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.
6
datasets available to search
ShareScore release 0.9.0
Dataset results
6 results for “Outdoor Localization”
A Dataset of Outdoor RSS Measurements for Localization
<p><strong>Update: </strong>New version includes additional samples taken in November 2022.</p> <p><strong>Dataset Description</strong></p> <p>This dataset is a large-scale set of measurements for RSS-based localization. The data consists of received signal strength (RSS) measurements taken using the POWDER Testbed at the University of Utah. Samples include either 0, 1, or 2 active transmitters.</p> <p>The dataset consists of 5,214 unique samples, with transmitters in 5,514 unique locations. The majority of the samples contain only 1 transmitter, but there are small sets of samples with 0 or 2 active transmitters, as shown below. Each sample has RSS values from between 10 and 25 receivers. The majority of the receivers are stationary endpoints fixed on the side of buildings, on rooftop towers, or on free-standing poles. A small set of receivers are located on shuttles which travel specific routes throughout campus.</p> <table> <tbody> <tr> <th>Dataset Description</th> <th>Sample Count</th> <th>Receiver Count</th> </tr> </tbody> <tbody> <tr> <td>No-Tx Samples</td> <td>46</td> <td>10 to 25</td> </tr> <tr> <td>1-Tx Samples</td> <td>4822</td> <td>10 to 25</td> </tr> <tr> <td>2-Tx Samples</td> <td>346</td> <td>11 to 12</td> </tr> </tbody> </table> <p>The transmitters for this dataset are handheld walkie-talkies (Baofeng BF-F8HP) transmitting in the FRS/GMRS band at 462.7 MHz. These devices have a rated transmission power of 1 W. The raw IQ samples were processed through a 6 kHz bandpass filter to remove neighboring transmissions, and the RSS value was calculated as follows:</p> <p>\(RSS = \frac{10}{N} \log_{10}\left(\sum_i^N x_i^2 \right) \)</p> <table> <tbody> <tr> <th>Measurement Parameters</th> <th>Description</th> </tr> </tbody> <tbody> <tr> <td>Frequency</td> <td>462.7 MHz</td> </tr> <tr> <td>Radio Gain</td> <td>35 dB</td> </tr> <tr> <td>Receiver Sample Rate</td> <td>2 MHz</td> </tr> <tr> <td>Sample Length</td> <td>N=10,000</td> </tr> <tr> <td>Band-pass Filter</td> <td>6 kHz</td> </tr> <tr> <td>Transmitters</td> <td>0 to 2</td> </tr> <tr> <td>Transmission Power</td> <td>1 W</td> </tr> </tbody> </table> <p>Receivers consist of Ettus USRP X310 and B210 radios, and a mix of wide- and narrow-band antennas, as shown in the table below Each receiver took measurements with a receiver gain of 35 dB. However, devices have different maxmimum gain settings, and no calibration data was available, so all RSS values in the dataset are uncalibrated, and are only relative to the device.</p> <p><strong>Usage Instructions</strong></p> <p>Data is provided in <code>.json</code> format, both as one file and as split files.</p> <pre><code>import json data_file = 'powder_462.7_rss_data.json' with open(data_file) as f: data = json.load(f) </code></pre> <p>The <code>json</code> data is a dictionary with the sample timestamp as a key. Within each sample are the following keys:</p> <ul> <li><code>rx_data</code>: A list of data from each receiver. Each entry contains RSS value, latitude, longitude, and device name.</li> <li><code>tx_coords</code>: A list of coordinates for each transmitter. Each entry contains latitude and longitude.</li> <li><code>metadata</code>: A list of dictionaries containing metadata for each transmitter, in the same order as the rows in <code>tx_coords</code></li> </ul> <p><strong>File Separations and Train/Test Splits</strong></p> <p>In the <code>separated_data.zip</code> folder there are several train/test separations of the data.</p> <ul> <li><code>all_data</code> contains all the data in the main JSON file, separated by the number of transmitters.</li> <li><code>stationary</code> consists of 3 cases where a stationary receiver remained in one location for several minutes. This may be useful for evaluating localization using mobile shuttles, or measuring the variation in the channel characteristics for stationary receivers.</li> <li><code>train_test_splits</code> contains unique data splits used for training and evaluating ML models. These splits only used data from the single-tx case. In other words, the union of each splits, along with <code>unused.json</code>, is equivalent to the file <code>all_data/single_tx.json</code>. <ul> <li>The <code>random</code> split is a random 80/20 split of the data.