pith. machine review for the scientific record. sign in

arxiv: 2604.20349 · v1 · submitted 2026-04-22 · 📡 eess.SP

Recognition: unknown

Descriptor: A Hybrid Indoor and Indoor-Outdoor Positioning Multi-Technology Dataset (HYMN)

Muhammad Ammad , Albrecht Michler , Paul Schwarzbach , Jonas Ninnemann , Hagen U{\ss}ler , Oliver Michler
Authors on Pith no claims yet

Pith reviewed 2026-05-10 00:19 UTC · model grok-4.3

classification 📡 eess.SP
keywords multi-technology datasetindoor-outdoor positioningsensor fusionlocalizationUWBBLEWiFiGNSS
0
0 comments X

The pith

The HYMN dataset supplies time-synchronized measurements from five positioning technologies across indoor-outdoor transitions for localization research.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper presents the HYMN dataset, which gathers data from Ultra-Wideband, Bluetooth Low Energy, WiFi, 5G, and GNSS systems in an industrial hall setting that includes transitions between indoor and outdoor areas. The measurements are time-stamped, each tagged with a unique identifier, and paired with ground truth position information. The dataset is structured to let researchers combine signals from these different systems to maintain continuous location estimates even when moving through environments where individual technologies encounter limitations. It supports tasks such as multi-sensor fingerprinting and cross-technology fusion by showing how heterogeneous signals can complement one another.

Core claim

HYMN is a multi-system and time-synchronized dataset for localization research based on opportunistic signals collected in an indoor-outdoor scenario. It comprises measurement data from five positioning systems including Ultra-Wideband, Bluetooth Low Energy, WiFi, 5G, and GNSS. Each instance carries a unique measurement identifier along with time-stamped observations for the respective systems and the corresponding ground truth information. The dataset enables multi-sensor fingerprinting, cross-technology fusion, and seamless indoor-outdoor positioning by allowing study of how the signals complement each other to overcome limitations such as GNSS degradation indoors or terrestrial systemvari

What carries the argument

The HYMN multi-technology dataset, a collection of time-synchronized measurements from five positioning systems with explicit indoor-outdoor transition coverage and ground truth.

If this is right

  • Multi-sensor fusion methods can examine how GNSS and terrestrial systems complement each other in covered areas.
  • Cross-technology fusion algorithms can be developed and tested directly on the provided synchronized observations.
  • Seamless indoor-outdoor positioning techniques become testable with explicit transition data included.
  • Fingerprinting approaches can exploit the combined observations from all five systems.
  • Researchers can address signal variability in dynamic environments by using the heterogeneous data together.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The dataset could support development of navigation systems that automatically blend or switch among technologies based on current signal conditions.
  • Similar multi-technology collections in urban or vehicular settings might extend the same complementarity approach to other mixed environments.
  • The focus on synchronization points to timing precision as a key requirement for any practical multi-sensor fusion implementation.
  • Adding further technologies or repeated collections over time could increase the dataset's value for long-term robustness studies.

Load-bearing premise

The measurements collected from the different technologies are accurately time-synchronized and the supplied ground truth positions are sufficiently precise for multi-system fusion research.

What would settle it

Independent re-collection of the same scenario that reveals consistent timing offsets between the five systems or ground truth errors exceeding typical positioning accuracy would demonstrate that the dataset cannot reliably support fusion tasks.

Figures

Figures reproduced from arXiv: 2604.20349 by Albrecht Michler, Hagen U{\ss}ler, Jonas Ninnemann, Muhammad Ammad, Oliver Michler, Paul Schwarzbach.

Figure 1
Figure 1. Figure 1: FIG. 1 [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIG. 3 [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIG. 4 [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: FIG. 5 [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: FIG. 6 [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
read the original abstract

