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.
9,302
datasets available to search
ShareScore release 0.9.0
Dataset results
9,302 results for “DETECT”
Data Transformation for Clustering Utilization for Feature Detection in MS
<p>Dataset and roof-of-concept method used for proceeding titled "Data Transformation for Clustering Utilization<br> for Feature Detection in MS" of IWBBIO 22 conference.</p>
Raw Data for the article: Use of 27G needles improves sensitivity and performance of ATCC anaerobe reference microorganism detection in BacT/Alert system
<p>Effective detection of microbiological contaminations present in medicinal cellular products is a crucial step to ensure patients' safety. In recent decades, several rapid microbiological methods have been developed and validated, but variabilities linked to the use of different resources have led to discordant validation of methods and performance results. Considering this, while developing an in-house BacT/Alert-based method, we evaluated all of the materials used in its validation. Of particular importance, we noticed that the syringe gauge used to inject the samples into the bottles was crucial to obtain robust results. We chose to conduct a comparative test between the BacT/Alert system and the compendial method described in the European Pharmacopoeia, using five dilutions of nine reference microorganism strains and 21G or 27G needles. Our results confirmed that the BacT/Alert system is a valid and faster alternative method to assess sterility of clinical cell therapy products, and that the use of 27G needles increases its sensitivity to detect reference anaerobe microorganisms.</p>
Stanford fiber-optic DAS array: Earthquake detection dataset
<p>Repurposing the fiber-optic cables from the existing telecommunication infrastructure makes it possible to record dense continuous seismic data in urban areas at low cost. From 2016 to 2019, we connected a disctributed acoustic sensing (DAS) interrogator unit to the fiber-optic cables in telecommunication conduits under Stanford University campus, recording years of continuous seismic data.</p> <p>This repository contains processed TensorFlow Record data files containing examples of earthquake and background noise signals recorded by the Stanford fiber-optic DAS array. These data were used for training, evaluation, and testing of a convolutional neural network for earthquake detection. </p> <p> </p> <p> </p>
Radiomics and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to detect breast malignant Lesions
<p>We uploade the dataset of the manuscript "Radiomics and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to detect breast malignant Lesions" by Current Oncology.</p> <p> </p>
The Tensor Brain - Entity Level Visual Relationship Detection Challenge
<p>This dataset contains images and annotations from real-world scenarios. It is aimed at testing a machine's perception performance in terms of object recognition, relationship detection, and instance and semantic memory retrieval.</p>
Warren and entrance detections by thermal imager
<ol> <li>Thermal imaging technology is a developing field in wildlife management. Most thermal imaging work in wildlife science has been limited to larger ungulates and surface-dwelling mammals. Little work has been undertaken on the use of thermal imagers to detect fossorial animals and/or their burrows. Survey methods such as white-light spotlighting can fail to detect the presence of burrows (and therefore the animals within), particularly in areas where vegetation obscures burrows. Thermal imagers offer opportunity to detect the radiant heat from these burrows, and therefore the presence of the animal, particularly in vegetated areas. Thermal imaging technology has become increasingly available through the provision of smaller, more cost-effective units. Their integration with drone technology provides opportunities for researchers and land managers to utilise this technology in their research/management practices. </li> <li>We investigated the ability of both consumer (<AUD$20,000) and professional imagers (>AUD$65,000) mounted on drones to detect rabbit burrows (warrens) and entrances in the landscape as compared to visual assessment. </li> <li>Thermal imagery and visual inspection detected active rabbit warrens when vegetation was scarce. The presence of vegetation was a significant factor in detecting entrances (P<0.001, α=0.05). The