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.
1,943
datasets available to search
ShareScore release 0.9.0
Dataset results
1,943 results for “machine learning”
An Empirical Study of Refactorings and Technical Debt in Machine Learning Systems
<p>Machine Learning (ML), including Deep Learning (DL), systems, i.e., those with ML capabilities, are pervasive in today's data-driven society. Such systems are complex; they are comprised of ML models and many subsystems that support learning processes. As with other complex systems, ML systems are prone to classic technical debt issues, especially when such systems are long-lived, but they also exhibit debt specific to these systems. Unfortunately, there is a gap of knowledge in how ML systems actually evolve and are maintained. In this paper, we fill this gap by studying refactorings, i.e., source-to-source semantics-preserving program transformations, performed in real-world, open-source software, and the technical debt issues they alleviate. We analyzed 26 projects, consisting of 4.2 MLOC, along with 327 manually examined code patches. The results indicate that developers refactor these systems for various reasons, both specific and tangential to ML; some refactorings correspond to established technical debt categories. In contrast, others do not, and code duplication is a major cross-cutting theme that particularly involved ML configuration and model code, which was also the most refactored. We also introduce 14 and 7 new ML-specific refactorings and technical debt categories, respectively, and put forth several recommendations, best practices, and anti-patterns. The results can potentially assist practitioners, tool developers, and educators in facilitating long-term ML system usefulness.</p>
georgestein/ml-in-cosmology: Machine learning in cosmology
<p>An attempt to create a comprehensive list of machine learning applications to cosmology, organized by subject matter and arXiv posting date. See https://github.com/georgestein/ml-in-cosmology for the most up-to-date list.</p> <p>Each entry contains the paper title, a simple summary of the machine learning methods used in the work, and the arXiv link.</p> <p>This will continue to be periodically updated</p>
Data from: Evaluation of parametric and nonparametric machine-learning techniques for prediction of saturated and near-saturated hydraulic conductivity
Parametric and nonparametric supervised machine learning techniques were used to estimate saturated and near saturated hydraulic conductivities (Ks, K10) from easily measurable soil properties including name of pedological horizon (HOR), soil texture (sand, silt & clay), organic matter (OM), bulk density (BD) and water contents (θpF1, θpF2, θpF3 and, θpF4.2) measured at four different matric heads (-10, -100, -1000, and -15848 cm). Using a stepwise linear model (SWLM) and the Lasso regression as parametric methods with 316 data in training and 135 data in testing phase, four pedotransfer functions (PTFs) were obtained in which water contents for both methods play an important role compared to other variables. SWLM showed better performance than Lasso in the testing phase for log(Ks) and log(K10) prediction with RMSE of 0.666 and 0.551 cm d-1 and R2 of 0.26 and 0.65. Nonparametric supervised machine learning methods trained and tested with similar data set significantly improved the accuracy of Ks prediction with R2 of 0.52, 0.36 and 0.53 for Gaussian regression process (GPR), support vector machine (SVM) and Ensemble (ENS) method in the testing stage. These methods also described 74.9, 66.7 and 72.5% of the variation of log(K10). Bootstrapping method validated the strong performance of nonparametric techniques. Feature selection capability of GPR determined that instead of using a model with all predictors, HOR, silt, θpF1 and θpF3 are sufficient for the prediction of log(Ks) or log(K10), HOR, silt, and OM can predict as accurate as the comprehensive model with all variables.
