Identifying Value in Crowdsourced Wireless Signal Measurements

While crowdsourcing is an attractive approach to collect large-scale wireless measurements, understanding the quality and variance of the resulting data is difficult. Our work analyzes the quality of crowdsourced cellular signal measurements in the context of basestation localization, using large international public datasets (419M signal measurements and 1M cells) and corresponding ground truth values. Performing localization using raw received signal strength (RSS) data produces poor results and very high variance. Applying supervised learning improves results moderately, but variance remains high. Instead, we propose feature clustering, a novel application of unsupervised learning to detect hidden correlation between measurement instances, their features, and localization accuracy. Our results identify RSS standard deviation and RSS-weighted dispersion mean as key features that correlate with highly predictive measurement samples for both sparse and dense measurements respectively. Finally, we show how optimizing crowdsourcing measurements for these two features dramatically improves localization accuracy and reduces variance.

[1]  John Krumm,et al.  Accuracy characterization for metropolitan-scale Wi-Fi localization , 2005, MobiSys '05.

[2]  Guobin Shen,et al.  Walkie-Markie: Indoor Pathway Mapping Made Easy , 2013, NSDI.

[3]  Xiaoli Li,et al.  Eliminating noisy information in Web pages for data mining , 2003, KDD '03.

[4]  References , 1971 .

[5]  Aditya Akella,et al.  Obtaining in-context measurements of cellular network performance , 2012, IMC '12.

[6]  Haiyun Luo,et al.  Zero-Configuration, Robust Indoor Localization: Theory and Experimentation , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[7]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[8]  Shashi Shekhar,et al.  Spatial Databases: A Tour , 2003 .

[9]  Mike Y. Chen,et al.  Practical Metropolitan-Scale Positioning for GSM Phones , 2006, UbiComp.

[10]  Johan Alexander Nordstrand Rusvik Localizing Cell Towers from Crowdsourced Measurements , 2015 .

[11]  Vincent Lenders,et al.  A software-defined sensor architecture for large-scale wideband spectrum monitoring , 2015, IPSN.

[12]  P. Widhalm,et al.  Characterization of mobile phone localization errors with OpenCellID data , 2015, 2015 4th International Conference on Advanced Logistics and Transport (ICALT).

[13]  Bhaskar Krishnamachari,et al.  Ecolocation: a sequence based technique for RF localization in wireless sensor networks , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

[14]  M. Marina,et al.  Impact of Indoor-Outdoor Context on Crowdsourcing based Mobile Coverage Analysis , 2015, AllThingsCellular@SIGCOMM.

[15]  Jie Gao,et al.  Drive-By Localization of Roadside WiFi Networks , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[16]  N. Megiddo Linear-time algorithms for linear programming in R3 and related problems , 1982, FOCS 1982.

[17]  Eyal de Lara,et al.  Calibree: Calibration-Free Localization Using Relative Distance Estimations , 2009, Pervasive.

[18]  David Kotz,et al.  Risks of Using AP Locations Discovered Through War Driving , 2006, Pervasive.

[19]  Anshul Rai,et al.  Zee: zero-effort crowdsourcing for indoor localization , 2012, Mobicom '12.

[20]  Jie Yang,et al.  Accuracy characterization of cell tower localization , 2010, UbiComp.

[21]  Axel Küpper,et al.  Estimating locations and coverage areas of mobile network cells based on crowdsourced data , 2013, 6th Joint IFIP Wireless and Mobile Networking Conference (WMNC).

[22]  David R. Cox,et al.  The statistical analysis of series of events , 1966 .

[23]  Venkata N. Padmanabhan,et al.  Indoor localization without the pain , 2010, MobiCom.

[24]  Massimiliano Molinari,et al.  Spatial Interpolation based Cellular Coverage Prediction with Crowdsourced Measurements , 2015, C2BD@SIGCOMM.

[25]  H. Chernoff,et al.  The Use of Maximum Likelihood Estimates in {\chi^2} Tests for Goodness of Fit , 1954 .

[26]  S. C. Johnson Hierarchical clustering schemes , 1967, Psychometrika.

[27]  Emmanuel J. Candès,et al.  A Geometric Analysis of Subspace Clustering with Outliers , 2011, ArXiv.

[28]  Laura Littman,et al.  New Times, New Methods: Upgrading Spectrum Enforcement , 2014 .

[29]  Jing Gao,et al.  Truth Discovery on Crowd Sensing of Correlated Entities , 2015, SenSys.

[30]  Srinivasan Seshan,et al.  Access Point Localization Using Local Signal Strength Gradient , 2009, PAM.

[31]  Vipin Kumar,et al.  A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs , 1998, SIAM J. Sci. Comput..

[32]  Suman Banerjee,et al.  Can they hear me now?: a case for a client-assisted approach to monitoring wide-area wireless networks , 2011, IMC '11.

[33]  Nimrod Megiddo,et al.  Linear-time algorithms for linear programming in R3 and related problems , 1982, 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982).

[34]  Sourav Bhattacharya,et al.  A grid-based algorithm for on-device GSM positioning , 2010, UbiComp.

[35]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[36]  Nimrod Megiddo,et al.  Linear-Time Algorithms for Linear Programming in R^3 and Related Problems , 1982, FOCS.

[37]  Hui Xiong,et al.  Enhancing data analysis with noise removal , 2006, IEEE Transactions on Knowledge and Data Engineering.

[38]  R. S. Yuill The Standard Deviational Ellipse; An Updated Tool for Spatial Description , 1971 .

[39]  Guobin Shen,et al.  Experiencing and handling the diversity in data density and environmental locality in an indoor positioning service , 2014, MobiCom.

[40]  Andreas Achtzehn,et al.  CrowdREM: Harnessing the Power of the Mobile Crowd for Flexible Wireless Network Monitoring , 2015, HotMobile.

[41]  D. Griffith Spatial Autocorrelation and Spatial Filtering: Gaining Understanding Through Theory and Scientific Visualization , 2010 .

[42]  Yunhao Liu,et al.  Locating in fingerprint space: wireless indoor localization with little human intervention , 2012, Mobicom '12.