consumer imager did not detect as many warren entrances as either the professional imager or visual inspection (P=0.009, α=0.05). Active warren entrances obscured by vegetation could not be accurately identified on exported imagery from the consumer imager and several false-positive detections occurred when reviewing this footage. </li> <li>We suggest that the exportable frame rate (Hz)was the key factor in image quality and subsequent false positive detections. This feature should be considered when selecting imagers and suggest that a minimum export rate of 30Hz is required. Thermal imagers are a useful additional tool to aid in identification of entrances for active warrens and professional imagers detected more warrens and entrances than either consumer imagers or visual inspection.</li> </ol>
TestDataset for Oneat networks for detection and prediction of dividing Hela cells for different imaging modalities
<p>Here we present the tif files to be used to test the Oneat networks for detection and prediction of division events for Hela cells imaged under different imaging modalities and presented originally here: https://zenodo.org/record/6139958#.Yjcjl3rMJD8</p>
Recurrence and metastasis detection of breast cancer
<p>This dataset includes 88 H&E stained whole slide images (WSI) of breast cancer downloaded from TCGA (<a href="https://portal.gdc.cancer.gov/repository/">https://portal.gdc.cancer.gov/repository/</a>) with the type of Formalin-Fixed Paraffin-Embedded (FFPE), of which 5 cases have recurrence or metastasis.</p>
Datasets for Multimodal Biosensing for Vestibular Network-Based Cybersickness Detection
<p>These are the datasets about the experimental group (N=20, where N is the sample size, that is, 20 participants in total) and control group (N=20, where N is the sample size, that is, 20 participants in total) for our published paper entitled "Multimodal Biosensing for Vestibular Network-Based Cybersickness Detection", DOI: 10.1109/JBHI.2021.3134024. </p> <p>1. What do these datasets include?</p> <p>There are 40 participants' data in 40 folders, respectively. Each folder includes EEG data, Questionnaires, and answers as well as other non-EEG biometrics and memory test result of the cognitive task.</p> <p><br> 1.1 EEG data<br> All EEG data is either *.easy file or *.info file. The *.easy file is the raw EEG data. The *.info file is the information (e.g., EEG montage) paired with those raw EEG data. The *.info file can be simply readable by any Notepad software. The *.easy file can be readable by Neuroelectrics's plugin for EEGLAB (https://www.neuroelectrics.com/wiki/index.php/EEGLAB). Note, most of the participants' EEG data is a single easy file, but due to technical problems, few participants' EEG data consists of some separated easy files. Please use the function 'merge dataset' in the EEGLAB to merge them, and then use the following markers to extract segments of interest.</p> <p>All received EEG markers are integer numbers. Specifically, the markers are as follows:</p> <p>For control group:<br> a) The 'target' stimuli in the cognitive task: 16<br> b) The 'distractor' stimuli in cognitive task:32<br> c) The end of Baseline_1(that is, before the first cognitive task): 37<br> d) The end of Baseline_2(that is, before the round 1 neutral task): 47<br> e) The end of Baseline_3(that is, before the round 2 neutral task): 57<br> f) The end of Baseline_4(that is, before the second cognitive task): 67<br> g) The end of FMS reporting during the round 1 neutral task: 100<br> h) The end of FMS reporting during the round 2 neutral task: 101</p> <p>For experimental group:</p> <p>a) The 'target' stimuli in the cognitive task: 16<br> b) The 'distractor' stimuli in cognitive task:32<br> c) The end of Baseline_1(that is, before the first cognitive task): 37<br> d) The end of Baseline_2(that is, before the tunnel travel task): 47<br> e) The end of Baseline_3(that is, before the rollercoaster task): 57<br> f) The end of Baseline_4(that is, before the second cognitive task): 67<br> g) The end of FMS reporting during the Tunnel travel task: 100<br> h) The end of FMS reporting during the Rollercoaster task: 101</p> <p>1.2 Questionnaires</p> <p>1.2.1 SSQ<br> All SSQ questionnaires are named as xxx_QuestionnaireResult.csv, where xxx stands for the timestamps.