Find research datasets worth reusing

opencc-by-4.0Feb 2020View details →

A Wi-Fi Channel State Information (CSI) and Received Signal Strength (RSS) data-set for human presence and movement detection

This data-set consists of antenna-wise received signal strength (RSS) and channel state information (CSI) data. Both types of data have been captured using the <a href="https://dhalperi.github.io/linux-80211n-csitool/">Intel CSI Tools</a>. The RSS data have been used in our paper "Detecting Human Movement from Ambient Wi-Fi Signal Strength". This release extends the README with a data dictionary for the annotations. We hope to add more information about the data acquisition process (e.g., data acquisition protocols).

opencc-by-4.0Apr 2024View details →

HALOC Dataset | WiFi CSI-based Long-Range Person Localization Using Directional Antennas

WiFi CSI-based Long-Range Person Localization Using Directional Antennas This repository contains the HAllway LOCalization (HALOC) dataset and WiFi system CAD files as proposed in <a href="https://openreview.net/forum?id=AOJFcEh5Eb" target="_blank" rel="noopener">[1]</a>. PyTroch Dataloader A minimal PyTorch dataloader for the HALOC dataset is provided at: <a href="https://github.com/StrohmayerJ/HALOC" target="_blank" rel="noopener">https://github.com/StrohmayerJ/HALOC</a> Dataset Description The HALOC dataset comprises six sequences (in .csv format) of synchronized WiFi Channel State Information (CSI) and 3D position labels. Each row in a given .csv file represents a single WiFi packet captured via ESP-IDF, with CSI and 3D coordinates stored in the "data" and ("x", "y", "z") fields, respectively. The sequences are divided into training, validation, and test subsets as follows: <table> <tbody> <tr> <td>Subset</td> <td>Sequences</td> </tr> <tr> <td>Training</td> <td>0.csv, 1.csv, 2.csv and 3.csv</td> </tr> <tr> <td>Validation</td> <td>4.csv</td> </tr> <tr> <td>Test</td> <td>5.csv</td> </tr> </tbody> </table>   WiFi System CAD files We provide CAD files for the 3D printable parts of the proposed WiFi system consisting of the main housing (housing.stl), the lid (lid.stl), and the carrier board (carrier.stl) featuring mounting points for the Nvidia Jetson Orin Nano and the ESP32-S3-DevKitC-1 module.  Download and Use This data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to our paper [1]. [1] Strohmayer, J., and Kampel, M. (2024). “WiFi CSI-based Long-Range Person Localization Using Directional Antennas”, The Second Tiny Papers Track at ICLR 2024, May 2024, Vienna, Austria. <a href="https://openreview.net/forum?id=AOJFcEh5Eb" target="_blank" rel="noopener">https://openreview.net/forum?id=AOJFcEh5Eb</a> BibTeX citation: <pre>@inproceedings{ strohmayer2024wifi, title={WiFi {CSI}-based Long-Range Person Localization Using Directional Antennas}, author={Julian Strohmayer and Martin Kampel}, booktitle={The Second Tiny Papers Track at ICLR 2024}, year={2024}, url={https://openreview.net/forum?id=AOJFcEh5Eb} }</pre>

