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.
1,654
datasets available to search
ShareScore release 0.7.1
Dataset results
1,654 results for “Automation”
The Dataset of Quantifying Alignment Deviations for Uniaxial Material Mechanical Testing via Automated Machine Learning
<p>The dataset consists of 4 alignment deviations of the uniaxial testing machine as well as 12 strain measurement points on cruciform specimens. A deep learning model is trained on the dataset to quantify 4 alignment deviations using 12 strain values on a thin plate specimen. The design of experiments includes Optimal Latin Hypercube, numerical modelling of Finite Element Methods. Using the Optimal Latin Hypercube, 12496 distinct groups of DOE simulation tests are constructed. Under the boundary conditions of 4 distinct deviations, 12 strain values at the required location on the cruciform specimen are obtained using Python scripts.</p> <p>The nine CSV files correspond to the nine analysis steps. The only difference among the nine analysis steps is the pretension force acting on RP1. Each CSV file contains 24 columns of data, and the corresponding contents of each column of data are as follows:</p> <ul> <li>Columns 1-6 are the freedoms of RP1 reference point, which are U1, U2, U3, ur1, UR2 and UR3 respectively;</li> <li>Columns 7-12 are the freedoms of RP2 reference points, which are U1, U2, U3, ur1, UR2 and UR3 respectively;</li> <li>Columns 13-24 are the strain values of the last 12 strain measurements of the thin plate rectangular specimen。</li> </ul>
Data from: Crowdsourcing training material for automated bird sound classification – a pilot study
<p>Data from the manuscript "Crowdsourcing training material for automated bird sound classification – a pilot study" by Petteri Lehikoinen, Meeri Rannisto, Ulisses Camargo, Aki Aintila, Patrik Lauha, Esko Piirainen, Panu Somervuo & Otso Ovaskainen</p>
[Supplementary material] Automated Code Generation for Inter-parameter Dependencies in REST APIs
<p>This is the supplementary material of the paper entitled Automated Code Generation for Inter-parameter Dependencies in REST APIs.</p>
Data from: Domain-specific neural networks improve automated bird sound recognition already with small amount of local data
<p><span><span>An automatic bird sound recognition system is a useful tool for collecting data of different bird species for ecological analysis. Together with autonomous recording units (ARUs), such a system provides a possibility to collect bird observations on a scale that no human observer could ever match. During the last decades progress has been made in the field of automatic bird sound recognition, but recognizing bird species from untargeted soundscape recordings remains a challenge. <br></span></span></p> <p><span><span>In this article we demonstrate the workflow for building a global identification model and adjusting it to perform well on the data of autonomous recorders from a specific region. We show how data augmentation and a combination of global and local data can be used to train a convolutional neural network to classify vocalizations of 101 bird species. We construct a model and train it with a global data set to obtain a base model. The base model is then fine-tuned with local data from Southern Finland in order to adapt it to the sound environment of a specific location and tested with two data sets: one originating from the same Southern Finnish region and another originating from a different region in German Alps.<br></span></span></p> <p><span><span>Our results suggest that fine-tuning with local data significantly improves the network performance. Classification accuracy was improved for test recordings from the same area as the local training data (Southern Finland) but not for recordings from a different region (German Alps). Data augmentation enables training with a limited number of training data and even with few local data samples significant improvement over the base model can be achieved. Our model outperforms the current state-of-the-art tool for automatic bird sound classification.<br></span></span></p> <p><span><span>Using local data to adjust the recognition model for the target domain leads to improvement over general non-tailored solutions. The process introduced in this article can be applied to build a fine-tuned bird sound classification model for a specific environment.</span></span></p>
Automated Classification of Dyadic Conversation Scenarios using Autonomic Nervous System Responses
<p>This repository contains supplementary files for our study "Automated Classification of Dyadic Conversation Scenarios using Autonomic Nervous System Responses". The two files are:</p> <p>- ConversationClassification_FeatureTable.xlsx is an MS Excel file that contains all physiological features (individual features and synchrony features) for all valid dyads and all intervals.</p> <p>- ConversationClassification_SynchronyCalculation.zip contains the MATLAB 2021b code used to calculate four physiological synchrony metrics: dynamic time warping, nonlinear interdependence, coherence, and cross-correlation. It also includes some open-source code from other authors that is required for our synchrony calculation code to work. As inputs, the synchrony calculation functions accept 4-minute signal vectors from both participants in the dyad.</p>
Sample dataset to accompany Hamilton, Chang, Lee, & Chang. Semi-automated anatomical labeling and inter-subject warping of high-density intracranial recording electrodes in electrocorticography
