Advertisement

Deep Learning Architectures for Accurate Millimeter Wave Positioning in 5G

  • João GanteEmail author
  • Gabriel Falcão
  • Leonel Sousa
Article
  • 31 Downloads

Abstract

The introduction of 5G’s millimeter wave transmissions brings a new paradigm to wireless communications. Whereas physical obstacles were mostly associated with signal attenuation, their presence now adds complex, non-linear phenomena, including reflections and scattering. The result is a multipath propagation environment, shaped by the obstacles encountered, indicating a strong presence of hidden spatial information within the received signal. To untangle said information into a mobile device position, this paper proposes the usage of neural networks over beamformed fingerprints, enabling a single-anchor positioning approach. Depending on the mobile device target application, positioning can also be enhanced with tracking techniques, which leverage short-term historical data. The main contributions of this paper are to discuss and evaluate typical neural network architectures suitable to the beamformed fingerprint positioning problem, including convolutional neural networks, hierarchy-based techniques, and sequence learning approaches. Using short sequences with temporal convolutional networks, simulation results show that stable average estimation errors of down to 1.78 m are obtained on realistic outdoor scenarios, containing mostly non-line-of-sight positions. These results establish a new state-of-the-art accuracy value for non-line-of-sight millimeter wave outdoor positioning, making the proposed methods very competitive and promising alternatives in the field.

Keywords

5G Deep learning Millimeter wave Outdoor positioning Temporal convolutional networks 

Notes

Acknowledgements

This work was supported by national funds through Fundação para a Ciência e a Tecnologia (FCT) with references UID/CEC/50021/2019, UID/EEA/50008/2019, and PTDC/EEI-HAC/30485/2017, as well as FCT Grant No. FRH/BD/103960/2014.

