Indoor Localization Using Smartphone Magnetic and Light Sensors: a Deep LSTM Approach

Abstract

With the increasing demand for location-based services, indoor localization has attracted great interest. In this paper, we present DeepML, a deep long short-term memory (LSTM) based system for indoor localization using magnetic and light sensors on smartphones. We experimentally verify the feasibility of using bimodal data from magnetic and light sensors for indoor localization for closed environments where there is no ambient light. We then design the DeepML system, which first builds bimodal images by data preprocessing, and then trains a deep LSTM network in the offline phase. Newly received magnetic field and light data are then exploited for estimating the location of the mobile device using a probabilistic method. The extensive experiments verify the effectiveness of the proposed DeepML system.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

References

  1. 1.

    Khelifi F, Bradai A, Benslimane A, Rawat P, Atri M (2018) A survey of localization systems in internet of things. Springer Mobile Networks and Applications Journal, pp 1–25

  2. 2.

    Kumarasiri R, Alshamaileh K, Tran NH, Devabhaktuni V (2016) An improved hybrid RSS/TDOA wireless sensors localization technique utilizing Wi-Fi networks. Springer Mobile Networks and Applications 21(2):286–295

    Article  Google Scholar 

  3. 3.

    Kan C, Ding G, Wu Q, Zhang T (2018) Robust localization with crowd sensors: a data cleansing approach. Springer Mobile Networks and Applications 23(1):108–118

    Article  Google Scholar 

  4. 4.

    Gu Y, Lo A, Niemegeers I (2009) A survey of indoor positioning systems for wireless personal networks. IEEE Commun Surveys Tuts 11(1):13–32

    Article  Google Scholar 

  5. 5.

    Wang X, Mao S, Pandey S, Agrawal P (2014) CA2T: Cooperative antenna arrays technique for pinpoint indoor localization. In: Proc MobiSPC 2014, Niagara Falls, Canada, pp 392–399

  6. 6.

    Bahl P, Padmanabhan VN (2000) Radar: an in-building RF-based user location and tracking system. In: Proc IEEE INFOCOM’00, Tel Aviv, Israel, pp 775–784

  7. 7.

    Youssef M, Agrawala A (2005) The Horus WLAN location determination system. In: Proc ACM MobiSys’05, Seattle, WA, pp 205–218

  8. 8.

    Caso G, De Nardis L (2017) Virtual and oriented WiFi fingerprinting indoor positioning based on multi-wall multi-floor propagation models. Springer Mobile Networks and Applications 22(5):825–833

    Article  Google Scholar 

  9. 9.

    Liu H-H (2017) The quick radio fingerprint collection method for a WiFi-based indoor positioning system. Springer Mobile Networks and Applications 22(1):61–71

    Article  Google Scholar 

  10. 10.

    Xiao J, Wu K, Yi Y, Ni L (2012) FIFS: Fine-grained indoor fingerprinting system. In: Proc IEEE ICCCN’12, Munich, Germany, pp 1–7

  11. 11.

    Wang X, Gao L, Mao S, Pandey S (2017) CSI-Based fingerprinting for indoor localization: a deep learning approach. IEEE Trans Veh Technol 66(1):763–776

    Google Scholar 

  12. 12.

    Chung J, Donahoe M, Schmandt C, Kim I-J, Razavai P, Wiseman M (2011) Indoor location sensing using geo-magnetism. In: Proc ACM MobiSys’11, Bethesda, MD, pp 141–154

  13. 13.

    Storms W, Shockley J, Raquet J (2010) Magnetic field navigation in an indoor environment. In: Proc IEEE UPINLBS’10, Kirkkonummi, Finland, pp 1–10

  14. 14.

    Gozick B, Subbu KP, Dantu R, Maeshiro T (2011) Magnetic maps for indoor navigation. IEEE Trans Instrum Meas 60(12):3883–3891

    Article  Google Scholar 

  15. 15.

