural predictability were assay specific. Taken together, these results highlight that behavioural predictability may be independent from underlying mean-level behavioural traits and suggest that males and females may differentially adjust the consistency of their risk-taking behaviour in response to subtle changes in environmental conditions.

opencc-zeroOct 2022View details →

opencc-by-4.0Oct 2022View details →

Towards transferable data-driven models to predict urban pluvial flood water depth in Berlin, Germany

The attached files include the predictive features and the water depth from 2D hydrodynamic simulations that were used to train data driven models to predict water depth in Berlin.

opencc-by-4.0Oct 2022View details →

Two-dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials

This repo contains the supplementary data sets for the to-be-published paper entitled "Two-dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials".   This repo contains the following data sets: 1. CIF files for amorphous porous materials (activated carbon, hyper-cross-linked polymers, Kerogen, PIMs). 2. Grand canonical Monte Carlo (GCMC) simulation results for single-component adsorption isotherms in ToBaCCo1.0 MOFs and in amorphous porous materials. Gas molecules include Kr, Xe, ethane, propane, butane, n-hexane, and 2,2-dimethylbutane. 3. Textural properties of ToBaCCo1.0 MOFs and amorphous porous materials. 4. Trained machine learning models. R code that can work with these ML models is hosted on <a href="https://github.com/snurr-group/2D-energy-histogram">GitHub</a>.

dryad36/100

CGG short tandem repeat genotype predictions

As expansions of CGG short tandem repeats (STR) are established as the genetic aetiology of many neurodevelopmental disorders, we aimed to elucidate the inheritance patterns and role of CGG STRs in autism-spectrum disorder (ASD). By genotyping 6,063 CGG STR loci in a large cohort of trios and quads with an ASD-affected proband, we determined an unprecedented rate of CGG repeat length deviation across a single generation. While the concept of repeat length being linked to deviation rate was solidified, we demonstrate how shorter STRs display greater degrees of size variation. We observed that CGG STRs did not segregate by Mendelian principles, with a bias against longer repeats, which appeared to magnify as repeat length increased. Through logistic regression, we identified 19 genes that displayed significantly higher rates and degrees of CGG STR expansion within the ASD-affected probands (p < 1 x 10-5). This study not only highlights novel repeat expansions that may play a role in ASD but also reinforces the hypothesis that CGG STRs are specifically linked to human cognition.

opencc-zeroOct 2022View details →

opencc-by-4.0Oct 2022View details →

To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features - Dataset

This repository contains the reproduction steps and intermediate artifacts corresponding to the paper 'To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features'. During the submission process, this repository is anonymized to our best ability.  The file 'README' contains the description of which file contains what data, and how they correspond to different parts of the paper.

opencc-by-4.0Aug 2017View details →

Individual-level trait diversity predicts phytoplankton community properties better than species richness or evenness

This archive includes the final summary tables used for the analyses.

opencc-by-4.0Sep 2017View details →

Predicted genes annotated with Prokka for the 623 archaeal UBA genomes

Gene prediction and annotation for the 623 archaeal UBA metagenome-assembled genomes using Prokka v1.12 with Pfam v31 and UniProt databases created on April 17, 2017 according to the Prokka instructions. These genomes are described in: Parks DH, et al. 2017. Recovery of nearly 8,000 metagenome-assembled genomes substantially expands the tree of life. Nat Microbiol, doi:10.1038/s41564-017-0012-7/ . https://www.nature.com/articles/s41564-017-0012-7

Data set for the paper "Predicting Relevance of Change Recommendations"

Data set for the paper Predicting Relevance of Change Recommendations by Thomas Rolfsnes, Leon Moonen, and David Binkley, In International Conference on Automated Software Engineering (ASE), pp. 694–705. 2017, IEEE. Please cite this work by referring to the corresponding conference publication (a preprint is included in this package). Abstract: Software change recommendation seeks to suggest artifacts (e.g., files or methods) that are related to changes made by a developer, and thus identifies possible omissions or next steps. While one obvious challenge for recommender systems is to produce accurate recommendations, a complimentary challenge is to rank recommendations based on their relevance. In this paper, we address this challenge for recommendation systems that are based on evolutionary coupling. Such systems use targeted association-rule mining to identify relevant patterns in a software system's change history. Traditionally, this process involves ranking artifacts using interestingness measures such as confidence and support. However, these measures often fall short when used to assess recommendation relevance. We propose the use of random forest classification models to assess recommendation relevance. This approach improves on past use of various interestingness measures by learning from previous change recommendations. We empirically evaluate our approach on fourteen open source systems and two systems from our industry partners. Furthermore, we consider complimenting two mining algorithms: CO-CHANGE and TARMAQ. The results find that random forest classification significantly outperforms previous approaches, receives lower Brier scores, and has superior trade-off between precision and recall. The results are consistent across software system and mining algorithm.

