No Perfect Outdoors: Towards A Deep Profiling of GNSS-based Location Contexts

While both outdoor and indoor localization methods are flourishing, how to properly marry them to offer pervasive localizability in urban areas remains open. Recently proposals on indoor-outdoor detection make the first step towards such an integration, yet complicated urban environments render such a binary classification incompetent. In this paper, we intend to fully explore raw GNSS measurements in order to better characterize the diversified urban environments. Essentially, we tackle the challenges introduced by the complex GNSS data and apply a deep learning model to identify representations for respective location contexts. We further develop two preliminary applications of our deep profiling. On one hand, we offer a more fine-grained semantic classification than binary indoor-outdoor detection. On the other hand, we derive a GPS error indicator more meaningful than that provided by Google Maps. These results are all corroborated by our extensive data collection and trace-driven evaluations.

[1]  Mahesh K. Marina,et al.  A semi-supervised learning approach for robust indoor-outdoor detection with smartphones , 2014, SenSys.

[2]  J LaMance,et al.  ASSISTED GPS : A LOW-INFRASTRUCTURE APPROACH , 2002 .

[3]  Chi Zhang,et al.  Pulsar: Towards Ubiquitous Visible Light Localization , 2017, MobiCom.

[4]  Evangelos Kalogerakis,et al.  RisQ: recognizing smoking gestures with inertial sensors on a wristband , 2014, MobiSys.

[5]  Jie Xiong,et al.  ArrayTrack: A Fine-Grained Indoor Location System , 2011, NSDI.

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

[7]  Jie Liu,et al.  COIN-GPS: indoor localization from direct GPS receiving , 2014, MobiSys.

[8]  Paramvir Bahl,et al.  RADAR: an in-building RF-based user location and tracking system , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[9]  Christos Faloutsos,et al.  AutoPlait: automatic mining of co-evolving time sequences , 2014, SIGMOD Conference.

[10]  Joongheon Kim,et al.  Energy-efficient rate-adaptive GPS-based positioning for smartphones , 2010, MobiSys '10.

[11]  Hari Balakrishnan,et al.  Accurate, Low-Energy Trajectory Mapping for Mobile Devices , 2011, NSDI.

[12]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[13]  Qiang Wang,et al.  Energy efficient GPS sensing with cloud offloading , 2012, SenSys '12.

[14]  Will Hedgecock,et al.  Accurate real-time relative localization using single-frequency GPS , 2014, SenSys.

[15]  Feng Zhao,et al.  Energy-accuracy trade-off for continuous mobile device location , 2010, MobiSys '10.

[16]  Jun Luo,et al.  WOLoc: WiFi-only outdoor localization using crowdsensed hotspot labels , 2017, IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.

[17]  Guang Tan,et al.  SatProbe: Low-energy and fast indoor/outdoor detection based on raw GPS processing , 2017, IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.

[18]  Mo Li,et al.  IODetector: a generic service for indoor outdoor detection , 2012, SenSys '12.

[19]  Moustafa Youssef,et al.  The Horus WLAN location determination system , 2005, MobiSys '05.

[20]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[21]  Yunhao Liu,et al.  Lasagna: towards deep hierarchical understanding and searching over mobile sensing data , 2016, MobiCom.

[22]  Prabal Dutta,et al.  Luxapose: indoor positioning with mobile phones and visible light , 2014, MobiCom.

[23]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[24]  Xinbing Wang,et al.  Large-scale Wireless Fingerprints Prediction for Cellular Network Positioning , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[25]  Prasant Misra,et al.  Energy efficient GPS acquisition with Sparse-GPS , 2014, IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks.

[26]  Jianxin Wu,et al.  GROPING: Geomagnetism and cROwdsensing Powered Indoor NaviGation , 2015, IEEE Transactions on Mobile Computing.

[27]  Elliott D. Kaplan Understanding GPS : principles and applications , 1996 .

[28]  Mikkel Baun Kjærgaard,et al.  EnTracked: energy-efficient robust position tracking for mobile devices , 2009, MobiSys '09.

[29]  E. Groth,et al.  A pattern-matching algorithm for two-dimensional coordinate lists. [for stellar positions] , 1986 .

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

[31]  Piotr Indyk,et al.  Faster GPS via the sparse fourier transform , 2012, Mobicom '12.

[32]  Romit Roy Choudhury,et al.  EnLoc: Energy-Efficient Localization for Mobile Phones , 2009, IEEE INFOCOM 2009.

[33]  Moustafa Youssef,et al.  No need to war-drive: unsupervised indoor localization , 2012, MobiSys '12.