This article introduces the HYMN (HYbrid Multi-technology Navigation) dataset: a multi-system, and time synchronized dataset for localization research based on opportunistic signals collected in an indoor-outdoor scenario. HYMN comprises measurement data collected in an industrial hall setting for five different positioning systems including Ultra-Wideband (UWB), Bluetooth Low Energy (BLE), WiFi, 5G, and Global Navigation Satellite System (GNSS). Unlike existing datasets that focus on single technologies or purely indoor/outdoor scenarios, HYMN combines five positioning technologies with explicit coverage of indoor-outdoor transitions, enabling multi-sensor fusion research for seamless localization. Each instance of data is identified through a unique measurement id and it represents time-stamped observations relevant for each system respectively along with the ground truth information. HYMN is designed to support a wide range of localization tasks including multi-sensor fingerprinting, cross-technology fusion, and seamless indoor-outdoor positioning. The synchronized measurements from GNSS and other terrestrial systems enable researchers to investigate how heterogeneous signals complement each other to overcome individual technology limitations such as GNSS degradation in covered areas or terrestrial system variability in dynamic environments.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The paper introduces the HYMN dataset, a multi-technology collection of time-stamped measurements from UWB, BLE, WiFi, 5G, and GNSS collected in an industrial hall with explicit indoor-outdoor transitions, together with ground-truth information, to support multi-sensor fusion, fingerprinting, and seamless indoor-outdoor positioning research.

Significance. If the synchronization and ground-truth accuracy claims hold, the dataset would address a clear gap by supplying heterogeneous signals under realistic transition conditions, enabling reproducible cross-technology fusion studies that single-technology or purely indoor/outdoor datasets cannot support.

major comments (2)
  1. [Abstract] Abstract: the statement that the dataset supplies 'time-stamped observations ... along with the ground truth information' and is 'time synchronized' is not accompanied by any description of the synchronization mechanism (common clock, NTP/PTP, hardware trigger, or post-hoc alignment) or the ground-truth sensor and its reported accuracy. These omissions are load-bearing for the central claim of utility in multi-sensor fusion and seamless localization.
  2. [Abstract] Abstract: no information is given on data-collection procedures, receiver configurations, sampling rates, or quality-control steps (e.g., outlier rejection, multipath mitigation during GNSS outages). Without these, it is impossible to assess whether the measurements are suitable for the advertised research tasks.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. The comments highlight important aspects of clarity in the abstract that we will address through targeted revisions while preserving the paper's focus on the dataset itself.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the statement that the dataset supplies 'time-stamped observations ... along with the ground truth information' and is 'time synchronized' is not accompanied by any description of the synchronization mechanism (common clock, NTP/PTP, hardware trigger, or post-hoc alignment) or the ground-truth sensor and its reported accuracy. These omissions are load-bearing for the central claim of utility in multi-sensor fusion and seamless localization.

    Authors: We agree that the abstract would benefit from a brief reference to the synchronization mechanism and ground-truth accuracy to better support the central claims. The full manuscript describes these in the Data Collection and Ground Truth sections. We will revise the abstract to add a concise clause summarizing the approach and accuracy, with a pointer to the relevant sections for full details. revision: yes

  2. Referee: [Abstract] Abstract: no information is given on data-collection procedures, receiver configurations, sampling rates, or quality-control steps (e.g., outlier rejection, multipath mitigation during GNSS outages). Without these, it is impossible to assess whether the measurements are suitable for the advertised research tasks.

    Authors: We acknowledge that the abstract, due to length constraints, does not include these operational details. The full manuscript provides them in the dedicated Data Acquisition section. We will revise the abstract to include a short statement referencing the methods for collection procedures, configurations, sampling rates, and quality controls, enabling readers to locate the information needed to evaluate suitability for the intended research tasks. revision: yes

Circularity Check

0 steps flagged

No circularity: dataset descriptor with no derivation chain

full rationale

The paper introduces and describes a multi-technology positioning dataset (HYMN) collected in an industrial hall with indoor-outdoor transitions. It contains no equations, no predictions, no fitted parameters, no uniqueness theorems, and no self-citations that bear load on any claimed derivation. All statements are descriptive of the data collection process and intended uses; the central claim (availability of time-stamped multi-system observations plus ground truth) is not derived from prior results within the paper and does not reduce to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a dataset introduction paper rather than a mathematical or theoretical work. No free parameters, axioms, or invented entities are invoked.

pith-pipeline@v0.9.0 · 5520 in / 997 out tokens · 34287 ms · 2026-05-10T00:19:51.684090+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Bridging the Indoor-Outdoor Gap: Cross-Technology Ranging for Seamless Robot Navigation

    eess.SP 2026-04 unverdicted novelty 7.0

    The HYMN dataset reveals that GNSS, UWB, WiFi FTM, and BLE ranging technologies are complementary, with their performance weaknesses overlapping at indoor-outdoor transitions, based on synchronized measurements agains...