Investigating Non-Usually Employed Features in the Identification of Architectural Smells: A Machine Learning-Based Approach
<p>Architectural smells (ASs) negatively affect the maintenance and evolution of software at the architectural level. Most of the current approaches for ASs identification rely on the same small and well-known set of usually employed metrics (UE-Ms) with fixed thresholds. Machine learning (ML) is a promising technique for smell identification as algorithms can learn from a rich set of metrics/features, covering several characteristics of the software and incorporating a certain degree of subjectivity. This has been explored by building datasets with a robust and rich set of features, including not only the UE-Ms but also other non-usually employed metrics (NUE-Ms). However, usually the UE-Ms determine the output of the algorithms, obfuscating other metrics that have the potential to improve the classification. This also leads to inflated and difficult to maintain datasets. <br> In this paper, we investigate the accuracy of some ML algorithms employing only NUE-Ms. We scoped our study in the classification of two smells: God Component and Unstable Dependency. This investigation revealed a set of NUE-Ms that can be also used to identify these smells and the contribution of each one for the classification. Based on this information, software engineers can then build a final dataset just with the potential features. We also briefly present our tool, called InSet, that was used by academics and practitioners to identify smells in their systems. The feedback of them was used as the oracle to compare our tool to other approaches and good results were reached. </p>
[ITU-T AI Challenge] Input/Output of project "Improving the capacity of IEEE 802.11 WLANs through Machine Learning"
<p>This data set will be used by participants of the ITU-T AI Challenge. </p> <p>The data set contains:</p> <ul> <li>Input files: contain information such as nodes labels, nodes position, or channels used. These files have been used to simulate the behavior of random WLAN deployments under different channel bonding conditions. </li> <li>Output files: contain the output of the simulations - throughput per STA, RSSI that each STA receives from its AP, interference map from APs' point of view, average SINR experienced by each device during packet receptions.</li> </ul> <p>More details can be found on the official website of the challenge: <a href="https://www.upf.edu/web/wnrg/ai_challenge">https://www.upf.edu/web/wnrg/ai_challenge</a></p> <p><strong>[Update - 28 July 2020] </strong>A script (<a href="https://zenodo.org/api/files/88053224-d3a9-417e-b034-f08c763069ac/script_process_dataset.sh?versionId=2817eabd-ab9e-496a-a7d6-f67d227c51bf">script_process_dataset.sh</a>) has been added to process the output files. In particular, the results of each deployment are separated into different files. Besides, different files are created according to the type of label/feature (throughput, airtime, RSSI map, and interference list).</p> <p><strong>[Update - 22 September 2020] </strong>A new feature has been added to all the files in the data set. In particular, we have added the average Signal-to-Interference-plus-Noise Ration (SINR) experienced by each STA during packet receptions (including data and control packets). The SINR values in APs are marked as Inf because we focus on downlink transmissions only.</p> <p><strong>[Update - 30 September 2020] </strong>The test data set has been released, which corresponds to the simulations of a set of deployments with different characteristics. Input node files are contained in <a href="https://zenodo.org/api/files/88053224-d3a9-417e-b034-f08c763069ac/input_node_files_test.zip">input_node_files_test.zip</a>, while <a href="https://zenodo.org/api/files/88053224-d3a9-417e-b034-f08c763069ac/output_simulator_test.zip">output_simulator_test.zip</a> includes the output generated by the simulator. The label (i.e., the throughput) of the test data set will not be included in this repository until the next update (estimated date: 15 October 2020).</p> <p><strong>[Update - 19 October 2020] </strong>After participants have submitted their solutions, we provide the entire test data set, including the actual throughput obtained by each AP and STA in the test deployments.</p>
Replication Package for the Paper: "A Machine Learning Based Ensemble Method for Automatic Multiclass Classification of Decisions: A Study of the Hibernate Developer Mailing List"
