research-article

Open access

City-Wide Signal Strength Maps: Prediction with Random Forests

Authors:

Emmanouil Alimpertis,

Athina Markopoulou,

Konstantinos PsounisAuthors Info & Claims

WWW '19: The World Wide Web Conference

Pages 2536 - 2542

https://doi.org/10.1145/3308558.3313726

Published: 13 May 2019 Publication History

All formats PDF

Abstract

Signal strength maps are of great importance to cellular providers for network planning and operation, however they are expensive to obtain and possibly limited or inaccurate in some locations. In this paper, we develop a prediction framework based on random forests to improve signal strength maps from limited measurements. First, we propose a random forests (RFs)-based predictor, with a rich set of features including location as well as time, cell ID, device hardware and other features. We show that our RFs-based predictor can significantly improve the tradeoff between prediction error and number of measurements needed compared to state-of-the-art data-driven predictors, i.e., requiring 80% less measurements for the same prediction accuracy, or reduces the relative error by 17% for the same number of measurements. Second, we leverage two types of real-world LTE RSRP datasets to evaluate into the performance of different prediction methods: (i) a small but dense Campus dataset, collected on a university campus and (ii) several large but sparser NYC and LA datasets, provided by a mobile data analytics company.

References

[1]

A. Shubaa, A. Le, E. Alimpertis, M. Gjoka, A. Markopoulou. 2016. AntMonitor: System and Applications. arXiv:1611.04268 (Nov. 2016).

[2]

E. Alimpertis, N. Fasarakis-Hilliard, and A. Bletsas. 2014. Community RF sensing for source localization. IEEE Wireless Comm. Letters 3, 4 (2014), 393-396.

[3]

E. Alimpertis and A. Markopoulou. 2017. A system for crowdsourcing passive mobile network measurements. In 14th USENIX NSDI'17, Posters Sessions. USENIX Association, Boston, Massachusetts, USA.

[4]

T. Bilen, B. Canberk, and K. R. Chowdhury. 2017. Handover Management in Software-Defined Ultra-Dense 5G Networks. IEEE Network 31, 4 (2017), 49-55.

Digital Library

[5]

L. Breiman. 2001. Random Forests”. Machine Learning 45, 1 (Oct. 2001), 5-32.

Digital Library

[6]

Y. J. Bultitude and T. Rautiainen. 2007. IST-4-027756 WINNER II D1. 1.2 V1. 2 WINNER II Channel Models. Technical Report.

[7]

R. JGB Campello, D. Moulavi, and J. Sander. 2013. Density-based clustering based on hierarchical density estimates. In PAKDD '13. Springer, 160-172.

[8]

A. Chakraborty, Md S. Rahman, H. Gupta, and S. R Das. {n. d.}. SpecSense: Crowdsensing for Efficient Querying of Spectrum Occupancy. In Proc. of the IEEE INFOCOM '17. 1-9.

[9]

B. Cici, E. Alimpertis, A. Ihler, and A. Markopoulou. 2016. Cell-to-cell activity prediction for smart cities. In Proc. of the IEEE INFOCOM WKSHPS '16. IEEE, 903-908.

[10]

H. Deng, C. Peng, A. Fida, J. Meng, and Y C. Hu. 2018. Mobility Support in Cellular Networks: A Measurement Study on Its Configurations and Implications. In Proc. of the ACM IMC '18. ACM, 147-160.

Digital Library

[11]

R. Enami, D. Rajan, and J. Camp. 2018. RAIK: Regional analysis with geodata and crowdsourcing to infer key performance indicators. In Proc. of the IEEE WCNC '18. 1-6.

[12]

ETSI. 2015. LTE, Evolved Universal Terrestrial Radio Access (E-UTRA), Physical layer Measurements (3GPP TS 36.214 version 12.2.0 Release 12). http://www.etsi.org/.

[13]

M. R. Fida, A. Lutu, M. K. Marina, and O. Alay. 2017. ZipWeave: Towards efficient and reliable measurement based mobile coverage maps. In Proc. of the IEEE INFOCOM '17. IEEE.

[14]

A. Gomez-Andrades, R. Barco, P. Munoz, and I. Serrano. 2017. Data analytics for diagnosing the RF condition in self-organizing networks. IEEE Transactions on Mobile Computing 16, 6 (2017), 1587-1600.

Digital Library

[15]

S. He and K. G. Shin. 2018. Steering Crowdsourced Signal Map Construction via Bayesian Compressive Sensing. In Proc. of the IEEE INFOCOM '18. IEEE, 1016-1024.