opencc-by-4.0Oct 2024View details →

Wallhack1.8k Dataset | Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition

This repository contains the Wallhack1.8k dataset for WiFi-based long-range activity recognition in Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS)/Through-Wall scenarios, as proposed in [1,2], as well as the CAD models (of 3D-printable parts) of the WiFi systems proposed in [2]. PyTroch Dataloader A minimal PyTorch dataloader for the Wallhack1.8k dataset is provided at: <a href="https://github.com/StrohmayerJ/wallhack1.8k" target="_blank" rel="noopener">https://github.com/StrohmayerJ/wallhack1.8k</a> Dataset Description The Wallhack1.8k dataset comprises 1,806 CSI amplitude spectrograms (and raw WiFi packet time series) corresponding to three activity classes: "no presence," "walking," and "walking + arm-waving." WiFi packets were transmitted at a frequency of 100 Hz, and each spectrogram captures a temporal context of approximately 4 seconds (400 WiFi packets). To assess cross-scenario and cross-system generalization, WiFi packet sequences were collected in LoS and through-wall (NLoS) scenarios, utilizing two different WiFi systems (BQ: biquad antenna and PIFA: printed inverted-F antenna). The dataset is structured accordingly: <ul> <li>LOS/BQ/ <- WiFi packets collected in the LoS scenario using the BQ system</li> <li>LOS/PIFA/ <- WiFi packets collected in the LoS scenario using the PIFA system</li> <li>NLOS/BQ/ <- WiFi packets collected in the NLoS scenario using the BQ system</li> <li>NLOS/PIFA/ <- WiFi packets collected in the NLoS scenario using the PIFA system</li> </ul> These directories contain the raw WiFi packet time series (see Table 1). Each row represents a single WiFi packet with the complex CSI vector H being stored in the "data" field and the class label being stored in the "class" field. H is of the form [I, R, I, R, ..., I, R], where two consecutive entries represent imaginary and real parts of complex numbers (the Channel Frequency Responses of subcarriers). Taking the absolute value of H (e.g., via numpy.abs(H)) yields the subcarrier amplitudes A. To extract the 52 L-LTF subcarriers used in [1], the following indices of A are to be selected: <pre><code># 52 L-LTF subcarriers csi_valid_subcarrier_index = [] csi_valid_subcarrier_index += [i for i in range(6, 32)] csi_valid_subcarrier_index += [i for i in range(33, 59)]</code></pre> Additional 56 HT-LTF subcarriers can be selected via: <pre><code># 56 HT-LTF subcarriers csi_valid_subcarrier_index += [i for i in range(66, 94)] csi_valid_subcarrier_index += [i for i in range(95, 123)]</code></pre> For more details on subcarrier selection, see <a href="https://docs.espressif.com/projects/esp-idf/en/stable/esp32/api-guides/wifi.html">ESP-IDF</a> (Section Wi-Fi Channel State Information) and <a href="https://github.com/espressif/esp-csi">esp-csi</a>. Extracted amplitude spectrograms with the corresponding label files of the train/validation/test split: "trainLabels.csv," "validationLabels.csv," and "testLabels.csv," can be found in the spectrograms/ directory. The columns in the label files correspond to the following: [Spectrogram index, Class label, Room label] <ul> <li>Spectrogram index: [0, ..., n]</li> <li>Class label: [0,1,2], where 0 = "no presence", 1 = "walking", and 2 = "walking + arm-waving."</li> <li>Room label: [0,1,2,3,4,5], where labels 1-5 correspond to the room number in the NLoS scenario (see Fig. 3 in [1]). The label 0 corresponds to no room and is used for the "no presence" class.</li> </ul> Dataset Overview: Table 1: Raw WiFi packet sequences. <table> <tbody> <tr> <td>Scenario</td> <td>System</td> <td>"no presence" /  label 0</td> <td>"walking"  / label 1</td> <td>"walking + arm-waving" /  label 2</td> <td>Total</td> </tr> <tr> <td>LoS</td> <td>BQ</td> <td>b1.csv</td> <td>w1.csv, w2.csv, w3.csv, w4.csv and w5.csv</td> <td>ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv</td> <td> </td> </tr> <tr> <td>LoS</td> <td>PIFA</td> <td>b1.csv</td> <td>w1.csv, w2.csv, w3.csv, w4.csv and w5.csv</td> <td>ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv</td> <td> </td> </tr> <tr> <td>NLoS</td> <td>BQ</td> <td>b1.csv</td> <td>w1.csv, w2.csv, w3.csv, w4.csv and w5.csv</td> <td>ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv</td> <td> </td> </tr> <tr> <td>NLoS</td> <td>PIFA</td> <td>b1.csv</td> <td>w1.csv, w2.csv, w3.csv, w4.csv and w5.csv</td> <td>ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv</td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td>4</td> <td>20</td> <td>20</td> <td>44</td> </tr> </tbody> </table> Table 2: Sample/Spectrogram distribution across activity classes in Wallhack1.8k. <table> <tbody> <tr> <td>Scenario</td> <td>System</td> <td> "no presence" /  label 0 </td> <td> "walking"  / label 1 </td> <td>"walking + arm-waving" /  label 2</td> <td>Total</td> </tr> <tr> <td>LoS</td> <td>BQ</td> <td>149</td> <td>154</td> <td>155</td> <td> </td> </tr> <tr> <td>LoS</td> <td>PIFA</td> <td>149</td> <td>160</td> <td>152</td> <td> </td> </tr> <tr> <td>NLoS</td> <td>BQ</td> <td>148</td> <td>150</td> <td>152</td> <td> </td> </tr> <tr> <td>NLoS</td> <td>PIFA</td> <td>143</td> <td>147</td> <td>147</td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td>589</td> <td>611</td> <td>606</td> <td>1,806</td> </tr> </tbody> </table>   Download and Use This data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to one of our papers [1,2]. [1] Strohmayer, Julian, and Martin Kampel. (2024). “Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition”, In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 42-56). Cham: Springer Nature Switzerland, doi: <a href="https://doi.org/10.1007/978-3-031-63211-2_4" target="_blank" rel="noopener">https://doi.org/10.1007/978-3-031-63211-2_4</a>. [2] Strohmayer, Julian, and Martin Kampel., “Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition,” 2024 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2024, pp. 3594-3599, doi: <a href="https://doi.org/10.1109/ICIP51287.2024.10647666" target="_blank" rel="noopener">https://doi.org/10.1109/ICIP51287.2024.10647666</a>. BibTeX citations: <pre>@inproceedings{strohmayer2024data, title={Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition}, author={Strohmayer, Julian and Kampel, Martin}, booktitle={IFIP International Conference on Artificial Intelligence Applications and Innovations}, pages={42--56}, year={2024}, organization={Springer}} @INPROCEEDINGS{10647666,   author={Strohmayer, Julian and Kampel, Martin},   booktitle={2024 IEEE International Conference on Image Processing (ICIP)},    title={Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition},    year={2024},   volume={},   number={},   pages={3594-3599},   keywords={Visualization;Accuracy;System performance;Directional antennas;Directive antennas;Reflector antennas;Sensors;Human Activity Recognition;WiFi;Channel State Information;Through-Wall Sensing;ESP32},   doi={10.1109/ICIP51287.2024.10647666}} </pre>