<p>This is the replication package for the paper: "A Machine Learning Based Ensemble Method for Automatic Classification of Decisions: A Study of the Hibernate Developer Mailing List". It contains the source code and dataset of our experiment for the replication by other researchers. In the meanwhile, we provide brief description of the files in the replication package below.</p> <p><strong>1. code folder</strong></p> <ul> <li><em>experiment.py </em>contains the source code for our experiment, which is conducted on Windows 10 and Python 3.7.0. <strong>Note that you may get slightly</strong> <strong>different experiment results when conducting the experiments on different environment configurations.</strong></li> <li><em>requirement.txt</em> records all the installation packages and their version numbers needed for the current program to run. You can use "<em>pip install -r requirement.txt</em>" to rebuild the project and install all dependencies. <strong>Note that you may get slightly different experiment results when using different packages or versions. </strong></li> </ul> <p><strong>2. dataset folder</strong></p> <ul> <li><em>decisions.xlsx </em>contains 844 labelled sentence-level decisions from the Hibernate developer mailing list.</li> </ul>
Machine learning simulation data
<p>README.md</p> <p>This project "A Machine Learning Protocol for Predicting Protein Infrared Spectra" was supported by Prof. Shaul Mukamel(the University of California, Irvine), Prof. Jonathan D. Hirst(University of Nottingham),and Prof.Jun Jiang(University of Science and Technology of China).</p> <p>Simulation data and code of ML protocl for IR spectra of proteins.</p> <p>Any researchers who interested in protein spectroscopy can use our ML protcol online service: <a href="http://dcaiku.com:12880/platform/first">http://dcaiku.com:12880/platform/first</a></p> <p>For the simulation data which including: <br> 1. optimization_M06L_b3lyp.tar: ab initio molecular dynamics (AIMD) trajectory and quantum mechanics (QM) data with full input and output files for N-methylacetamide (NMA) ;<br> 2. CCPVDZ-coupling.tar:QM data with full input and output files for N-acetyl-glycine-N'-methylamide (GLDP); <br> 3. MD_protein_2.tar: MD trajectory for 12 proteins with different temperatures;<br> 4. trp-cage.tgz: MD trajectory for trp-cage;</p>
Data from: Trends in anesthesiology research: a machine learning approach to theme discovery and summarization
Objectives: Traditionally, summarization of research themes and trends within a given discipline was accomplished by manual review of scientific works in the field. However, with the ushering in of the age of "big data", new methods for discovery of such information become necessary as traditional techniques become increasingly difficult to apply due to the exponential growth of document repositories. Our objectives are to develop a pipeline for unsupervised theme extraction and summarization of thematic trends in document repositories, and to test it by applying it to a specific domain. Methods: To that end, we detail a pipeline, which utilizes machine learning and natural language processing for unsupervised theme extraction, and a novel method for summarization of thematic trends, and network mapping for visualization of thematic relations. We then apply this pipeline to a collection of anesthesiology abstracts. Results: We demonstrate how this pipeline enables discovery of major themes and temporal trends in anesthesiology research and facilitates document classification and corpus exploration. Discussion: The relation of prevalent topics and extracted trends to recent events in both anesthesiology, and healthcare in general, demonstrates the pipeline's utility. Furthermore, the agreement between the unsupervised thematic grouping and human-assigned classification validates the pipeline's accuracy and demonstrates another potential use. Conclusion: The described pipeline enables summarization and exploration of large document repositories, facilitates classification, aids in trend identification. A more robust and user-friendly interface will facilitate the expansion of this methodology to other domains. This will be the focus of future work for our group.
Data from: Assessing the potential information content of multicomponent visual signals: a machine learning approach
Careful investigation of the form of animal signals can offer novel insights into their function. Here, we deconstruct the face patterns of a tribe of primates, the guenons (Cercopithecini), and examine the information that is potentially available in the perceptual dimensions of their multicomponent displays. Using standardized colour-calibrated images of guenon faces, we measure variation in appearance both within and between species. Overall face pattern was quantified using the computer vision 'eigenface' technique, and eyebrow and nose-spot focal traits were described using computational image segmentation and shape analysis. Discriminant function analyses established whether these perceptual dimensions could be used to reliably classify species identity, individual identity, age and sex, and, if so, identify the dimensions that carry this information. Across the 12 species studied, we found that both overall face pattern and focal trait differences could be used to categorize species and individuals reliably, whereas correct classification of age category and sex was not possible. This pattern makes sense, as guenons often form mixed-species groups in which familiar conspecifics develop complex differentiated social relationships but where the presence of heterospecifics creates hybridization risk. Our approach should be broadly applicable to the investigation of visual signal function across the animal kingdom.