</p> <p>1.2.2 FMS</p> <p>For control group:<br> All FMS questionnaires are named as xxx_Nature_FMS_backup.csv or xxx_Bio-data and FMS Nature.csv, where xxx stands for the timestamps and 'Nature' refers to the vection-free neutral task. The FMS scores in the xxx_FMS_backup.csv and xxx_Bio-data and FMS 'Task name'.csv are the exactly same. Unlike the xxx_Bio-data and FMS 'Task name'.csv contains the non-EEG biometrics as well, the xxx_FMS_backup.csv is pure FMS scores and easy to read.</p> <p>For experimental group:</p> <p>All FMS questionnaires are named as xxx_Gabor_FMS_backup.csv or xxx_Rollercoaster_FMS_backup.csv or xxx_Bio-data and FMS GaborRacer.csv or xxx_Bio-data and FMS Rollercoaster.csv, where xxx stands for the timestamps and Gabor or GaborRacer refer to the tunnel travel task. The FMS scores in the xxx_FMS_backup.csv and xxx_Bio-data and FMS 'Task name'.csv are the exactly same. Unlike the xxx_Bio-data and FMS 'Task name'.csv contains the non-EEG biometrics as well, the xxx_FMS_backup.csv is pure FMS scores and easy to read.</p> <p>1.3 Non-EEG biometrics<br> All non-EEG biometrics are named as xxx_Bio-data 'Task name'.csv, where 'Task name' refers to 'VA' (that is the cognitive task), or 'Nature' (for the control group) or 'GaborRacer' (for the experimental group) or 'Rollercoaster' (for the experimental group). The column information is as follows:<br> Column A: time<br> Column Q: PPG raw data (the left index finger)<br> Column R: Fingertip temperature (the left middle finger)<br> Column S: Forehead temperature<br> Column T: VR hermetic space temperature</p> <p>The data in other columns are not used in this study.</p> <p>1.4 The memory test result of the cognitive task</p> <p>Memory test result: xxx_CheckMemoryResult.csv, where xxx stands for the timestamps.</p> <p>Column A: time</p> <p>Column B: memory test result (Correct/Wrong)</p> <p>Column C: the number of the target (green sunfish)</p> <p>Column D: the reported number of the target in the memory test</p>
Fused Image dataset for convolutional neural Network-based crack Detection (FIND)
<p>The “<strong>F</strong>used <strong>I</strong>mage dataset for convolutional neural <strong>N</strong>etwork-based crack <strong>D</strong>etection” (<strong>FIND</strong>) is a large-scale image dataset with pixel-level ground truth crack data for deep learning-based crack segmentation analysis. It features four types of image data including raw intensity image, raw range (i.e., elevation) image, filtered range image, and fused raw image. The FIND dataset consists of 2500 image patches (dimension: 256x256 pixels) and their ground truth crack maps for each of the four data types.</p> <p>The images contained in this dataset were collected from multiple bridge decks and roadways under real-world conditions. A laser scanning device was adopted for data acquisition such that the captured raw intensity and raw range images have pixel-to-pixel location correspondence (i.e., spatial co-registration feature). The filtered range data were generated by applying frequency domain filtering to eliminate image disturbances (e.g., surface variations, and grooved patterns) from the raw range data [1]. The fused image data were obtained by combining the raw range and raw intensity data to achieve cross-domain feature correlation [2,3]. Please refer to [4] for a comprehensive benchmark study performed using the FIND dataset to investigate the impact from different types of image data on deep convolutional neural network (DCNN) performance.</p> <p>If you share or use this dataset, please cite [4] and [5] in any relevant documentation. </p> <p>In addition, an image dataset for crack classification has also been published at [6].</p> <p>References:</p> <p>[1] Shanglian Zhou, & Wei Song. (2020). Robust Image-Based Surface Crack Detection Using Range Data. Journal of Computing in Civil Engineering, 34(2), 04019054. <a href="https://doi.org/10.1061/(asce)cp.1943-5487.0000873">https://doi.org/10.1061/(asce)cp.1943-5487.0000873</a></p> <p>[2] Shanglian Zhou, & Wei Song. (2021). Crack segmentation through deep convolutional neural networks and heterogeneous image fusion. Automation in Construction, 125. <a href="https://doi.org/10.1016/j.autcon.2021.103605">https://doi.org/10.1016/j.autcon.2021.103605</a></p> <p>[3] Shanglian Zhou, & Wei Song. (2020). Deep learning–based roadway crack classification with heterogeneous image data fusion. Structural Health Monitoring, 20(3), 1274-1293. <a href="https://doi.org/10.1177/1475921720948434">https://doi.org/10.1177/1475921720948434</a> </p> <p>[4] Shanglian