opencc-by-4.0Dec 2021View details →

Alien CSI Akrotiri Bioblitz 2019

The Akrotiri Bioblitz in Cyprus was a one-off event held as part of the Alien-CSI COST Action (CA17122). It took place for 24 hours between Wednesday, February 27 and Thursday, February 28, 2019. The aim of this bioblitz was to improve knowledge of the biodiversity of the Akrotiri Peninsula, identify potential risks to the biodiversity caused by invasive species and trial methods that could be used throughout Europe for this purpose. More information about the event can be found on these pages: <a href="https://osf.io/csvgz/wiki/home/">https://osf.io/csvgz/wiki/home/</a>.    All bioblitz records can be found in the iNaturalist project <a href="https://www.inaturalist.org/projects/akrotiri-bioblitz-cyprus">akrotiri-bioblitz-cyprus</a> and in the GBIF dataset (Hadjikyriakou et al. 2019). At the time of writing, 396 species had obtained  “research grade” status on iNaturalist and included also captive and cultivated organisms. These species were assigned native/alien status, a level of establishment using the categories described by Groom et al. (2019a) and their occurrence in Akrotiri and Cyprus was determined based on the Flora of Cyprus by Hand et al. (2021), the Cyprus Database of Alien Species (CyDAS) by Martinou et al. (2020), the Amphibians and Reptiles of Cyprus by Baier et al. (2013), Fauna Europaea (<a href="https://fauna-eu.org/">https://fauna-eu.org</a>), Sparrow and John (2016), Ridout (1983), Peterson et al. (2019), Guerrini et al. (2007), Englezou et al. (2018), Nahum et al. (2010), Christia et al. (2011), Jørgensen and Sørensen (2008), Can and Arap (2005), Haouas gharsallah et al. (2010), Flint (1997), Bouaziz-Yahiatene et al. (2017), Zogaris et al. (2012), Gözüaçık and Atay (2016), Groom et al. (2019b), Savvides et al. (2015) and Litterski & Mayrhofer (1998). In addition, we compared our bioblitz species checklist with the species present in the occurrence dataset on GBIF preceding the bioblitz (GBIF 2019).  An overview of the establishment status of the recorded species during the Akrotiri bioblitz can be found in the csv file and summary table (pdf) included in this upload.