Low-complexity Reinforcement Learning Decoders for Autonomous, Scalable, Neuromorphic intra-cortical Brain Machine Interfaces
<p><strong>General Description. </strong>TThis dataset comprises recordings from four BMI (Brain-Machine Interface) experiments conducted on two adult macaques. Three of the experiments involved joystick-controlled tasks, while the fourth was a center-out reaching task. In the center-out task, the macaque was trained to maneuver a joystick-controlled cursor from a central position on a computer screen to one of eight square-shaped target locations. The macaques were able to use a wireless integrated system to control a robotic platform (on which they were seated) enabling independent mobility driven by neuronal activity in their motor cortices. Neural activity was recorded from populations of single neurons via multiple electrode arrays implanted in the arm region of the primary motor cortex. A general overview is provided below:</p> <ol> <li>A titanium head post (Crist Instruments, MD, USA) was surgically affixed before implanting the microelectrode arrays. In NHP-A, four microelectrode arrays with 16 electrodes each were implanted, while NHP-B was implanted with one array containing 100 electrodes in the hand/arm region of the left primary motor cortex.</li> <li>Spike signals were recorded using an in-house 100-channel wireless neural recording system, sampled at 13 kHz. The wide-band signals were band-pass filtered between 300 and 3000 Hz to eliminate low-frequency components. Spike detection thresholds were determined using the formula: Thr = 5σ, where σ = median(|x| / 0.6745), <em>x</em> is the filtered signal, and <em>σ</em> estimates the standard deviation of background noise.</li> </ol> <p>In Experiments 1, 2, and 3, the behavioral task involved controlling the motion of a robotic wheelchair using a three-directional, spring-loaded joystick. These tasks included: a) turning 90° right, b) moving forward by 2 meters, c) turning 90° left, and d) remaining stationary for 5 seconds (stop task). The success rate varied across experiments. Experiment 4 also involved joystick control, but followed a classical center-out reaching paradigm. </p> <p><strong>Dataset Description. </strong>The dataset is organized into folders (labeled as experiment 1, 2, 3, and 4) containing data from both NHP-A and NHP-B. Each folder contains data from separate dates labeled as YYMMDD (at the end of the filename). For experiment 1, data from the following dates are present: 15-10-08, 15-10-12, 15-10-19, 15-10-26, 15-11-02, 15-11-16, 15-11-23, and 15-12-10. For experiment 2, following dates are: 18-02-20, 18-03-06, 18-03-08, 18-03-20, 18-03-26, 18-04-13, 18-04-16, 18-04-23. For experiment 3: 14-08-14, 14-08-18, 14-08-20, 15-10-14. For experiment 4: 18-12-03, 18-12-13, 19-01-07, 19-02-20. File naming conventions across all experiments are as follows</p> <ol> <li>targTest: This corresponds to the direction of the joystick recorded for each trial. (decoded using the decoder)</li> <li>targTrain: Ground truth label, corresponding to the actual direction of the joystick.</li> <li>testSet: Number of spike counts from each channel (used for testing corresponding to all the sessions)</li> <li>trainSet: Number of spike counts from each channel (used for calibration, mostly) </li> </ol> <p><strong>Additional Information.</strong> This dataset is a simplified and curated version designed to reproduce the results presented in the associated paper. Note that Experiments 1 and 3 have partial datasets already publicly available at: <a href="https://osf.io/dce96/" target="_new" rel="noopener">https://osf.io/dce96/</a>. However, those versions are raw and can be processed using the variable descriptions below to extract spike counts with a specified bin width. Each file includes the following fields:</p> <ol> <li> joystick_adfreq: The frequency of operation of the joystick.</li> <li>X_Voltage: The voltage reading corresponding to the x-coordinate (while joystick operation).</li> <li>Y_Voltage: The voltage reading corresponding to the y-coordinate (while joystick operation).</li> <li>Spike_data(Channel Number): The Channel Number corresponding to which the neuronal data is recorded.</li> <li>Spike_data(Cluster): Descripting the cluster on which the channels are placed.</li> <li>Spike_data(Spike Times): The timestamp corresponding to the detection of a spike.</li> <li>Spike_data(Spike Number): The total number of spikes calculated for a particular trial from a particular channel.</li> <li>Spike_data(Mean Spike Waveform): The mean neuronal data (for that trial from a particular channel) describing a spike.</li> <li>Spike_data(Spike Amplitude): The mean spike amplitude of that particular channel.</li> <li>IMETrainingData(SentSignals): The truth labels corresponding to a particular trial.</li> <li>IMETrainingData(Timestamps): Time stamps corresponding to each sent signal (data).</li> <li>IMETrainingData(ReasonFail): String data; Reason if the trial failed.</li> <li>IMETrainingData(TrialOutcomes): Trial results corresponding to successful or unsuccessful!</li> <li>IMETrainingData(StartTime): corresponding to the beginning of each trial.</li> <li>IMETrainingData(EndTime): corresponding to the end of each trial.</li> </ol> <p><strong>Possible use cases. </strong>This dataset is well-suited for designing, training, and evaluating iBMI decoders. It provides a valuable resource for researchers aiming to model sensorimotor cortical spiking, benchmark iBMI decoders under consistent conditions, or explore neuromorphic and reinforcement learning-based approaches to decoder design.</p> <p><strong>Contact Information. </strong>We would be delighted to hear from you if you find this dataset useful—especially if it contributes to a publication. Contact: A. Basu <arinbasu@cityu.edu.hk>; A. Ghosh <aghosh14@illinois.edu>.</p> <p><strong>Citation. </strong>A. Ghosh, S. Shaikh, B. Zhou, P. S. V. Sun, C. Libedinsky, R. So, A. Basu, "Low-complexity Reinforcement Learning Decoders for Autonomous, Scalable, Neuromorphic intra-cortical Brain Machine Interfaces," Neuroelectronics 2025(2):0006, <a href="https://doi.org/10.55092/neuroelectronics20250006">https://doi.org/10.55092/neuroelectronics20250006</a></p>
The protracted role of India-Eurasia collision in the uplift of the Tibetan plateau revealed by Machining Learning
Open the record for dataset details and reuse information.