</li> <li><code>special_test_cases</code> contains the stationary transmitter data, indoor transmitter data (with high noise in GPS location), and transmitters off campus.</li> <li>The <code>grid</code> split divides the campus region in to a 10 by 10 grid. Each grid square is assigned to the training or test set, with 80 squares in the training set and the remainder in the test set. If a square is assigned to the test set, none of its four neighbors are included in the test set. Transmitters occuring in each grid square are assigned to train or test. One such random assignment of grid squares makes up the <code>grid</code> split.</li> <li>The <code>seasonal</code> split contains data separated by the month of collection, in April, July, or November</li> <li>The <code>transportation</code> split contains data separated by the method of movement for the transmitter: walking, cycling, or driving. The <code>non-driving.json</code> file contains the union of the walking and cycling data.</li> <li><code>campus.json</code> contains the on-campus data, so is equivalent to the union of each split, not including <code>unused.json</code>.</li> </ul> </li> </ul> <p><strong>Digital Surface Model</strong></p> <p>The dataset includes a digital surface model (DSM) from a State of Utah 2013-2014 LiDAR <a href="https://doi.org/10.5069/G9TH8JNQ">survey</a>. This map includes the University of Utah campus and surrounding area. The DSM includes buildings and trees, unlike some digital elevation models.</p> <p>To read the data in python:</p> <pre><code>import rasterio as rio import numpy as np import utm dsm_object = rio.open('dsm.tif') dsm_map = dsm_object.read(1) # a np.array containing elevation values dsm_resolution = dsm_object.res # a tuple containing x,y resolution (0.5 meters) dsm_transform = dsm_object.transform # an Affine transform for conversion to UTM-12 coordinates utm_transform = np.array(dsm_transform).reshape((3,3))[:2] utm_top_left = utm_transform @ np.array([0,0,1]) utm_bottom_right = utm_transform @ np.array([dsm_object.shape[0], dsm_object.shape[1], 1]) latlon_top_left = utm.to_latlon(utm_top_left[0], utm_top_left[1], 12, 'T') latlon_bottom_right = utm.to_latlon(utm_bottom_right[0], utm_bottom_right[1], 12, 'T') </code></pre> <p><strong>Dataset Acknowledgement:</strong> This DSM file is acquired by the State of Utah and its partners, and is in the public domain and can be freely distributed with proper credit to the State of Utah and its partners. The State of Utah and its partners makes no warranty, expressed or implied, regarding its suitability for a particular use and shall not be liable under any circumstances for any direct, indirect, special, incidental, or consequential damages with respect to users of this product.</p> <p><strong>DSM DOI:</strong> <a href="https://doi.org/10.5069/G9TH8JNQ">https://doi.org/10.5069/G9TH8JNQ</a></p>
Dataset from: 'Tropical deforestation accelerates local warming and loss of safe outdoor working hours'
<p>Abstract:</p> <p>'Climate change has increased heat exposure in many parts of the tropics, negatively impacting outdoor worker productivity and health. Although it is known that tropical deforestation causes local warming, the extent to which this warming affects people across the tropics is unknown. Here, we combine worker health guidelines with satellite, reanalysis, and population data to investigate how increases in local temperatures associated with recent deforestation (2003-2018) affects outdoor working conditions across low-latitude countries, and how future global climate change will magnify heat exposure for people in deforested areas. We find that the local warming associated with just 15 years of deforestation has caused losses in safe thermal working conditions for 2.8 million outdoor workers. We also show recent large-scale forest loss caused particularly large impacts on populations in locations such as the Brazilian states of Mato Grosso and Pará. Future global warming and additional forest loss will magnify these impacts.'</p>
A Reproducible Analysis of RSSI Fingerprinting for Outdoors Localization Using Sigfox: Preprocessing and Hyperparameter Tuning (datasets)