<p>This dataset accompanies the following paper: <br> Hamilton, Chang, Lee, and Chang. Semi-automated anatomical labeling and inter-subject warping of <br> high-density intracranial recording electrodes in electrocorticography</p> <p>This data includes an anonymized and de-identified CT and T1 MRI scan, plus all intermediate and final files<br> produced by the img_pipe software for testing and instructional purposes. This subject had a right hemisphere implantation including high density grids, strip electrodes, and depth electrodes.</p> <p>img_pipe software and installation instructions can be found at http://github.com/changlabucsf/img_pipe</p> <p>If you wish to follow along yourself, we recommend creating a new subject in your Freesurfer $SUBJECTS_DIR, <br> then copy the acpc and CT directories from this dataset into that new subject directory. </p> <p>The electrode montage is provided in test_subj_montage.txt and describes the type of electrodes implanted<br> (grid, strip, or depth) and their general location. </p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 10. Meeting Room Equipped with Different Sensors
<p>To illustrate the basic working principle of a perceptual neuro-symbolic network in a concrete application, a simplified, concrete example is given in the following. In this example, office meeting room is equipped with different sensors (tactile floor sensors, motion detectors, light barriers, a door contact sensor, a camera, and a microphone) as sketched in Figure 10.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 9. Modular Hierarchical Organization of Perceptual Neuro-Symbolic Networks
<p>In analogy to how it is reported for the brain by A. Luria, connections of the lowest levels of the architecture of Figure 9 are predefined. Higher-level connections are set via a learning process, concretely via a supervised learning process that was described in detail in . More recent research findings indicate that learning could also already take place at lower levels of<br> perception and that unsupervised learning could be crucial for setting these connections. In, first attempts have been made to develop an unsupervised learning strategy for the model.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 8. Modular Hierarchical Organization of the Human Perceptual System
<p>In order to perform complex tasks, neuro-symbols have to be connected to neuro-symbolic networks. For the structural organization of this neuro-symbolic network, the modular hierarchical organization of the human perceptual cortex as described by A. Luria [27] was taken as a blueprint (see Figure 8).</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 1. Examples for Today Well Manageable and not yet Well Manageable Processes in Automation
<p>Despite the many progresses that have been achieved in automation and AI over the last decades, applications have mainly been successful for circumscribed, well-defined tasks in environments that are relatively specific, well-structured, and characterized by a limited number of possible occurring processes, states, and ways how to react to them [59]. There, technical solutions can even exceed certain human capabilities. The situation changes however if we switch to systems that should perform a broader range of tasks in less well-structured environments. Here, the limits of technical feasibility are being stretched to the utmost [7]. This fact is probably best illustrated by<br> the following two concrete examples in Figure 1.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 4. Methodology in the Field of Brain-Like Artificial Intelligence for Automation
<p>An overview of the methodology for developing Brain-Like AI architectures for automation– as applied in the research of this article – is sketched in Figure 4.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 6. Overview of Brain-Inspired Architecture for Machine Perception
<p>Figure 6 gives an overview about the developed architecture for human-like machine perception which bases on insights about the working mechanisms of the human perceptual system. The central element of the model is the so-called “neuro-symbolic network”, which processes data coming from different sensor sources and additionally considers information coming from<br> “higher-level” sources referred to as memory, knowledge, and focus of attention . Within the neuro-symbolic network, so called “neuro-symbolic information processing” takes place based on information exchange of “neuro-symbols”. The focus in this article will be on the description of the<br> functioning of neuro-symbols and the neuro-symbolic network. Details about the other modules and functional aspects of the model can amongst others be found in.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 7. Function Principle of Neuro-Symbols
<p>In Figure 7, the basic function principle of neuro-symbols is illustrated. One characteristic of neuro-symbols is that they represent symbolic information. In the case of perception, this symbolic inforamtion are perceptual images like for instance a face or a voice (see Section 4.2.1.2 for more details). Furthermore, neuro-symbols show a number of analogies to biological neurons. They have an activation degree (AD), which indicates if the perceptual image that each neuro-symbol respresents is currently perceived in the environment. Each neuro-symbol has a certain number of inputs and one output. Via the inputs, information about the activation degree of other neurosymbols is collected. Like illustrated in the example of Figure 7, a neuro-symbol representing a face could for instance receive information from neuro-symbols representing a head, eyes, and a mouth.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 2. Two Possible Progress Scenarios for How to Reach Towards Machines and Systems with Human- Level Cognitive Skills