opencc-by-sa-4.0Jan 2022View details →

CSI-based Device-free Localization and Obfuscation

This dataset has been used to study CSI-based device-free localization and test the performance of different obfuscation systems in the paper "AntiSense: Standard-compliant CSI obfuscation against unauthorized Wi-Fi sensing." It contains many CSI traces collected in an indoor environment in several conditions. All the data have been collected with commercial Wi-Fi systems using IEEE 802.11ac and 80-MHz-wide channels.

opencc-by-4.0Feb 2022View details →

HYDRO-CSI, Project 1.2: In-stream hydrology. Part 1: Groundwater measurements

The continuous exchange of water between surface water and groundwater is a key environmental process controlling the transport and the fate of nutrients, solutes and pollutants in river networks. The dynamics of the near-stream groundwater has a non-negligeable role on controlling flow direction and solutes exchange between the stream water with the adjacent groundwater, however it is rarely considered in solute transport experiments. Despite the amount of individual studies, we are still uncertain about how the physical processes controlling in-stream solutes transport change with different hydrologic conditions and how these processes can be inferred by modelling outcomes. In this project we investigated groundwater and stream interactions in order to characterize the physical processes that control the water and solute exchange in the river corridor and their variability over time. To do so, we drilled 36 wells in the near-stream domain, and 7 piezometers in the stream channel. We observed the water level and electrical conductivity every 15 min at 22 of the 36 wells with a water level sensor (Orpheus Mini, OTT, Kempten, Germany, resolution of 1 mm and accuracy of ±0.05% FS) over a period of 32 months (July 2018 - March 2021). The dataset includes the following files: > "Raw groundwater measurements.xlsx"  This file includes groundwater table elevation measured as depth from the upper limit of the well (time step of 15 minutes, Orpheus Mini, OTT, Kempten, Germany, resolution of 1 mm and accuracy of ±0.05% FS). Every excel file includes also Electrical Conductivity measurements (μS/cm) and Voltage (V) of the instruments. Every sheet in this .xlsx file reports measurement for one sensor in the specific observation-well where it was placed. > "Groundwater elevation data - wells metadata and fixed groundwater table elevation.xlsx" This file includes the raw groundwater table measurements measured via the OTT, information on the well network, elevation and location of the observation wells, location of subsurface layers, and suggested correction of the groundwater table measurements for short periods with missing data. > "Hand-measurements and metadata.xlsx" This file includes the list of in-situ inspections and hand-measurements of the groundwater table conducted over the entire observation period in every well and piezometer of the groundwater-monitoring well network. Every sheet includes details on the instruments measuring the groundwater table, their offset with hand-measured data, information on their re-calibration, and calculation of the groundwater elevation above the reference plane after each hand-measurement.

opencc-by-4.0Jun 2022View details →

CSI-COP Dataset of Organisations to Approach in Citizen Science Projects

This dataset complements CSI-COP project deliverable D2.3 report: 'Framework for Engaging Citizen Scientists'. The D2.3 deliverable was produced in 2020 by partners in CSI-COP work package 2 led by Professor Olga Stepankova of Czech Technical University, Prague (CTU). The Stepankova et al. (2020) report is available on this Zenodo platform here: <a href="https://zenodo.org/record/4066515#.Yrx9DezMLb0">https://zenodo.org/record/4066515#.Yrx9DezMLb0</a>

opencc-by-4.0Sep 2024View details →

Velocity from the shelf at Station CSI 6 in 2017

<div>Title: Velocity from the shelf at Station CSI 6 in 2017</div> <div> </div> <div>Velocity Data from ADCP deployed at CSI 6 (~ 20 m)</div> <div>Time - days counted from Jan. 1, 2017 (UTC) - Jan. 1 is Day 1.</div> <div>u, v, horizontal velocity in east and north direction in m/s</div> <div>Zmab (bin depth meter above bottom)</div> <div>Invalid data is indicated by a large velocity of -32.768 m/s</div> <div>PI: Chunyan Li at Louisiana State University</div> <div>Project: NSF 1736713 </div> <div>File name: Velocity_from_shelf_CSI6_2017.dat</div> <div> </div> <div>Pubications: </div> <div>Li, C. A. Sheremet, W. Huang, P. Dash, A. Katkar, M. N. Allahdadi, N. Chaichitehrani, C. M. Bachmann, V. H. Rivera-Monroy (2024). Dynamic impact of transiting weather systems on coastal currents in the northern Gulf of Mexico, Deep Sea Research Part II: Topical Studies in Oceanography, Volume 216, 2024, 105395, https://doi.org/10.1016/j.dsr2.2024.105395.</div>