Reference graph

Works this paper leans on

37 extracted references · 21 canonical work pages · cited by 1 Pith paper

  1. [1]

    A fast indoor/outdoor transition detection algorithm based on machine learning,

    Y . Zhu, H. Luo, Q. Wang, F. Zhao, B. Ning, Q. Ke, and C. Zhang, “A fast indoor/outdoor transition detection algorithm based on machine learning,”Sensors, vol. 19, no. 4, p. 786, Feb. 2019. [Online]. Available: http://dx.doi.org/10.3390/s19040786

    work page doi:10.3390/s19040786 2019

  2. [2]

    Automatic generation of routing graphs for indoor-outdoor transitional space to support seamless navigation,

    Z. Wang, S. Zlatanova, M. A. Mostafavi, K. Khoshelham, L. D ´ıaz-Vilari˜no, and K.-J. Li, “Automatic generation of routing graphs for indoor-outdoor transitional space to support seamless navigation,”ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. X- 1/W1-2023, p. 487–492, Dec. 2023. [Online]. Available: http://dx...

    work page doi:10.5194/isprs-annals-x-1-w1-2023-487-2023 2023

  3. [3]

    Gvins: Tightly coupled gnss–visual–inertial fusion for smooth and consistent state estimation,

    S. Cao, X. Lu, and S. Shen, “Gvins: Tightly coupled gnss–visual–inertial fusion for smooth and consistent state estimation,” IEEE Transactions on Robotics, vol. 38, no. 4, p. 2004–2021, Aug

    2004

  4. [4]

    Available: http://dx.doi.org/10.1109/tro.2021.3133730

    [Online]. Available: http://dx.doi.org/10.1109/tro.2021.3133730

    work page doi:10.1109/tro.2021.3133730 2021

  5. [5]

    Multipath/nlos detection based on k-means clustering for gnss/ins tightly coupled system in urban areas,

    H. Wang, S. Pan, W. Gao, Y . Xia, and C. Ma, “Multipath/nlos detection based on k-means clustering for gnss/ins tightly coupled system in urban areas,”Micromachines, vol. 13, no. 7, p. 1128, Jul

  6. [6]

    Available: http://dx.doi.org/10.3390/mi13071128

    [Online]. Available: http://dx.doi.org/10.3390/mi13071128

    work page doi:10.3390/mi13071128

  7. [7]

    On indoor localization using wifi, ble, uwb, and imu technologies,

    S. G. Leitch, Q. Z. Ahmed, W. B. Abbas, M. Hafeez, P. I. Laziridis, P. Sureephong, and T. Alade, “On indoor localization using wifi, ble, uwb, and imu technologies,”Sensors, vol. 23, no. 20, p. 8598, Oct

  8. [8]

    Available: http://dx.doi.org/10.3390/s23208598

    [Online]. Available: http://dx.doi.org/10.3390/s23208598

    work page doi:10.3390/s23208598

  9. [9]

    Indoor positioning algorithm based on the improved rssi distance model,

    G. Li, E. Geng, Z. Ye, Y . Xu, J. Lin, and Y . Pang, “Indoor positioning algorithm based on the improved rssi distance model,” Sensors, vol. 18, no. 9, p. 2820, Aug. 2018. [Online]. Available: http://dx.doi.org/10.3390/s18092820

    work page doi:10.3390/s18092820 2018

  10. [10]

    Integrity monitoring for positioning of intelligent transport systems using integrated rtk-gnss, imu and vehicle odometer,

    A. El-Mowafy and N. Kubo, “Integrity monitoring for positioning of intelligent transport systems using integrated rtk-gnss, imu and vehicle odometer,”IET Intelligent Transport Systems, vol. 12, no. 8, p. 901–908, Jul. 2018. [Online]. Available: http://dx.doi.org/10.1049/ iet-its.2018.0106

    work page arXiv 2018

  11. [11]

    Improved multi-sensor fusion positioning system based on gnss/lidar/vision/imu with semi-tight coupling and graph optimization in gnss challenging environments,

    J. Zhu, H. Zhou, Z. Wang, and S. Yang, “Improved multi-sensor fusion positioning system based on gnss/lidar/vision/imu with semi-tight coupling and graph optimization in gnss challenging environments,” IEEE Access, vol. 11, p. 95711–95723, 2023. [Online]. Available: http://dx.doi.org/10.1109/access.2023.3311359

    work page doi:10.1109/access.2023.3311359 2023

  12. [12]

    Ordip: Principle, practice and guidelines for open research data in indoor positioning,