Machine Learning in the Financial Industry - 189 Articles
Open the record for dataset details and reuse information.
Data and R code for cluster analysis and machine learning modelling of favourite places for outdoor recreation
Open the record for dataset details and reuse information.
Machine Learning-assisted immunophenotyping of peripheral blood identifies innate immune cells as best predictor of response to induction chemo-immunotherapy in head and neck squamous cell carcinoma – knowledge obtained from the CheckRad-CD8 trial
<p>Raw cell counts from peripheral blood immune phenotyping across individual patients.</p>
Leveraging Machine Learning for Size and Shape Analysis of Nanoparticles: A Shortcut to Electron Microscopy
Open the record for dataset details and reuse information.
Dynamic profiling and binding affinity prediction of NBTI antibacte-rials against DNA gyrase enzyme by multidimensional machine learning and molecular dynamics simulations
<p>The chemical libraries used in this study comprised of 199 and 133 structurally diverse novel bacterial topoisomerase inhibitors (<em>alias</em> NBTIs), with experimentally determined <em>in vitro</em> antibacterial potencies against <em>Staphylococcus aureus</em> DNA gyrase (IC<sub>50</sub>=0.007-50 µM) and <em>Escherichia coli</em> DNA gyrase (IC<sub>50</sub>=0.020-100 µM), respectively (named as NBTI<em><sub>SA</sub></em> and NBTI<em><sub>EC</sub></em>), were compiled from the literature as *.sdf file format. The chemical structures comprising both NBTI libraries were initially sketched by using ChemDraw Professional 20.1.1 suite and subsequently energetically minimized utilizing Discovery Studio’s integrated Merck Molecular Force Field (MMFF) module. Moreover 4D ligands ensembles of both libraries ready to be used for multidimensional QSAR modeling are available, as well.</p>
PPARγ-bla dataset curated and enriched using the Enalos tools and Enalos KNIME nodes for machine learning analysis (SCENARIOS project)
<p>A curated and enriched dataset for PPARγ-bla, intended for in silico model development, was obtained from PubChem BioAssay under the numeric identifier AID 743194 using Enalos tools and Enalos KNIME nodes. This dataset specifically utilizes compounds from the Tox21 10K chemical library that underwent screening against the PPARγ-bla HEK293H cell line. The cell line contains a beta-lactamase reporter gene, and all the information was extracted from PubChem Bioassay ID 743194 using Enalos tools and Enalos KNIME nodes. The original bioassay, consisting of 6587 compounds, assessed the antagonist activity of small molecules and classified them as 'active', 'inactive' or 'inconsistent' based on their AC50 (potency) score. The curated PPARγ dataset comprises 1230 compounds selected from the original bioassay and enriched with 777 molecular descriptors extracted from their 2D structure using EnalosMold2 KNIME nodes.</p>
SNSynergy: similarity network-based machine learning framework for synergy prediction towards new cell lines and new anticancer drug combinations
Open the record for dataset details and reuse information.
Unveiling the diffusion of Re, Cr, and I in saturated compacted bentonite using machine learning method
Open the record for dataset details and reuse information.