opencc-by-4.0Dec 2022View details →

CSI-COP Citizen Scientists App Investigations

This open-access dataset presents project results from CSI-COP project work package 4 task T4.2 in which citizen scientists conducted investigations on apps in their smart devices. The App investigations dataset was created using Excel spreadsheet. Users can explore the information recorded by the citizen scientists by using the filters on the column headings, for example, on type of app (games; news, etc.), or language of app (including English, Greek, Hebrew).

opencc-by-4.0Oct 2023View details →

EU HORIZON2020 CSI-COP Anonymous dataset on Citizen scientists

This dataset complements CSI-COP deliverable report D4.3: 'CSI-COP Citizen Scientists Age, Gender, Socio-Economic and Geographical (AGSEG) Distribution Report'. Researchers can review the dataset and analyse anonymous data on who the citizen scientists were in the EU Horizon2020 funded CSI-COP project with citizen scientists investigating GDPR compliance in websites and apps.

opencc-by-4.0Apr 2022View details →

HYDRO-CSI, Project 1.2: In-stream hydrology. Part 2: instantaneous injections

The continuous exchange of water between surface water and groundwater is a key environmental process controlling the transport and the fate of nutrients, solutes and pollutants in river networks. The dynamics of the near-stream groundwater has a non-negligeable role on controlling flow direction and solutes exchange between the stream water with the adjacent groundwater, however it is rarely considered in solute transport experiments. Despite the amount of individual studies, we are still uncertain about how the physical processes controlling in-stream solutes transport change with different hydrologic conditions and how these processes can be inferred by modelling outcomes. In this project we investigated solute transport in a headwater stream reach via instantaneous (slug) solute injections. The study site is a 55 m long corridor downstream of the Weierbach experimental catchment (see <a href="https://onlinelibrary.wiley.com/doi/full/10.1002/hyp.14140">Hissler et al., 2021)</a>. The stream channel is unvegetated and consists of deposited colluvial material and fragmented schists (up to 50 cm depth) with underlying fractured slate bedrock that sporadically forms the streambed. The average channel slope is 6% and a 50 cm step riffle sits between wells 7W1 and 7W2 (see <a href="https://onlinelibrary.wiley.com/doi/10.1002/hyp.14310">Bonanno et al., 2021</a>). The stream reach is divided in 11 sections that define the nomenclature of the groundwater observation well network (eg. section one is indicated by wells 1W1 and 1W2). The complete list of groundwater measurements has been published in a previous Zenodo dataset and can be found <a href="https://zenodo.org/record/6245818#.YlacmehBxD9">HERE</a>. The tracer chosen for the experiments is chloride. For each experiment, we prepared an NaCl solution using 2 liters of stream water and a fixed mass of reagent-grade NaCl. We injected the solution in a turbulent pool at the beginning of the stream reach (right before section 1) to assure complete mixing in the stream water. Electrical conductivity was measured via portable conductivity meter (Multisonde WTW). Conversion between EC and chloride concentration has been deduced via EC-chloride concentration plots in laboratory where a fixed amount of NaCl solution with known concentration has been progressively added to a sample the stream water collected before the experiment. Every regression equation between EC and chloride concentration plot had a R2>0.998. The dataset includes 30 files of chronologically-numbered instantaneous injections. The instantaneous injections have been conducted from 6-Dec-2018 to 11-June-2021. Every file includes: > A map of the investigated stream reach; > WTW sensor location along the stream reach and their distance from injection point; > The amount of NaCl mass injected in the stream; > Pictures of the stream channel and streamflow; > Notes about presence of leaf packs; > Time and net chloride concentration [mg/l] for each sensor.  All the experiments, data cleaning, sensor calibration, and conversion from EC to Cl- concentration have been conducted by Bonanno Enrico between 2018 and 2021 as part of the Ph.D. project HYDRO-CSI (PRIDE15/10623093). François Barnic, Laurent Gourdol, Jean François Iffly and Jérôme Juilleret calibrated the Multisonde WTW and provided the necessary training. Laurent Pfister and Julian Klaus managed the project and were responsible for the founding acquisition.