References

  1. 1.
    Pirinen P (2014) A brief overview of 5G research activities. In: 2014 1st International conference on 5G for ubiquitous connectivity (5GU), pp 17–22Google Scholar
  2. 2.
    Rappaport TS, Heath RW, Daniels RC, Murdock JN (2014) Millimeter wave wireless communications. Prentice Hall, Upper Saddle RiverGoogle Scholar
  3. 3.
    del Peral-Rosado JA, Raulefs R, López-Salcedo JA, Seco-Granados G (2017) Survey of cellular mobile radio localization methods: from 1G to 5G. IEEE Commun Surv Tutor 20:1124–1148CrossRefGoogle Scholar
  4. 4.
    Witrisal K, Meissner P, Leitinger E, Shen Y, Gustafson C, Tufvesson F, Haneda K, Dardari D, Molisch AF, Conti A, Win MZ (2016) High-accuracy localization for assisted living: 5G systems will turn multipath channels from foe to friend. IEEE Signal Process Mag 33(2):59–70CrossRefGoogle Scholar
  5. 5.
    Koivisto M, Hakkarainen A, Costa M, Kela P, Leppanen K, Valkama M (2017) High-efficiency device positioning and location-aware communications in dense 5G networks. IEEE Commun Mag 55(8):188–195CrossRefGoogle Scholar
  6. 6.
    Kanhere Ojas, Rappaport Theodore S (2018) Position locationing for millimeter wave systems. In: GLOBECOM 2018—2018 IEEE global communications conferenceGoogle Scholar
  7. 7.
    Ye X, Yin X, Cai X, Pérez Yuste A, Xu H (2017) Neural-network-assisted UE localization using radio-channel fingerprints in LTE networks. IEEE Access 5:12071–12087CrossRefGoogle Scholar
  8. 8.
    Gante J, Falcao G, Sousa L (2018) Beamformed fingerprint learning for accurate millimeter wave positioning. In: IEEE 88th vehicular technology conference (VTC Fall)Google Scholar
  9. 9.
    Gante J, Falcao G, Sousa L (2019) Enhancing beamformed fingerprint outdoor positioning with hierarchical convolutional neural networks. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP)Google Scholar
  10. 10.
    Savic V, Larsson EG (2015) Fingerprinting-based positioning in distributed massive MIMO systems. In: 2015 IEEE 82nd vehicular technology conference (VTC2015-Fall)Google Scholar
  11. 11.
    MediaTek MT 3339 datasheet. https://labs.mediatek.com/en/chipset/MT3339. Accessed 19 Feb 2018
  12. 12.
    Fischer S (2014) Observed time difference of arrival (OTDOA) positioning in 3GPP LTE. In: Qualcomm Technologies Inc., White PaperGoogle Scholar
  13. 13.
    Wei Z, Zhao Y, Liu X, Feng Z (2017) DoA-LF: a location fingerprint positioning algorithm with millimeter-wave. IEEE Access 5:22678–22688CrossRefGoogle Scholar
  14. 14.
    Shahmansoori A, Garcia GE, Destino G, Seco-Granados G, Wymeersch H (2018) Position and orientation estimation through millimeter-wave mimo in 5G systems. IEEE Trans Wirel Commun 17(3):1822–1835CrossRefGoogle Scholar
  15. 15.
    Abu-Shaban Z, Zhou X, Abhayapala T, Seco-Granados G, Wymeersch H (2018) Error bounds for uplink and downlink 3d localization in 5g mmwave systems. IEEE Trans Wirel Commun 17:4939CrossRefGoogle Scholar
  16. 16.
    Hu S, Berg A, Li X, Rusek F (2017) Improving the performance of OTDOA based positioning in NB-IoT systems. In: 2017 IEEE global communications conference (GLOBECOM)Google Scholar
  17. 17.
    Weill LR, Grewal MS, Andrews AP (2007) Global positioning systems, inertial navigation, and integration, 2nd edn. Wiley, HobokenGoogle Scholar
  18. 18.
    Guerra A, Guidi F, Dardari D (2018) Single-anchor localization and orientation performance limits using massive arrays: Mimovs.beamforming. IEEE Trans Wirel Commun 17(8):5241–5255CrossRefGoogle Scholar
  19. 19.
    Bengio Y, LeCun Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  20. 20.
    3GPP (2018) Evolved universal terrestrial radio access (E-UTRA); LTE positioning protocol (LPP). In: 3rd Generation Partnership Project (3GPP), TS 36.355 V14.5.1Google Scholar
  21. 21.
    Mao G, Fidan B, Anderson BD (2007) Wireless sensor network localization techniques. Comput Netw 51(10):2529–2553CrossRefzbMATHGoogle Scholar
  22. 22.
    Rappaport TS, Reed JH, Woerner BD (1996) Position location using wireless communications on highways of the future. IEEE Commun Mag 34(10):33–41CrossRefGoogle Scholar
  23. 23.
    Lemic F, Martin J, Yarp C, Chan D, Handziski V, Brodersen R, Fettweis G, Wolisz A, Wawrzynek J (2016) Localization as a feature of mmWave communication. In: 2016 international wireless communications and mobile computing conference (IWCMC), pp 1033–1038Google Scholar
  24. 24.
    Gante J, Falcao G, Sousa L (2018) Data-aided fast beamforming selection for 5G. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP)Google Scholar
  25. 25.
    Azar Y, Wong GN, Wang K, Mayzus R, Schulz JK, Zhao H, Gutierrez F, Hwang D, Rappaport TS (2013) 28 GHz propagation measurements for outdoor cellular communications using steerable beam antennas in New York city. In: 2013 IEEE international conference on communications (ICC), pp 5143–5147Google Scholar