A UWB Radar and Machine Learning-Based Tool for Detecting Victims Through Foliage in Search and Rescue Operations
<h1>Project Description</h1> <p>During our research in University of West Attica (UniWA) we addressed the problem of victim detection through foliage in Search and Rescue operations. For this purpose, a dataset of respiration signal sessions in the field was collected using a proposed tool consiting of a UWB pulsed radar system, and then these data fed a machine learning tool to enhance FR's operations by providing predictions about human presence behind foliage. In addition, two anemometer sensors were used to record wind data, and a respiration belt was employed to obtain the ground truth measurements about the subject's respiration rate.</p> <p>The setup for each session was the same. The UWB radar [<a href="https://sensorlogic.ai/sensor-products">1</a>] was mounted on tripod facing the foliage, the subject was located behind the foliage wearing a respiration belt [<a href="https://www.zephyranywhere.com/">4</a>] for breath recording. On the same tripod two anemometers [<a href="https://gr.mouser.com/new/dfrobot/dfrobot-rs485-wind-speed-transmitter/">2</a>],[<a href="https://gr.mouser.com/new/dfrobot/dfrobot-rs485-wind-direction-transmitter/">3</a>] were placed so a comprehesive image of the wind condiditon during the session could be obtained. These sensors were connected to a laptop via USB, about 3 meters away. The distance between the tripod and the foliage was fixed at 1 meter. Foliage (mostly bushes and small olive trees) had length varying from 1 to 3 meters and the subject (in case of presence session) was from 0.5 to 3 meters away from the foliage. In total we never exceeded the 9.2 meters range (unambiguous range) limit of the radar.</p> <h1>Dataset Description</h1> <p>The dataset consists of 268 sessions of radar, wind and respiration belt data, of which 141 sessions correspond to human presence and 127 to human absence. Each session has a duration of 150 seconds, thus amounting to approximately 6 hours of data for human presence and approximately 5.5 hours of data for human absence.</p> <h2>Dataset Contents</h2> <p>Each session folder is given an individual name X = posixtime; this name designates the exact time (in posixtime format) when the session was started. For example, in the dataset preview below there can be seen one folder named "1688457913"; this folder corresponds to the measurement session that was initiated exactly on 1688457913 in posixtime format (in this example, X = 1688457913). Furthermore, for the "X" posixtime-named folder, there are the following subfolders and files:</p> <p>1. One subfolder named Workspaces_X, containing:</p> <ul> <li>Files named "<em>Workspace_k.mat</em>", where k the number of the created workspaces containing radar signal recording at 16 FPS.</li> <li>A file named "<em>settings.mat</em>", containing the device settings and the session's distances regarding topology.</li> <li>A file named "<em>windData_original.mat</em>", containing the original data from anemometer sensors saved from the data stream at 4 FPS, provided from a microcontroller followed RS485 protocol.</li> </ul> <p>2. Two files containing the raw data recorded from the respiration belt (only for folders corresponding to human presence and for which a respiration belt was used for obtaining the ground truth measurements of the subject's respiration data.)</p> <ul> <li>The "<em>1_YY_MM_DD_HH_MM_general.csv</em>", contains the timestamp in datetime of the sensor and the Android device, the heart rate estimation, the mean breaths per minute and the included IMU belt sensor measurement.</li> <li>The "<em>1_YY_MM_DD_HH_MM_wave.csv</em>", contains the timestamp in datetime of the sensor and the Android device, and 18 values (FPS) of the strain gauge sensor changes from the respiration belt.</li> </ul> <p>3. A file named "<em>X.xlsx</em>", containing the concatenation of the workspaces of the radar signal.</p> <p>4. A file named "<em>windData_X.csv</em>", containing the synchronized data of anemometer sensors with radar data.</p> <p>5. A file named "<em>BeltWfm_X.xlsx</em>", containing the synchronized data of respiration belt with radar data (only for folders corresponding to human presence and for which a respiration belt was used for obtaining the ground truth measurements of the subject's respiration data).</p> <h1>Proposed Tool COTS components</h1> <ol> <li>SLMX4 UWB pulse radar [<a href="https://sensorlogic.ai/sensor-products">1</a>]</li> <li>Wind Speed [<a href="https://gr.mouser.com/new/dfrobot/dfrobot-rs485-wind-speed-transmitter/">2</a>] and Direction [<a href="https://gr.mouser.com/new/dfrobot/dfrobot-rs485-wind-direction-transmitter/">3</a>] sensors</li> <li>Wind data recording equipment (UART TTL to RS485 Converter, MT3608 DC/DC converter, Arduino)</li> <li>Respiration belt [<a href="https://www.zephyranywhere.com/">4</a>]</li> </ol>
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.