opencc-by-4.0Sep 2024View details →

Velocity from the shelf at Station CSI 6 in 2020

<div>Title: Velocity from the shelf at Station CSI 6 in 2020</div> <div> </div> <div>Velocity Data from ADCP deployed at CSI 6 (~ 20 m)</div> <div>Time - days counted from Jan. 1, 2020 (UTC) - Jan. 1 is Day 1.</div> <div>u, v, horizontal velocity in east and north direction in m/s</div> <div>Zmab (bin depth meter above bottom)</div> <div>Invalid data is indicated by a large velocity of -32.768 m/s</div> <div>PI: Chunyan Li at Louisiana State University</div> <div>Project: NSF 1736713 </div> <div>File name: Velocity_from_shelf_CSI6_2020A.dat</div> <div> </div>

opencc-by-4.0Dec 2022View details →

CSI-COP Citizen scientists website investigations

This open-access dataset presents project results from CSI-COP project work package 4 task T4.1 in which citizen scientists conducted investigations on websites across the Internet. The website investigations' dataset was created using Excel spreadsheet. Users can explore the information recorded by the citizen scientists by using the filters on the column headings, for example, on type of website (games; news, etc.), or language of website (including English, Greek, Hebrew).

opencc-by-4.0Sep 2023View details →

WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32

WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32 This repository contains the WiFi CSI human presence detection and activity recognition datasets proposed in [1]. Datasets <ul> <li>DP_LOS - Line-of-sight (LOS) presence detection dataset, comprised of 392 CSI amplitude spectrograms.</li> <li>DP_NLOS - Non-line-of-sight (NLOS) presence detection dataset, comprised of 384 CSI amplitude spectrograms.</li> <li>DA_LOS - LOS activity recognition dataset, comprised of 392 CSI amplitude spectrograms.</li> <li>DA_NLOS - NLOS activity recognition dataset, comprised of 384 CSI amplitude spectrograms.</li> </ul> Table 1: Characteristics of presence detection and activity recognition datasets.  <table> <tbody> <tr> <td>Dataset</td> <td>Scenario</td> <td>#Rooms</td> <td>#Persons</td> <td>#Classes</td> <td>Packet Sending Rate</td> <td>Interval </td> <td>#Spectrograms</td> </tr> <tr> <td>DP_LOS</td> <td>LOS</td> <td>1</td> <td>1</td> <td>6</td> <td>100Hz</td> <td>4s (400 packets)</td> <td>392</td> </tr> <tr> <td>DP_NLOS</td> <td>NLOS</td> <td>5</td> <td>1</td> <td>6</td> <td>100Hz</td> <td>4s (400 packets)</td> <td>384</td> </tr> <tr> <td>DA_LOS</td> <td>LOS</td> <td>1</td> <td>1</td> <td>3</td> <td>100Hz</td> <td>4s (400 packets)</td> <td>392</td> </tr> <tr> <td>DA_NLOS</td> <td>NLOS</td> <td>5</td> <td>1</td> <td>3</td> <td>100Hz</td> <td>4s (400 packets)</td> <td>384</td> </tr> </tbody> </table>   Data Format Each dataset employs an 8:1:1 training-validation-test split, defined in the provided label files trainLabels.csv, validationLabels.csv, and testLabels.csv. Label files use the sample format [i c], with i corresponding to the spectrogram index (i.png) and c corresponding to the class. For presence detection datasets (DP_LOS , DP_NLOS), c in {0 = "no presence", 1 = "presence in room 1", ..., 5 = "presence in room 5"}. For activity recognition datasets (DA_LOS , DA_NLOS), c in {0="no activity", 1="walking", and 2="walking + arm-waving"}. Furthermore, the mean and standard deviation of a given dataset are provided in meanStd.csv. Download and Use This data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to our paper [1]. [1] Strohmayer, Julian, and Martin Kampel. "WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32" International Conference on Computer Vision Systems. Cham: Springer Nature Switzerland, 2023.  BibTeX citation: <pre>@inproceedings{strohmayer2023wifi, title={WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32}, author={Strohmayer, Julian and Kampel, Martin}, booktitle={International Conference on Computer Vision Systems}, pages={41--50}, year={2023}, organization={Springer} }</pre>

opencc-by-4.0Dec 2019View details →

JRSE-CSI-Manning

Data files in support of article in Journal of Renewable and Sustainable Energy, entitled "A novel clear-sky index for color imagery used in short-term irradiance forecasting" by Jeff Manning and Ross Baldick.