<p>The train/validation/test sets used in the study "<strong>A Reproducible Analysis of RSSI Fingerprinting for Outdoors Localization Using Sigfox: Preprocessing and Hyperparameter Tuning</strong>".</p> <p>Preprint:<a href="https://arxiv.org/abs/1908.06851"> https://arxiv.org/abs/1908.06851</a></p> <p>Published paper: <a href="https://ieeexplore.ieee.org/document/8911792">https://ieeexplore.ieee.org/document/8911792</a></p> <p> </p> <p>The dataset used to create these sets was published in:</p> <p><a href="http://www.mdpi.com/2306-5729/3/2/13">http://www.mdpi.com/2306-5729/3/2/13</a></p> <p>The full dataset is available here:</p> <pre><a href="https://doi.org/10.5281/zenodo.1212478">https://doi.org/10.5281/zenodo.1212478</a> </pre> <p>The credit for the creation of the dataset goes to Aernouts, Michiel; Berkvens, Rafael; Van Vlaenderen, Koen; and Weyn, Maarten.</p> <p> </p>
Deep Reinforcement Learning for END-To-END Local Motion Planning of Autonomous Aerial Robots in Unknown Outdoor Environments: Real-Time Flight Experiments
<p> </p> <p>Videos for the real flight tests and the simulation experiments </p>
Outdoor fingerprint localization with BLE beacons
<p><strong>Introduction</strong></p><p>The data set contains received signal strength (RSS) measurements made with Bluetooth Low Energy (BLE) technology, which can be used for outdoor fingerprint-based localization applications, as presented in an article "<a href="https://ieeexplore.ieee.org/document/9900607">LOG-a-TEC Testbed Outdoor Localization Usign BLE Beacons</a>".</p><p><strong>Measurement setup</strong></p><p>The measurements were created with WL1837MOD radio connected to a <a href="https://log-a-tec.eu/hw-lgtc.html">in-house embedded device</a>. The data set was collected with 40 nodes of the <a href="https://log-a-tec.eu">LOG-a-TEC testbed</a> positioned at the campus of the Jožef Stefan Institute, Ljubljana. The experimentation area is composed of 5 x 26 positions separated by 1.2 m covering 150 square meters. On each position a mobile phone was broadcasting BLE advertising beacons with power of -2 dBm in interval of 100 ms. Surrounding testbed nodes were collecting the beacons for approximately a minute for each position.</p><p><strong>Data set</strong></p><p>Measurements are stored in JSON format where each object contains rss measurement (in dBm) with corresponding timestamp (in seconds). The folder contains two JSON files:</p><ul><li>spring_data.json - measurements made in May 2022,</li><li>winter_data.json - smaller measurements made in December 2021. This data set contains only the measurements from the middle row of the campus park.</li></ul>
A dataset for RSSI based outdoor localization using LoRaWAN in a harbor as a harsh and industrial environment
<p>Enabling precise device localization is a critical requirement for the future of industry. Leveraging signal features for location determination has emerged as a leading approach and good alternative for Global Navigation Satellite Systems (GNSS) because of their limitations (low accuracy for indoor environments, expensive chips, and high energy consumption). On this basis, to provide localization for IoT in an industry with a harsh environment, the adopted wireless networks should have a long range coverage area. LoRaWAN is one of the most common communication networks that can provide large coverage with low power consumption and low implementation cost. Between various signal features that can be used for localization, Received Signal Strength (RSS) received more attention because of their low-cost deployment. But, RSS is highly dependent and sensitive to environmental changes, such as temperature, humidity, and background noise. This sensitivity becomes more intensive in an industrial environment with a harsh and dynamic environment. In order to evaluate the environmental effects on RSS in the harsh and highly dynamic industry, we present a comprehensive repository of LoRaWAN Received Signal Strength Indicator (RSSI) measurements, collected in a harbor as a testbed featuring three LoRaWAN gateways and one mobile end node. During the data collecting process, the mobile device obtains its location via a GPS and transmits it as the LoRaWAN message. In addition, to provide more insight of the effect of dynamic environment on the RSSI, two end nodes are implemented in fixed locations. These end nodes transmit messages with fixed time intervals including their unique id. The collected dataset includes RSSI and SNR measurements recorded by multiple gateways for each transmitted packet by fixed or mobile end nodes, and timestamp. This dataset enables the development and evaluation of RSSI-based localization and allows researchers to explore the challenges and opportunities associated with localization in dynamic IoT deployments.</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.