Zhou, Carlos Canchila, & Wei Song. (2023). Deep learning-based crack segmentation for civil infrastructure: data types, architectures, and benchmarked performance. Automation in Construction, 146. <a href="https://doi.org/10.1016/j.autcon.2022.104678">https://doi.org/10.1016/j.autcon.2022.104678</a></p> <p>[5] (<strong>This dataset</strong>) Shanglian Zhou, Carlos Canchila, & Wei Song. (2022). Fused Image dataset for convolutional neural Network-based crack Detection (FIND) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.6383044">https://doi.org/10.5281/zenodo.6383044</a></p> <p>[6] Wei Song, & Shanglian Zhou. (2020). Laser-scanned roadway range image dataset (LRRD). Laser-scanned Range Image Dataset from Asphalt and Concrete Roadways for DCNN-based Crack Classification, DesignSafe-CI. <a href="https://doi.org/10.17603/ds2-bzv3-nc78">https://doi.org/10.17603/ds2-bzv3-nc78</a></p>
Tango Spacecraft Wireframe Dataset Model for Line Segments Detection
<p><strong>Reference Paper:</strong></p> <p><a href="https://doi.org/10.1016/j.actaastro.2023.01.012"><strong>M. Bechini, M. Lavagna, P. Lunghi, Dataset generation and validation for spacecraft pose estimation via monocular images processing, Acta Astronautica 204 (2023) 358–369</strong></a></p> <p><a href="https://www.researchgate.net/publication/361924362_Spacecraft_Pose_Estimation_via_Monocular_Image_Processing_Dataset_Generation_and_Validation">M. Bechini, P. Lunghi, M. Lavagna. "Spacecraft Pose Estimation via Monocular Image Processing: Dataset Generation and Validation". In 9th European Conference for Aeronautics and Aerospace Sciences (EUCASS)</a></p> <p><strong>General Description:</strong></p> <p>The "<em>Tango Spacecraft Wireframe Dataset Model for Line Segments Detection</em>" dataset here published should be used for line detection and segmentation tasks. It is split into 30002 train images and 3002 test images representing the Tango spacecraft from Prisma mission, being the only publicly available dataset of synthetic space-borne images tailored to line detection tasks (up to our knowledge). The label of each image gives the reprojection of a simplified wireframe model of Tango on the image plane split into lines. The labels are written following the Wireframe Model format. The "<em>Tango Spacecraft Wireframe Dataset Model for Line Segments Detection</em>" is also the largest dataset with wireframe annotations available up to date. More information on the dataset split and on the label format are reported below. </p> <p><strong>Images Information:</strong></p> <p>The dataset comprises 30002 synthetic grayscale images of Tango spacecraft from Prisma mission that serves as train set, while the test set is formed by 3002 synthetic grayscale images of Tango spacecraft from Prisma mission in PNG format. About 1/6 of the images both in the train and in the test set have a non-black background, obtained by rendering an Earth-like model in the raytracing process used to define the images reported. The images are noise-free to increase the flexibility of the dataset. The illumination direction of the spacecraft in the scene is uniformly distributed in the 3D space in agreement with the Sun position constraints.</p> <p><br> <strong>Labels Information:</strong></p> <p>Labels in the Wireframe dataset format are here provided in separated JSON files. The files are formatted per each image as in the following example:</p> <ul> <li> width : 98 # width in pixels (int) of the current image</li> <li> height : 176 # height in pixels (int) of the current image</li> <li> lines : [[line1], [line2], ..., [lineN]] # list of lines in each image</li> <li> filename : tango_img_866.png # string with image name and format</li> </ul> <p>Per each line (line1, ... , lineN) in lines, the format is [x0, y0, x1, y1].</p> <p>(x0, y0) are the coordinates (float) of the line starting point in the image reference frame (x pointing right and y pointing down with origin located in the top-left corner of the image).<br> (X1, y1) are the coordinates (float) of the line ending point in the image reference frame (x pointing right and y pointing down with origin located in the top-left corner of the image).</p> <p>Note that the starting point is assumed to be the left-most endpoint (lower x coordinate in image reference frame) of each line. In the case of vertical lines, the starting point is the upper-most endpoint (lower y coordinate in image reference frame) of each line.