    G. G. Anagnostopoulos, P. Barsocchi, A. Crivello, C. Pend ˜ao, I. Silva, and J. Torres-Sospedra, “Ordip: Principle, practice and guidelines for open research data in indoor positioning,”Internet of Things, vol. 30, p. 101485, 2025. [Online]. Available: https: //www.sciencedirect.com/science/article/pii/S2542660524004268

    2025

  13. [13]

    Deep learning based wireless localization for indoor navigation,

    R. Ayyalasomayajula, A. Arun, C. Wu, S. Sharma, A. R. Sethi, D. Vasisht, and D. Bharadia, “Deep learning based wireless localization for indoor navigation,” inProceedings of the 26th Annual International Conference on Mobile Computing and Networking, ser. MobiCom ’20. ACM, Apr. 2020, p. 1–14. [Online]. Available: http://dx.doi.org/10.1145/3372224.3380894

    work page doi:10.1145/3372224.3380894 2020

  14. [14]

    Deep-learning source localization using multi-frequency magnitude- only data,

    H. Niu, Z. Gong, E. Ozanich, P. Gerstoft, H. Wang, and Z. Li, “Deep-learning source localization using multi-frequency magnitude- only data,”The Journal of the Acoustical Society of America, vol. 146, no. 1, p. 211–222, Jul. 2019. [Online]. Available: http://dx.doi.org/10.1121/1.5116016

    work page doi:10.1121/1.5116016 2019

  15. [15]

    Fundamental limits of rss fingerprinting based indoor localization,

    Y . Wen, X. Tian, X. Wang, and S. Lu, “Fundamental limits of rss fingerprinting based indoor localization,” in2015 IEEE Conference on Computer Communications (INFOCOM). IEEE, Apr. 2015. [Online]. Available: http://dx.doi.org/10.1109/infocom.2015.7218637

    work page doi:10.1109/infocom.2015.7218637 2015

  16. [16]

    Comparative study of indoor positioning datasets focusing on localization accuracy success rate and floor classification,

    A. Ayub, Z. Z. Abidin, A. Alhammadi, N. F. Soliman, M. A. Khan, and A. D. Algarni, “Comparative study of indoor positioning datasets focusing on localization accuracy success rate and floor classification,”Scientific Reports, vol. 15, no. 1, Oct. 2025. [Online]. Available: http://dx.doi.org/10.1038/s41598-025-17692-w

    work page doi:10.1038/s41598-025-17692-w 2025

  17. [17]

    Ujiindoorloc,

    R. M. Joaqun Torres-Sospedra, “Ujiindoorloc,” 2014. [Online]. Available: https://archive.ics.uci.edu/dataset/310

    2014

  18. [18]

    Crowdsourced wifi database and benchmark software for indoor positioning,

    E. S. Lohan, J. Torres-Sospedra, P. Richter, H. Lepp ¨akoski, J. Huerta, and A. Cramariuc, “Crowdsourced wifi database and benchmark software for indoor positioning,” 2017. [Online]. Available: https://zenodo.org/record/889798

    2017

  19. [19]

    Wifi rss measurements in tampere university multi-building campus, 2017,

    E. S. Lohan, J. Torres-Sospedra, and A. Gonzalez, “Wifi rss measurements in tampere university multi-building campus, 2017,”

    2017

  20. [20]

    Available: https://zenodo.org/record/5174851

    [Online]. Available: https://zenodo.org/record/5174851

    work page arXiv

  21. [21]

    Datasets of indoor uwb measurements for ranging and positioning in good and challenging scenarios,

    A. Moragrega, “Datasets of indoor uwb measurements for ranging and positioning in good and challenging scenarios,” 2021. [Online]. Available: https://zenodo.org/record/5095373

    work page arXiv 2021

  22. [22]

    Long-term wi-fi fingerprinting dataset and supporting material,

    G. M. Mendoza-Silva, P. Richter, J. Torres-Sospedra, E. S. Lohan, and J. Huerta, “Long-term wi-fi fingerprinting dataset and supporting material,” 2020. [Online]. Available: https://zenodo.org/ record/3748719

    work page arXiv 2020

  23. [23]

    Mohammadi

    M. Mohammadi. (2018) Ble rssi dataset for indoor localization and navigation. Kaggle. Accessed: Nov. 27, 2025. [Online]. Available: https://www.kaggle.com/datasets/mehdimka/ble-rssi-dataset

    2018

  24. [24]