  26. 26.
    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958MathSciNetzbMATHGoogle Scholar
  27. 27.
    Yu J, Zhu C, Zhang J, Huang Q, Tao D (2019) Spatial pyramid-enhanced netvlad with weighted triplet loss for place recognition. IEEE Trans Neural Netw Learn Syst. https://ieeexplore.ieee.org/document/8700608
  28. 28.
    Siqi B, Mingjiang Y, Yongjie L, Qun W (2018) Rfedrnn: an end-to-end recurrent neural network for radio frequency path fingerprinting. In: Mouhoub M, Sadaoui S, Mohamed OA, Ali M (eds) Recent trends and future technology in applied intelligence. Springer, Cham, pp 560–571Google Scholar
  29. 29.
    Yan Z, Zhang H, Piramuthu R, Jagadeesh V, DeCoste D, Di W, Yu Y (2015) HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In: 2015 IEEE international conference on computer Vision (ICCV), pp 2740–2748Google Scholar
  30. 30.
    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780CrossRefGoogle Scholar
  31. 31.
    Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: Proceedings of the 30th international conference on international conference on machine learning—volume 28, ICML’13, pp III–1310–III–1318Google Scholar
  32. 32.
    Bai S, Zico KJ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv e-prints, arXiv:1803.01271
  33. 33.
    Van Den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior AW, Kavukcuoglu K (2016) WaveNet: a generative model for raw audio. arXiv e-prints, arXiv:1609.03499
  34. 34.
    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3431–3440Google Scholar
  35. 35.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778Google Scholar
  36. 36.
    Obara T, et al (2016) Experiment of 28 GHz band 5G super wideband transmission using beamforming and beam tracking in high mobility environment. In: 2016 IEEE 27th annual international symposium on personal, indoor, and mobile radio communications (PIMRC)Google Scholar
  37. 37.
    Wireless InSite web-page. https://www.remcom.com/wireless-insite-em-propagation-software/. Accessed 19 Feb 2019
  38. 38.
    Caruana R, Lawrence S, Giles L (2000) Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: Proceedings of the 13th international conference on neural information processing systems, NIPS’00, pp 381–387, Cambridge, MA, USA, MIT PressGoogle Scholar
  39. 39.
    Kingma DP, Jimmy B (2014) Adam: a method for stochastic optimization. CoRR, arXiv:1412:6980
  40. 40.
    Super-E: low power and good performance (white paper). https://www.u-blox.com/en/white-papers. Accessed 19 Feb 2019; Requires registration
  41. 41.
    Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265–283Google Scholar
  42. 42.
    Hong C, Jun Y, You J, Chen X, Tao D (2015) Multi-view ensemble manifold regularization for 3d object recognition. Inf Sci 320:395–405MathSciNetCrossRefGoogle Scholar
  43. 43.
    Hong C, Yu J, Zhang J, Jin X, Lee K (2018) Multi-modal face pose estimation with multi-task manifold deep learning. IEEE Trans Ind Inf 15(7):3952–3961. https://ieeexplore.ieee.org/document/8554134
  44. 44.
    Yu J, Rui Y, Tao D (2014) Click prediction for web image reranking using multimodal sparse coding. IEEE Trans Image Process 23(5):2019–2032MathSciNetCrossRefzbMATHGoogle Scholar
  45. 45.
    Hong C, Yu J, Tao D, Wang M (2015) Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans Ind Electr 62(6):3742–3751Google Scholar
  46. 46.
    Fuzhen Z, Lang H, Jia H, Jixin M, Qing H (2017) Transfer learning with manifold regularized convolutional neural network. In: Li G, Ge Y, Zhang Z, Jin Z, Blumenstein M (eds) Knowledge science, engineering and management. Springer, Cham, pp 483–494Google Scholar
  47. 47.
    Fazel M, Hindi H, Boyd S (2004) Rank minimization and applications in system theory. In: Proceedings of the 2004 American control conference, vol 4, pp 3273–3278Google Scholar
  48. 48.
    Ouyang H, He N, Tran L, Gray A (2013) Stochastic alternating direction method of multipliers. In: International conference on machine learning, pp 80–88Google Scholar
  49. 49.
    Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670MathSciNetCrossRefzbMATHGoogle Scholar
  50. 50.
    Yu J, Yang X, Gao F, Tao D (2017) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern 47(12):4014–4024CrossRefGoogle Scholar
  51. 51.
    Parikh AP, Täckström O, Das D, Uszkoreit J (2016) A decomposable attention model for natural language inference. CoRR, arXiv:1606.01933
  52. 52.
    Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. CoRR, arXiv:1706.03762
  53. 53.
    Lee J, Lee Y, Kim J, Kosiorek AR, Choi S,Teh YW (2018) Set transformer. CoRR, arXiv:1810:00825

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.INESC-ID, ISTUniversidade de LisboaLisbonPortugal
  2. 2.Instituto de TelecomunicaçõesUniversity of CoimbraCoimbraPortugal

Personalised recommendations