</p> <p><strong>VERSION CONTROL</strong></p> <ul> <li><strong>v1.0</strong>: All the images (both for train and test) have different resolutions, with Tango always centered in the image. The height of the images is in the range 19 - 352 pixels, while the width is in the range 16 - 336 pixels. The height over width ratio spans from 0.34 to 3.25.</li> <li><strong>v2.0</strong>: This version contains all the images of v1.0 in the .zip folder named <em>Tango_WF.zip</em>, while in the .zip folder named <em>Tango_WF_fullscale.zip</em> there is the dataset (both train and test) of full scale images. These images have width=height=1024 pixels. The position of tango with respect to the camera is randomly selected from a uniform distribution, but it is ensured the full visibility in all the images. The labels for the wireframe are in the same format of v1.0.</li> </ul> <p>Note: the dataset in v1.0 is obtained by cropping the fullscale images in v2.0 and by properly rescaling the wireframe annotations.</p> <p>Note: this dataset contains the same images of the <em>"Tango Spacecraft Dataset for Region of Interest Estimation and Semantic Segmentation</em><em>"</em> v1.0 (DOI: <a href="https://doi.org/10.5281/zenodo.6507863">https://doi.org/10.5281/zenodo.6507863</a>) and also "<em>Tango Spacecraft Dataset for Monocular Pose Estimation</em>" v1.0 (DOI: <a href="https://doi.org/10.5281/zenodo.6499007">https://doi.org/10.5281/zenodo.6499007</a>) and they can be used together by combining the annotations of the relative pose and the ones of the reprojected wireframe model of Tango, with also the ones of the ROI. <strong>These three datasets give the most comprehensive dataset of space borne synthetic images ever published</strong> (up to our knowledge).</p>
Bioacoustic data for evaluating wind denoising and detection methods
<p>Acoustic survey data accompanying publication "Wind-robust sound event detection and denoising for bioacoustics", by Julius Juodakis and Stephen Marsland.</p> <p>Contents (see the publication for details):</p> <ul> <li>pilotdata/: short audio files used for selecting the best-fit wind model</li> <li>surveys/LSK_additional_wavs/: remaining recordings from the little spotted kiwi survey that have not been deposited previously</li> <li>surveys/rawannots/: annotations produced by the unadjusted, OLS-adjusted and QR-adjusted detectors, for two bird surveys</li> <li>surveys/reviewed/: annotations passing human review for the unadjusted and OLS-adjusted detectors, for two bird surveys</li> <li>denoising/: examples of noise and signal which were mixed to evaluate the denoising.</li> </ul> <p>Audio files are provided in WAV PCM format. Annotations and filters are intended for use with AviaNZ software (https://www.avianz.net/), and provided in AviaNZ-compatible JSON format.</p>
Dataset for detecting the electrical behavior of photovoltaic panels from RGB images
<p>The dynamic reconfiguration and maximum power point tracking in large-scale photovoltaic (PV) systems require a large number of voltage and current sensors. In particular, the reconfiguration process requires a pair of voltage/current sensors for each panel, which introduces costs, increases size and reduces reliability of the installation. A suitable solutions for reducing the number of sensors is to adopt image-based solution to estimate the electrical characteristics of the PV panels, but the lack of reliable data with large diversity of irradiance and shading conditions is a major problem in this topic. Therefore, this paper presents dataset correlating RGB images and electrical data of PV panels with different irradiance and shading conditions. The dataset was designed to support the design of image-based estimators of electrical data, which could be used to replace large arrays of sensors. The paper also describes the measurement platform used to collect the data, which helps to replicate the experiments in different geographical locations.</p>
Replication Package for the Paper: "Code Smells Detection via Modern Code Review: A Study of the OpenStack and Qt Communities"