[16]

A. Imran, A. Zoha, and A. Abu-Dayya. 2014. Challenges in 5G: How to empower SON with big data for enabling 5G. IEEE network 28, 6 (2014), 27-33.

[17]

J. Johansson, W. A Hapsari, Sean Kelley, and G. Bodog. 2012. Minimization of drive tests in 3GPP release 11. IEEE Comm. Magazine 50, 11 (2012).

[18]

Z. Li, A. Nika, X. Zhang, Y. Zhu, Y. Yao, B. Y Zhao, and H. Zheng. 2017. Identifying value in crowdsourced wireless signal measurements. In Proc. of the ACM WWW '17. ACM, 607-616.

Digital Library

[19]

R. Margolies, Richard Becker, S. Byers, S. Deb, R. Jana, S. Urbanek, and C. Volinsky. 2017. Can you find me now? Evaluation of network-based localization in a 4G LTE network. In Proc. of the IEEE INFOCOM '17. 1-9.

[20]

M. Molinari, M R. Fida, M. K Marina, and A. Pescape. 2015. Spatial Interpolation Based Cellular Coverage Prediction with Crowdsourced Measurements. In Proc. of the ACM SIGCOMM Workshop on Crowdsourcing and Crowdsharing of Big Internet Data (C2BID). ACM, 33-38.

Digital Library

[21]

K. P. Murphy. 2012. Machine Learning: A Probabilistic Prespective. The MIT Press, Cambridge, Massachusetts.

Digital Library

[22]

Open Signal Inc.2011. 3G and 4G LTE Cell Coverage Map. http://www.opensignal.com.

[23]

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, Oct. (2011), 2825-2830.

Digital Library

[24]

C. Phillips, M. Ton, D. Sicker, and D. Grunwald. 2012. Practical radio environment mapping with geostatistics. Proc. of the IEEE DYSPAN '12 (Oct. 2012), 422-433.

[25]

T. Rappaport. 2001. Wireless Communications: Principles and Practice (2nd ed.). Prentice Hall PTR, Upper Saddle River, NJ, USA.

Digital Library

[26]

A. Ray, S. Deb, and P. Monogioudis. 2016. Localization of LTE measurement records with missing information. In Proc. of the IEEE INFOCOM '16.

[27]

COST 231 Final Report. 1999. Digital mobile radio towards future generation systems. Technical Report.

[28]

Root Metrics Inc.2018. Metro RootScore Reports. http://www.rootmetrics.com/us.

[29]

Bernard Sklar. 1997. Rayleigh fading channels in mobile digital communication systems. I. Characterization. IEEE Comm. Magazine 35, 7 (1997), 90-100.

Digital Library

[30]

Tutela Inc.2011. Crowdsourced mobile data. http://www.tutela.com.

[31]

J. Yang, A. Varshavsky, H. Liu, Y. Chen, and M. Gruteser. 2010. Accuracy characterization of cell tower localization. In Proc. of the ACM UbiComp '10. ACM, 223-226.

Digital Library

[32]

Z. Yun and M. F. Iskander. 2015. Ray tracing for radio propagation modeling: Principles and applications. IEEE Access 3(2015), 1089-1100.

Cited By

Barbosa BCruz HMacedo ACardoso CFernandes FEras LAraújo JCalvacante GBarros F(2024)Application of Artificial Neural Networks for Prediction of Received Signal Strength Indication and Signal-to-Noise Ratio in Amazonian Wooded EnvironmentsSensors10.3390/s2408254224:8(2542)Online publication date: 16-Apr-2024
https://doi.org/10.3390/s24082542
Ye WHu XSleder SZhang ADayalan UHassan AFezeu RJajoo ALee MRamadan EQian FZhang ZSekar VYu MSeneviratne AVeitch D(2024)Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and PredictionProceedings of the ACM SIGCOMM 2024 Conference10.1145/3651890.3672250(340-357)Online publication date: 4-Aug-2024
https://dl.acm.org/doi/10.1145/3651890.3672250
Yang GWen PLiu YKong LLiu Y(2024)Spatial-Temporal Data Inference With Graph Attention Neural Networks in Sparse Mobile CrowdsensingIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.341839311:5(4617-4626)Online publication date: Sep-2024
https://doi.org/10.1109/TNSE.2024.3418393
Show More Cited By

Recommendations

Regression conformal prediction with random forests

Regression conformal prediction produces prediction intervals that are valid, i.e., the probability of excluding the correct target value is bounded by a predefined confidence level. The most important criterion when comparing conformal regressors is ...
Efficient Venn predictors using random forests