<p>Having identified the need for novel methods for machine recognition, situation assessment, and decision making in order to advance further in different automation domains, an important question is by what means can we reach such sophisticated mechanisms. The long-term goal in<br> mind is to construct machines and systems showing performances comparable to or even beyond human skill levels. In a guest talk at the Vienna University of Technology in 2008, Prof. Etienne Barnard, an expert in the field of Artificial Intelligence, made an interesting “conceptual suggestion” for two possible progress scenarios to reach this goal which could be summarized as depicted in Figure 2.</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 5. Differences in Validation Criteria between Classical Engineering Sciences and the Field of Brain- Like Artificial Intelligence for Automation
<p>A usual validation procedure in classical fields of engineering and computer sciences as well as in Applied AI, which is currently the dominant AI research domain, is to analyze and implement different potential methods to solve a given problem and to then compare their performance. What is thus usually desired are comparable, quantifiable results. In comparison, the starting situation is<br> different in the field of Brain-Like AI (see Figure 5).</p>
BRAIN Journal-Brain-Like Artificial Intelligence for Automation-Figure 3. Basic "Components" of Artificial and Biological (Brain-Controlled) Automation Systems
<p>Although basing on different concepts concerning their details, artificial and biological (brain-controlled) automation systems show common points concerning their principal components (see Figure 3).</p>
Automated Segmentation of Large Image Datasets using Artificial Intelligence for Microstructure Characterisation and Damage Analysis
<p>Many properties of commonly used materials are driven by their microstructure, which can be influenced<br>by the composition and manufacturing processes. To optimise future materials, understanding the<br>microstructure is critically important. Here, we present two novel approaches based on artificial intelligence<br>that allow the segmentation of the phases of a microstructure for which simple numerical approaches, such<br>as thresholding, are not applicable: One is based on the nnU-Net neural network, and the other on generative<br>adversarial networks (GAN).<br>Using scanning electron microscopy images collected from large areas (~1 mm²) of dual-phase steels as a<br>case study, we demonstrate how both methods effectively segment intricate microstructural details,<br>including martensite, ferrite, and damage sites, for subsequent analysis.<br>Either method shows substantial generalizability across a range of image sizes and conditions, including<br>heat-treated microstructures with different phase configurations. The nnU-Net excels in mapping large<br>image areas. Conversely, the GAN-based method performs reliably on smaller images, providing greater<br>step-by-step control and flexibility over the segmentation process.<br>This study highlights the benefits of segmented microstructural data for various purposes, such as<br>calculating phase fractions, modelling material behaviour through finite element simulation, and<br>conducting geometrical analyses of damage sites and the local properties of their surrounding<br>microstructure.</p> <p>https://doi.org/10.1016/j.matdes.2024.113031</p>
Data from: How many specimens make a sufficient training set for automated three dimensional feature extraction?
<p>Deep learning has emerged as a robust tool for automating feature extraction from 3D images, offering an efficient alternative to labour-intensive and potentially biased manual image segmentation methods. However, there has been limited exploration into the optimal training set sizes, including assessing whether artificial expansion by data augmentation can achieve consistent results in less time and how consistent these benefits are across different types of traits. In this study, we manually segmented 50 planktonic foraminifera specimens from the genus Menardella to determine the minimum number of training images required to produce accurate volumetric and shape data from internal and external structures. The results reveal unsurprisingly that deep learning models improve with a larger number of training images with eight specimens being required to achieve 95% accuracy. Furthermore, data augmentation can enhance network accuracy by up to 8.0%. Notably, predicting both volumetric and shape measurements for the internal structure poses a greater challenge compared to the external structure, due to low contrast differences between different materials and increased geometric complexity. These results provide novel insight into optimal training set sizes for precise image segmentation of diverse traits and highlight the potential of data augmentation for enhancing multivariate feature extraction from 3D images. </p>
FAIRness Assessment of Biomedical Data Using Automated Tools (Dataset)
<p>The data were collected as part of a Master's thesis project aimed at evaluating various automated FAIR assessment tools, applying them to biomedical data. The data sets identifiers were gathered as part of the Open Data LoM and IoM incentivization at Charité Universitätsmedizin Berlin, available at <a title="Dataset of the results of data validation for articles from 2021" href="https://doi.org/10.5281/zenodo.8249758">https://doi.org/10.5281/zenodo.8249758</a>, and reused in this project.</p> <p>The data represents cleaned, aggregated, and transformed results obtained from the API services of the following FAIR assessment tools: F-UJI, FAIR Enough, FAIR-Checker, and FAIR EVA.</p> <p>The raw data in .Rdata format will be shared on GitHub repository at <a title="FAIR Tools Analysis" href="https://github.com/anastasiabright/fair-tools-analysis">https://github.com/anastasiabright/fair-tools-analysis</a>.</p>
Dataset: Fidelity Disruptive Automation ETF (FBOT) 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.
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.