<p>This repository contains the data and results from the paper "Code Smells Detection via Modern Code Review: A Study of the OpenStack and Qt Communities" submitted to the ICPC 2021 special issue of the Empirical Software Engineering Journal, 2021.</p> <p> </p> <p>The replication package contains the following two folders:</p> <p> </p> <p><strong>1) data folder</strong></p> <p>The data folder contains the following four folders, which is organized by research questions (RQs).</p> <ul> <li>RQ1: The RQ1 folder contains the retrieved 1,539 code reviews that discuss code smells. Each review includes four parts: Code Change URL, Code Smell, Code Smell Discussion, and Source Code URL.</li> <li>RQ2: The RQ2 folder contains the coded data for RQ2, called <em>Data Labeling & Encoding for RQ2.mx18</em>. It is the results of data labeling and encoding for RQ2, which was analyzed by the MAXQDA tool.</li> <li>RQ3 and RQ5: <ul> <li><em>Extracted data for RQ3.1.xlsx</em>: this file contains the extracted data (i.e., specific refactoring actions suggested by reviewers) for RQ3.1.</li> <li><em>Data Labeling & Encoding for RQ3 and RQ5.mx18</em>: this file contains the extracted data for RQ3 (excluding the specific refactoring actions in RQ3.1) and RQ5.</li> <li><em>Code change status for RQ5.xlsx</em>: this file contains the information of status of code changes where the developers disagreed with the reviewers and chose to ignore the identified code smells.</li> </ul> </li> <li>RQ4: The RQ4 folder contains the extracted data for RQ4, called <em>Extracted data for RQ4.xlsx</em>.</li> </ul> <p>Note: The mx18 files can be opened by MAXQDA 18 or higher versions, which are available at https://www.maxqda.com/ for download. You may also use the free 14-day trial version of MAXQDA 2018, which is available at https://www.maxqda.com/trial for download.</p> <p> </p> <p><strong>2) scripts folder</strong></p> <p>The scripts folder contains the Python scripts that were used to search for code smell terms and the list of code smell terms.</p> <ul> <li><em>keyword.txt</em> contains the keywords associated with code smells, such as "smell, duplication, and dead".</li> <li><em>get_changes.py</em> is used for getting code changes from OpenStack and Qt.</li> <li><em>get_comments.py</em> is used for getting review comments for each code change.</li> <li><em>keywords_search.py</em> is used for searching review comments that contain at least one keyword.</li> <li><em>random_select.py</em> is used for randomly selecting review comments that do not contain any keyword.</li> <li><em>keywords_improve.py</em> is used for improving the keyword-based mining approach.</li> <li><em>tools.py</em> is used for supporting the process of keywords improving.</li> </ul>
Appendix of "Impact of Change Granularity in Refactoring Detection"
<p>This is the dataset for ICPC 2022 Impact of Change Granularity in Refactoring Detection, which contains data about coarse-grained refactorings in 19 open source repositories.</p> <p>There are 19 csv files in this dataset. Each of the csv contains 8 rows:</p> <p>1. repository: repository name <br> 2. commit(s): commit SHA-1 hash<br> 3. detected_refactoring_type: refactoring type detected in that commit<br> 4. description: description for that refactoring<br> 5. leftSideLocations: refactoring start place<br> 6. rightSideLocations: refactoring end place<br> 7. is_effective: whether this refactoring is a coarse-grained refactoring (null for refactoring whose coarse-granularity is equal to 1)<br> 8. granularity: coarse-granularity of this refactoring</p> <p>Note that refactorings detected using RefactoringMiner(2.2) with invalid locations has been excluded.</p>
Supplementary material for: AIRBORNE LASER SCANNING CHANGE DETECTION FOR QUANTIFYING GEOMORPHOLOGICAL PROCESSES IN HIGH MOUNTAIN REGIONS
<p>Supplementary material for: TCII/10-AIRBORNE LASER SCANNING CHANGE DETECTION FOR QUANTIFYING GEOMORPHOLOGICAL PROCESSES IN HIGH MOUNTAIN REGIONS</p> <p>For submission of the full paper to: International Society for Photogrammetry and Remote Sensing (ISPRS) / <strong>XXIV ISPRS Congress 2022 Nice, France, 6 - 11 June 2022</strong>.</p> <p><strong>ADDITIONAL FIGURES AND MAPS</strong><br> Supplementary materials:<br> Figure S1: Classification preparation and decision tree.<br> Figure S2: 3D distance change and change offset overall map.<br> Figure S3: Geomorphological map inventoried by manual mapping.<br> Figure S4: Classified real changes of the valley area between 2006 and 2017.<br> Figure S5: Classified real changes between 2006 and 2017.</p> <p> </p> <p> </p> <p> </p>
WHUL8-CDb, a block-level labelled cloud detection dataset collected from Landsat 8