    Shu Y, Bo C, Shen G, Zhao C, Li L, Zhao F (2015) Magicol: Indoor localization using pervasive magnetic field and opportunistic WiFi sensing. IEEE J Sel Areas Commun 33(7):1443–1457

    Article  Google Scholar 

  16. 16.

    Ma Y, Dou Z, Jiang Q, Hou Z (2016) Basmag: an optimized HMM-based localization system using backward sequences matching algorithm exploiting geomagnetic information. IEEE Sensors J 16(20):7472–7482

    Article  Google Scholar 

  17. 17.

    Yang Z, Wang Z, Zhang J, Huang C, Zhang Q (2015) Wearables can afford: Light-weight indoor positioning with visible light. In: Proc ACM Mobisys’15, Florence, Italy, pp 317– 330

  18. 18.

    Kuo Y-S, Pannuto P, Hsiao K-J, Dutta P (2014) Luxapose: Indoor positioning with mobile phones and visible light. In: Proc ACM MobiCom’14, Maui, HI, pp 447–458

  19. 19.

    Li L, Hu P, Peng C, Shen G, Zhao F (2014) Epsilon: a visible light based positioning system. In: Proc USENIX NSDI’14, Seattle, WA, pp 331–343

  20. 20.

    Zhang C, Zhang X (2016) LiTell: Robust indoor localization using unmodified light fixtures. In: Proc ACM MobiCom’16, New York, NY, pp 230–242

  21. 21.

    Xu Q, Zheng R, Hranilovic S (2015) IDyLL: Indoor localization using inertial and light sensors on smartphones. In: Proc ACM UbiComp’15, Osaka, Japan, pp 307–318

  22. 22.

    Zhao Z, Wang J, Zhao X, Peng C, Guo Q, Wu B (2017) NaviLight: Indoor localization and navigation under arbitrary lights. In: Proc IEEE INFOCOM’17, Atlanta, GA, pp 1–9

  23. 23.

    Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: Continual prediction with lstm. J Neural Comput 12(10):2451–2471

    Article  Google Scholar 

  24. 24.

    Greff K, Srivastava RK, Koutníik J, Steunebrink BR, Schmidhuber J (2017) Lstm: a search space odyssey. IEEE Trans Neural Netw Learn Syst 28(10):2222–2232

    MathSciNet  Article  Google Scholar 

  25. 25.

    Graves A, Jaitly N, Mohamed A-r (2013) Hybrid speech recognition with deep bidirectional LSTM. In: Proc IEEE ASRU’13, Olomouc, Czech Republic, pp 273–278

  26. 26.

    Ordonez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. MDPI Sensors 16(1):115

    Article  Google Scholar 

  27. 27.

    Do T-H, Yoo M (2016) An in-depth survey of visible light communication based positioning systems. MPDI Sensors 16(5):678

    Article  Google Scholar 

  28. 28.

    Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980

  29. 29.

    He S, Chan S-HG (2016) Wi-fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Commun Surveys Tuts 18(1):466–490. First Quarter

    Article  Google Scholar 

  30. 30.

    Win MZ, Shen Y, Dai W (2018) A theoretical foundation of network localization and navigation. Proc IEEE 106(7):1136–1165

    Article  Google Scholar 

  31. 31.

    Sun Y, Peng M, Zhou Y, Huang Y, Mao S (2018) Application of machine learning in wireless networks: Key techniques and open issues. arXiv:1809.08707

  32. 32.

    Rapinski J, Cellmer S (2016) Analysis of range based indoor positioning techniques for personal communication networks. Springer Mobile Networks and Applications 21(3):539–549

    Article  Google Scholar 

  33. 33.

    Wang X, Wang X, Mao S (2018) RF Sensing in the Internet of Things: a general deep learning framework. IEEE Commun Mag 56(9):62–67

    Article  Google Scholar 

  34. 34.