    Hong kong urbannav: An open-source multisensory dataset for benchmarking urban navigation algorithms,

    L.-T. Hsu, F. Huang, H.-F. Ng, G. Zhang, Y . Zhong, X. Bai, and W. Wen, “Hong kong urbannav: An open-source multisensory dataset for benchmarking urban navigation algorithms,”NAVIGATION: Journal of the Institute of Navigation, vol. 70, no. 4, 2023. [Online]. Available: https://navi.ion.org/content/70/4/navi.602

    2023

  25. [25]

    Android raw gnss measurement datasets for precise positioning,

    G. M. Fu, M. Khider, and F. van Diggelen, “Android raw gnss measurement datasets for precise positioning,” inProceedings of the 33rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2020), ser. GNSS

    2020

  26. [26]

    Institute of Navigation, Oct. 2020. [Online]. Available: http://dx.doi.org/10.33012/2020.17628

    work page doi:10.33012/2020.17628 2020

  27. [27]

    A multi-modal dataset for hybrid indoor positioning using wi-fi rss, embedded inertial sensors, and cctv images,

    B. A. Abdalla, H. S. Maghdid, and A. T. Sabir, “A multi-modal dataset for hybrid indoor positioning using wi-fi rss, embedded inertial sensors, and cctv images,”Data in Brief, vol. 64, p. 112370, Feb

  28. [28]

    Available: http://dx.doi.org/10.1016/j.dib.2025.112370

    [Online]. Available: http://dx.doi.org/10.1016/j.dib.2025.112370

    work page doi:10.1016/j.dib.2025.112370 2025

  29. [29]

    M. GmbH. Metirionic-DMK-215. [Online]. Avail- able: https://metirionic.com/wp-content/uploads/2022/08/ E-Metirionic-DMK-215.pdf

    2022

  30. [30]

    H. P. Enterprise. HPE Aruba Networking 630 Series Campus Access Points. PSNow. [Online]. Available: https://www.hpe.com/psnow/doc/ a00114648enw

  31. [31]

    L. G. AG. Leica ts16 totalstation – einfach vermessen. [Online]. Available: https://leica-geosystems.com/de-de/products/total-stations/ robotic-total-stations/leica-ts16

  32. [32]

    An empirical assessment of indoor-outdoor localization based on signals of opportunity from multiple systems,

    A. Michler, P. Schwarzbach, J. Ninnemann, M. Ammad, and O. Michler, “An empirical assessment of indoor-outdoor localization based on signals of opportunity from multiple systems,” in 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS). IEEE, Apr. 2025, p. 948–959. [Online]. Available: http://dx.doi.org/10.1109/PLANS61210.2025.11028349

    work page doi:10.1109/plans61210.2025.11028349 2025

  33. [33]

    (2021) Google Earth Pro

    Google. (2021) Google Earth Pro. Imagery date: Sept. 9, 2021. Coordinates: 51°34’10.18” N 13°50’07.02” E. Accessed: Dec. 18,

    2021

  34. [34]

    Available: https://www.google.com/earth/

    [Online]. Available: https://www.google.com/earth/

  35. [35]

    gnss lib py: Analyzing gnss data with python,

    D. Knowles, A. V . Kanhere, D. Neamati, and G. Gao, “gnss lib py: Analyzing gnss data with python,”SoftwareX, vol. 27, p. 101811, Sep. 2024. [Online]. Available: http://dx.doi.org/10.1016/j.softx.2024. 101811

    work page doi:10.1016/j.softx.2024 2024

  36. [36]

    Enhanced EKF-based time calibration for GNSS/UWB tight integration,

    Y . Guo, O. V ouch, S. Zocca, A. Minetto, and F. Dovis, “Enhanced EKF-based time calibration for GNSS/UWB tight integration,”IEEE Sensors Journal, vol. 23, no. 1, pp. 552–566, Jan. 2023. [Online]. Available: https://doi.org/10.1109/jsen.2022.3223974

    work page doi:10.1109/jsen.2022.3223974 2023

  37. [37]

    Tud-itvs/hymn-dataset,

    A. Michler, M. Ammad, P. Schwarzbach, J. Ninnemann, and H. Ußler, “Tud-itvs/hymn-dataset,” 2025. [Online]. Available: https: //zenodo.org/doi/10.5281/zenodo.17979434 9 Preprint – April 23, 2026

    work page doi:10.5281/zenodo.17979434 2025