<p>WHUL8-CDb was collected for the training of weakly-supervised cloud detection methods. It includes 500 globally distributed Landsat 8 Level-1C images (Fig. 1) collected following the distribution of the L8 Biome dataset as it comes to biomes and dominant land cover types. The motivation is that clouds are similar with each other in different regions, while the backgrounds are very different. In order to increase the diversity of training samples, we selected images with more background pixels by setting the cloud percentage from 0 to 50 when searching images. To handle all cloud situations, 5 images full of clouds were collected and included in WHUL8-CDb.</p> <p>The WHUL8-CDb dataset canbe downloaded on the following links:</p> <p>First part (1~11) : <a href="http://doi.org/10.5281/zenodo.6420035">https://doi.org/10.5281/zenodo.6420035</a></p> <p>Second part (12~22) : <a href="http://doi.org/10.5281/zenodo.6467663">https://doi.org/10.5281/zenodo.6467663</a></p> <p>Third part (23~33): <a href="http://doi.org/10.5281/zenodo.6510533">https://doi.org/10.5281/zenodo.6510533</a></p> <p>Fourth part (34~44): <a href="http://doi.org/10.5281/zenodo.6510679">https://doi.org/10.5281/zenodo.6510679</a></p> <p>Fifth part (45~55): <a href="http://doi.org/10.5281/zenodo.6510681">https://doi.org/10.5281/zenodo.6510681</a></p> <p>Sixth part (56~65): <a href="http://doi.org/10.5281/zenodo.6510681">https://doi.org/</a><a href="https://doi.org/10.5281/zenodo.6510683">10.5281/zenodo.6510683</a></p>
Face mask detection and masked facial recognition dataset (MDMFR Dataset)
<p>The unavailability of a unified standard dataset for face mask detection and masked facial recognition motivated us to develop an in-house MDMFR dataset (<a href="https://www.sciencedirect.com/science/article/pii/S1319157821003633#b0170">MDMFR, 2022</a>) to measure the performance of face mask detection and masked facial recognition methods. Both of these tasks have different dataset requirements. Face mask detection requires the images of multiple persons with and without mask. Whereas, masked face recognition requires multiple masked face images of the same person. Our MDMFR dataset consists of two main collections, 1) face mask detection, and 2) masked facial recognition. There are 6006 images in our MDMFR dataset. The face mask detection collection contains two categories of face images i.e., mask and unmask. Our detection database consists of 3174 with mask and 2832 without mask (unmasked) images. To construct the dataset, we captured multiple images of the same person in two configurations (mask and without mask). The masked facial recognition collection contains a total of 2896 masked images of 226 persons. More specifically, our dataset includes the images of both male and female persons of all ages including the children. The images of our dataset are diverse in terms of gender, race, and age of users, types of masks, <a href="https://www.sciencedirect.com/topics/computer-science/illumination-condition">illumination conditions</a>, face angles, occlusions, environment, format, dimensions, and size, etc. Before being fed to our DeepMaskNet model, all images are scaled to a width and height of 256 pixels. All images have a bit depth of 24. We prepared the images of our dataset for the proposed DeepMaskNet model during preprocessing where images are cropped in Adobe-Photoshop to exclude the extra information like neck and shoulder. As the input size of our Deepmasknet model was 256-by-256, so images were resized to 256-by-256 in publicly available Plastiliq Image Resizer software (<a href="https://www.sciencedirect.com/science/article/pii/S1319157821003633#b0215">Plastiliq, 2022</a>).</p>
Datasets for Simulation-based Anomaly Detection for Multileptons at the LHC
<p>The simulated background and signal data used for a signal model agnostic machine learning search. This search examined the decay of the Higgs boson to leptons working off of LHC data from the Atlas experiment. Details are provided in the paper entitled "Simulation-based Anomaly Detection for Multileptons at the LHC". </p>
A synthetic fraud detection data set.
<p>A synthetic fraud detection data set created using sklearn's make_blob for use in a blog.</p> <p>X, y = datasets.make_blobs(n_samples=[800000,200000], centers=None, cluster_std=[10.0, 2],random_state=42,n_features=4)</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.