    Wang X, Gao L, Mao S, Pandey S (2015) Deepfi: Deep learning for indoor fingerprinting using channel state information. In: Proc WCNC’15, New Orleans, LA, pp 1666–1671

  35. 35.

    Wang X, Gao L, Mao S (2015) Phasefi: Phase fingerprinting for indoor localization with a deep learning approach. In: Proc GLOBECOM’15, San Diego, CA, pp 1–6

  36. 36.

    Wang X, Gao L, Mao S (2016) CSI Phase fingerprinting for indoor localization with a deep learning approach. IEEE Internet of Things J 3(6):1113–1123

    Article  Google Scholar 

  37. 37.

    Wang X, Gao L, Mao S (2017) BiLoc: Bi-modality deep learning for indoor localization with 5 GHz commodity Wi-Fi. IEEE Access J 5(1):4209–4220

    Article  Google Scholar 

  38. 38.

    Xiao C, Yang D, Chen Z, Tan G (2017) 3-D BLE indoor localization based on denoising autoencoder. IEEE Access J 5:12751–12760

    Article  Google Scholar 

  39. 39.

    Gu F, Khoshelham K, Yu C, Shang J (2018) Accurate step length estimation for pedestrian dead reckoning localization using stacked autoencoders. IEEE Trans Instrum Meas, p 1

  40. 40.

    Khatab ZE, Hajihoseini A, Ghorashi SA (2018) A fingerprint method for indoor localization using autoencoder based deep extreme learning machine. IEEE Sens Lett 2(1):1–4

    Article  Google Scholar 

  41. 41.

    Abbas M, Elhamshary M, Rizk H, Torki M, Youssef M (2019) WiDeep: WiFi-based accurate and robust indoor localization system using deep learning. In: IEEE PerCom’19, Kyoto, Japan

  42. 42.

    Wang X, Wang X, Mao S (2017) CiFi: Deep convolutional neural networks for indoor localization with 5GHz Wi-Fi. In: Proc IEEE ICC 2017, Paris, France, pp 1–6

  43. 43.

    Wang W, Wang X, Mao S Deep convolutional neural networks for indoor localization with CSI images. IEEE Transactions on Network Science and Engineering, in press. https://doi.org/10.1109/TNSE.2018.2871165

  44. 44.

    Wang X, Wang X, Mao S (2017) ResLoc: Deep residual sharing learning for indoor localization with CSI tensors. In: Proc IEEE PIMRC 2017, Montreal, Canada, pp 1–6

  45. 45.

    Wang X, Yu Z, Mao S (2018) DeepML: Deep LSTM for indoor localization with smartphone magnetic and light sensors. In: Proc IEEE ICC 2017, Kansas City, MO, pp 1–6

  46. 46.

    Sahar A, Han D (2018) An LSTM-based indoor positioning method using Wi-Fi signals. In: Proc ACM international conference on vision, image and signal processing, Las Vegas, NV, p Article No 43

  47. 47.

    Bytelight Technology. [Online] Available: http://www.bytelight.com/

  48. 48.

    Hu Y, Xiong Y, Huang W, Li X-Y, Yang P, Zhang Y, Mao X (2018) Lightitude: Indoor positioning using uneven light intensity distribution. Proc ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2(2):Artical 67

    Article  Google Scholar 

Download references

Acknowledgments

This work is supported in part by the NSF under Grant CNS-1702957, and by the Wireless Engineering Research and Education Center (WEREC) at Auburn University.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Shiwen Mao.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Yu, Z. & Mao, S. Indoor Localization Using Smartphone Magnetic and Light Sensors: a Deep LSTM Approach. Mobile Netw Appl 25, 819–832 (2020). https://doi.org/10.1007/s11036-019-01302-x

Download citation

Keywords

  • Indoor localization
  • Deep long short-term memory (LSTM)
  • Magnetic and light sensors
  • Visible light positioning
  • Fingerprinting