Data for Developing Machine Learning Models to Predict Base Resistance of Pile Foundation

This data was collected from 86 static pile load tests across 37 different high-rise buildings in Vietnam, especially soft soil region in Mekong Delta (Ho Chi Minh City). The data was used to develop machine learning models to predict base resistance of piles. Further details can be found in publication: "Influence of Settlement on Base Resistance of Long Piles in Soft Soil—Field and Machine Learning Assessments", Link: https://www.mdpi.com/2673-7094/4/2/25. Recommended citation: Nguyen, Thanh T., Viet D. Le, Thien Q. Huynh, and Nhu H.T. Nguyen. 2024. "Influence of Settlement on Base Resistance of Long Piles in Soft Soil—Field and Machine Learning Assessments" Geotechnics 4, no. 2: 447-469. https://doi.org/10.3390/geotechnics4020025

Harnessing interactions between traits and the environment to improve predictions of ecosystem functioning

The data correspond to the manuscript entitled "Harnessing interactions between traits and the environment to improve predictions of ecosystem functioning". Data needed to reproduce the figure 2 about springtails colonisation of defaunated soil blocks, from two different environments (forest or meadow), with the springtail species classified according to the supposed dispersal ability. Species with long legs and antennae, a well-developed jumping apparatus (furcula), and a complete visual apparatus were considered to be able to disperse more rapidly on their own and were thus categorized as “fast” dispersers. Other species with reduced locomotor and vision organs were categorized as “slow” dispersers (Ponge et al. 2006a). The "number of individuals" corresponds to the number of individuals found in each defaunated soil block after one week in the initial data set (Auclarc et al., 2009). Ponge J-F, Dubs F, Gillet S, et al. 2006a. Decreased biodiversity in soil springtail communities: the importance of dispersal and landuse history in heterogeneous landscapes. Soil Biol Biochem 38: 1158–61. Auclerc A, Ponge JF, Barot S, and Dubs F. 2009. Experimental assessment of habitat preference and dispersal ability of soil springtails. Soil Biol Biochem 41: 1596–604.

opencc-by-4.0Jul 2023View details →

Data and scripts for Alameda streamflow prediction paper

These are the data and scripts that accompany the Alameda streamflow prediction paper titled: "Streamflow prediction at the intersection of physics and machine learning: a case study of two Mediterranean-climate watersheds"

Data for paper: Transfer learning for cross-context prediction of protein expression from 5'UTR sequence

This depsit contains data for the paper entitled: "Transfer learning for cross-context prediction of protein expression from 5'UTR sequence". The rebeca.zip file contains a snapshot of the rebeca package which can be used to train, fine tune and test the CONV-LSTM model used in this study. The datasets.zip file contains the compiled sequence to expression datasets from across all Flow-seq expressions considered in this study.  The analysis.zip file contains all data files and jupyter notebooks necessary to reproduce our analysis. Each Flow-seq study has a dedicated folder (e.g., `fepB') with two sub-folders: 1. The `data\_split' folder, which contains the steps necessary to split the Flow-seq data for our ML experiments (a `readme.txt' file describes the input and output files and a jupyter notebook is available to reproduce the data split); 2. The `data\_analysis' folder, which contains a jupyter notebook and the necessary input files to reproduce the analysis of our experiments.

Distributed predictive QoS in presence of network- and mobility-related drifts

The datasets represent a dynamic environment, where several client-vehicles are moving in an urban area. Each client runs a streaming cloud service constantly receiving data packets. Network simulation is performed using Simu5G, a library that emulates a 5G cellular environment in OMNeT++. The simulator's radio parameters are set according to the Macro-cell model proposed by International Telecommunication Union. The map comprises of an urban 600x600 square meters area located in a suburb of a European capital. Inside this area four 5G base-stations (gNodeBs) have been installed by the national network operator, enabling four 5G cells. This area, divided into several blocks by the actual road network is integrated in our simulation by an OpenStreetMap (OSM) instance. The total number of included vehicles is set to 25, according to vehicle density statistics in the corresponding country. The road network's traffic is simulated by SUMO that creates a digitized version of the (real-world) OSM map and produces the route files for the vehicles. Route files are loaded in the Simu5G simulator, where a network-vehicular mobility co-simulation takes place. For each vehicle's route we assume SUMO's default parameters for urban environment: exponential speed model (with maximum speed restriction as defined by the OSM traffic rules) and the probability matrix at intersections for {lane keeping, turn left and right} as {0.5, 0.25 and 0.25}, respectively. The following information is collected for each vehicle using OMNeT++'s monitoring service: timestamp, channel quality indicator, packet delay, measured signal to noise ratio (SNR), client position (x,y,z), client velocity (x,y,z), received SNR, radio link control throughput, serving cell, client throughput. These features are sampled at 1 Hz and comprise the values of our synthetic time-series QoS dataset.  We have created two drift datasets that correspond to complementary cases of major long-term changes in the considered environment: 1) a network infrastructure-driven scenario (Sc1) and 2) a human behavior-driven scenario (Sc2). In Sc1 we assume that two out of four gNodeBs are switched off under a cost-reduction on/off policy or an infrastructure-share strategy (adopted by MNOs) that would imply such changes. For Sc2 we modify the users' mobility pattern; we assume that a "hotspot" e.g., a metro station is created in the lower-right edge of the map resulting in a traffic increase to that area. This is achieved by increasing the probabilities of the routes leading to the "hotspot" in SUMO's route planning. All generated datasets have a total duration of 20 hrs (simulation time) and the respective drift event is introduced at t=10 hrs.

Preliminary results: Predicted cooling effect, lives saved and associated economic value from public green spaces in Paris

This dataset represents preliminary results predicting the cooling effect from public green spaces in Paris for the 10th, 22nd and 24th July 2019, the lives saved and associated economic valuation. The data format is a shapefile with coordinate reference system RGF93 v1 / Lambert-93 (EPSG:2154). Please see the README file for description of the variable names.  Full results will be shared in due course, alongside all code and a detailed description of the method. If you would like to know more about the method or would like to be informed when the full results and method are published, please contact Jo Garrett at j.k.garrett@Exeter.ac.uk