opencc-by-4.0Feb 2024View details →

CSI4Free: GAN-Augmented mmWave CSI for Improved Pose Classification

This refers to the gan-generated dataset for the paper" CSI4Free: GAN-Augmented mmWave CSI for Improved Pose Classification. Abstract:In recent years, Joint Communication and Sensing (JC&S), has demonstrated significant success, particularly in utilizing sub-6 GHz frequencies with commercial-off-the-shelf (COTS) Wi-Fi devices for applications such as localization, gesture recognition, and pose classification. Deep learning and the existence of large public datasets has been pivotal in achieving such results. However, at mmWave frequencies (30-300 GHz), which has shown potential for more accurate sensing performance, there is a noticeable lack of research in the domain of COTS Wi-Fi sensing. Challenges such as limited research hardware, the absence of large datasets, limited functionality in COTS hardware, and the complexities of data collection present obstacles to a comprehensive exploration of this field. In this work, we aim to address these challenges by developing a method that can generate synthetic mmWave channel state information (CSI) samples. In particular, we use a generative adversarial network (GAN) on an existing dataset, to generate 30,000 additional CSI samples. The augmented samples exhibit a remarkable degree of consistency with the original data, as indicated by the notably high GAN-train and GAN-test scores. Furthermore, we integrate the augmented samples in training a pose classification model. We observe that the augmented samples complement the real data and improve the generalization of the classification model. The repository is available here: https://github.com/nisarnabeel/Dataset-GAN-Augmented-mmWave-CSI-for-improved-pose-classification   Paper Link:https://ieeexplore.ieee.org/document/10646223/

opencc-by-4.0Sep 2019View details →

Channel State Information (CSI) analysis for predictive maintenance using Convolutional Neural Network (CNN)

Dataset manual: This dataset contains CSI amplitude values for rotating motors in an office environment. Details of the experiments may be found in the corresponding paper published in the DATA'19 workshop, SenSys (<a href="https://doi.org/10.1145/3359427.3361917">https://doi.org/10.1145/3359427.3361917</a>).  Folder structure: The folders for servo motor and stepper motor contains separate folders for network reconnection conditions (w_recc: with reconnections, wo_recc: without recconnections) and load conditions (w_load: with load and wo_load: without load). The data is stores as Matlab files with .mat extentions.  File structure: In each file name, the digits after the '_' at the end of the file name correspond to the speed of the motor. In case of stepper motor these numbers could be directly interpreted as rpm. Ex: table_inj_with_load_5_0.mat corresponds to stationary motor (0 rpm) and table_inj_with_load_5_250.mat corresponds to motor rotating with 250 rpm speed. In the case of servo motor these numbers should be mapped with the following table in order to get the speeds. 0: 0 rpm 50: 14.45 rpm 100: 8.02 rpm 150: 5.38 rpm 200: 4.05 rpm 250: 3.26 rpm 300: 2.67 rpm Ex: table_inj_with_load_50.mat corresponds to motor running with 14.45 rpm. Each file has 3 columns, each corresponding to CSI value, labels (speed/last digits in the file name) and the data sample number (not in sequence as a result of packer loss) respectively. CSI values are typically a matrix of size 3000*180 (3000 CSI samples for 3sec data @1kHz sampling rate and 180 channels for 6 antenna pairs @ 30 subcarrier data per antenna).

opencc-by-4.0Mar 2023View details →

Exposing the CSI - S1

This dataset has been used to study a CSI-based activity-recognition framework in the paper "Exposing the CSI: A Systematic Investigation of CSI-based Wi-Fi Sensing Capabilities and Limitations". The dataset is split into several archives, one for each experiment considered in the paper. A description of all the experiments can be found in the paper, together with a map of the lab reporting the location of all the nodes and target positions.

opencc-by-sa-4.0Mar 2023View details →

Exposing the CSI - S2