Successful use of probabilistic classification requires well-calibrated probability estimates, i.e., the predicted class probabilities must correspond to the true probabilities. In addition, a probabilistic classifier must, of course, also be as ...
On the asymptotics of random forests

The last decade has witnessed a growing interest in random forest models which are recognized to exhibit good practical performance, especially in high-dimensional settings. On the theoretical side, however, their predictive power remains largely ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

WWW '19: The World Wide Web Conference

May 2019

3620 pages

ISBN:9781450366748

DOI:10.1145/3308558

Editors:
Ling Liu
Georgia Tech, USA
,
Ryen White
Microsoft Research, USA

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

IW3C2: International World Wide Web Conference Committee

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 May 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '19

WWW '19: The Web Conference

May 13 - 17, 2019

CA, San Francisco, USA

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

36
Total Citations
View Citations
2,053
Total Downloads

Downloads (Last 12 months)562
Downloads (Last 6 weeks)58

Reflects downloads up to 11 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Barbosa BCruz HMacedo ACardoso CFernandes FEras LAraújo JCalvacante GBarros F(2024)Application of Artificial Neural Networks for Prediction of Received Signal Strength Indication and Signal-to-Noise Ratio in Amazonian Wooded EnvironmentsSensors10.3390/s2408254224:8(2542)Online publication date: 16-Apr-2024
https://doi.org/10.3390/s24082542
Ye WHu XSleder SZhang ADayalan UHassan AFezeu RJajoo ALee MRamadan EQian FZhang ZSekar VYu MSeneviratne AVeitch D(2024)Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and PredictionProceedings of the ACM SIGCOMM 2024 Conference10.1145/3651890.3672250(340-357)Online publication date: 4-Aug-2024
https://dl.acm.org/doi/10.1145/3651890.3672250
Yang GWen PLiu YKong LLiu Y(2024)Spatial-Temporal Data Inference With Graph Attention Neural Networks in Sparse Mobile CrowdsensingIEEE Transactions on Network Science and Engineering10.1109/TNSE.2024.341839311:5(4617-4626)Online publication date: Sep-2024
https://doi.org/10.1109/TNSE.2024.3418393
Bakopoulou EYang MZhang JPsounis KMarkopoulou A(2024)Location Leakage in Federated Signal MapsIEEE Transactions on Mobile Computing10.1109/TMC.2023.333203423:6(6936-6953)Online publication date: Jun-2024
https://doi.org/10.1109/TMC.2023.3332034
Alimpertis EMarkopoulou AButts CBakopoulou EPsounis K(2024)A Unified Prediction Framework for Signal Maps: Not All Measurements are Created EqualIEEE Transactions on Mobile Computing10.1109/TMC.2022.322177323:1(70-89)Online publication date: Jan-2024
https://doi.org/10.1109/TMC.2022.3221773
Vasudevan MYuksel M(2024)Machine Learning for Radio Propagation Modeling: A Comprehensive SurveyIEEE Open Journal of the Communications Society10.1109/OJCOMS.2024.34464575(5123-5153)Online publication date: 2024
https://doi.org/10.1109/OJCOMS.2024.3446457
Luo-Chen HKhatib ESethi DCruz EArostegui AMartín RMoreno R(2024)Scenario-Agnostic Localization System for Cellular Network Based on Feature EngineeringIEEE Open Journal of the Communications Society10.1109/OJCOMS.2024.34401865(4999-5012)Online publication date: 2024
https://doi.org/10.1109/OJCOMS.2024.3440186
Liu CZhu KTao CChen BZhao Y(2024)UAV-Assisted Active Sparse Crowdsensing for Ground Signal Map Construction Based on 3-D Spatial–Temporal CorrelationIEEE Internet of Things Journal10.1109/JIOT.2024.339940911:16(27260-27274)Online publication date: 15-Aug-2024
https://doi.org/10.1109/JIOT.2024.3399409
Shibli AZanouda T(2024)Data-Driven Radio Environment Map Estimation Using Graph Neural Networks2024 IEEE International Conference on Communications Workshops (ICC Workshops)10.1109/ICCWorkshops59551.2024.10615637(650-655)Online publication date: 9-Jun-2024
https://doi.org/10.1109/ICCWorkshops59551.2024.10615637
Li YLi ZGao ZChen T(2024)Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases2024 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)10.1109/DySPAN60163.2024.10632773(277-285)Online publication date: 13-May-2024
https://doi.org/10.1109/DySPAN60163.2024.10632773
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents