Skip to main content
SpringerLink
Log in

Indoor non-line-of-sight and multipath detection using deep learning approach

  • Original Article
  • Published:
GPS Solutions Aims and scope Submit manuscript

Abstract

Global navigation satellite systems (GNSSs) provide sufficient position accuracy outdoors but can perform poorly in indoor situations. Therefore, various techniques have been presented to meet the indoor requirements, among which the pseudolite system (PLS) is widely studied. A PLS has several error sources including clock error, thermal noise and path-dependent error; among them path-dependent errors, e.g., non-line-of-sight (NLOS, i.e., the direct ray is blocked, only reflected rays received) and multipath (i.e., the direct ray is received together with the reflected rays), are the most intractable to deal with and always cause large range errors. The indoor furniture and flat surfaces of the walls and ceilings make NLOS and multipath quite severe. Detecting NLOS and multipath is a classification problem, which can be well tackled by deep learning approaches. Deep learning algorithms are functions of nonlinear regression using thousands of parameters that distributed in many hidden layers whose values are determined by training phase. We present an NLOS and multipath detecting network (NMDN) that consists of five convolution layers and two fully connected layers; we feed NMDN with the outputs of a receiver’s tracking loop; subsequently, it tells us the detection results. The training and testing data sets are generated by a GNSS software receiver using intermediate frequency signal collected from an indoor PLS. The presented method is compared with two support vector machines, which are the traditional methods for classification, and shows an improvement of up to 45% in overall classification accuracy. The impacts of indoor NLOS and multipath are also analyzed with double difference observables. The results show NLOS causes more serious range error than multipath. The proposed method is suitable for detecting NLOS and multipath when the receiver operating environment is not stable.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  • Alex K, Ilya S, Geoffrey EH (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems, Lake Tahoe, Nevada, 3–6 Dec, pp 1097–1105

  • Babu R, Wang J (2009) Ultra-tight GPS/INS/PL integration: a system concept and performance analysis. GPS Solut 13(1):75–82

    Article  Google Scholar 

  • Bregar K, Mohorčič M (2018) Improving indoor localization using convolutional neural networks on computationally restricted devices. IEEE Access 6:17429–17441

    Article  Google Scholar 

  • Choi JS, Lee WH, Lee JH, Lee JH, Kim SC (2018) Deep learning based NLOS identification with commodity WLAN DEVICES. IEEE Trans Veh Technol 67(4):3295–3303

    Article  Google Scholar 

  • Dominik S, Andreas M, Sven B (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: Proceedings of artificial neural networks—ICANN 2010, Thessaloniki, Greece, 15–18 Sept, pp 92–101

  • Egea-Roca D et al (2015) Signal-level integrity and metrics based on the application of quickest detection theory to multipath detection. In: Proceedings of ION GNSS 2015, Institute of Navigation,Tampa, Florida, 14–18 Sept, pp 2926–2938

  • Egea-Roca D, Lopez-Salcedo JA, Seco-Granados G, Poor HV (2018) Performance bounds for finite moving average tests in transient change detection. IEEE Trans Signal Process 66(6):1594–1606

    Article  Google Scholar 

  • Groves PD, Jiang Z (2013) Height aiding, C/N0 weighting and consistency checking for GNSS NLOS and multipath mitigation in urban areas. J Navig 66(5):653–669

    Article  Google Scholar 

  • Groves PD, Jiang Z, Rudi M, Strode P (2013) A portfolio approach to NLOS and multipath mitigation in dense urban areas. In: Proceedings of ION GNSS + 2013, Institute of Navigation, Nashville, TN, 16–20 Sept, pp 3231–3247

  • Guo X, Zhou Y, Wang J, Liu K, Liu C (2018) Precise point positioning for ground-based navigation systems without accurate time synchronization. GPS Solut 22(2):34

    Article  Google Scholar 

  • Ian G, Yoshua B, Aaron C (2016) Deep learning. MIT Press, Boston. www.deeplearningbook.org

  • Jiang Z, Groves PD (2012) GNSS NLOS and multipath error mitigation using advanced multi-constellation consistency checking with height aiding. In: Proceedings of ION GNSS 2012, Institute of Navigation, Nashville, TN, 17–21 Sept, pp 79–88

  • Jiang Z, Groves PD (2014) NLOS GPS signal detection using a dual-polarisation antenna. GPS Solut 18(1):15–26

    Article  Google Scholar 

  • Jiang Z, Groves PD, Ochieng WY, Feng S, Milner CD, Mattos PG (2011) Multi-constellation GNSS multipath mitigation using consistency checking. In: Proceedings of ION GNSS 2011, Institute of Navigation, Portland, OR, 19–23 Sept, pp 3889–3902

  • Kbayer N, Sahmoudi M (2017) 3D-mapping-aided GNSS localization for integrity monitoring in urban environments. In: Proceedings of the 14th international multi-conference on systems, signals and devices (SSD), Marrakech, Morocco, 28–31 March, pp 591–596

  • Kbayer N, Sahmoudi M (2018) Performances analysis of GNSS NLOS bias correction in urban environment using a 3D city model and GNSS simulator. IEEE Trans Aerosp Electron Syst 54(4):1799–1814

    Article  Google Scholar 

  • Lee H, Wang J, Rizos C, Grejner-Brzezinska D, Toth C (2002) GPS/Pseudolite/INS integration: concept and first tests. GPS Solut 6(1):34–46

    Article  Google Scholar 

  • Loffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32th international conference on machine learning, Lille, France, 6–11 July, pp 448–456

  • Mass AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In the 30th international conference on machine learning, workshop on deep learning for audio, speech, and language processing, Atlanta, GA, 16–21 June. https://sites.google.com/site/deeplearningicml2013/accepted_papers. Accessed 15 May 2019

  • Naila M, Florent P (2014) Generalized max pooling. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition, Columbus, OH, 23–28 June, pp 2473–2480

  • Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning, Haifa, Israel, pp 807–814

  • Sokhandan N, Ziedan N, Broumandan A, Lachapelle G (2017) Context-aware adaptive multipath compensation based on channel pattern recognition for GNSS receivers. J Navig 70(5):944–962

    Article  Google Scholar 

  • Tang Z (2009) Research on relevant theory for GNSS signal design and evaluation. Doctor Thesis, Huazhong University of Science and Technology, Wuhan, China

  • Wang J (2002) Pseudolite application in positioning and navigation: progress and problems. J Glob Position Syst 1(1):48–56

    Article  Google Scholar 

  • Wang L, Groves PD, Ziebart MK (2013) GNSS shadow matching: Improving urban positioning accuracy using a 3D city model with optimized visibility scoring scheme. Navigation 60(3):195–207

    Article  Google Scholar 

  • 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 

  • Wen W, Zhang G, Hsu L-T (2018) Exclusion of GNSS NLOS receptions caused by dynamic objects in heavy traffic urban scenarios using real-time 3D point cloud: an approach without 3D maps. In: Proceedings of IEEE/ION PLANS 2018, Monterey, CA, 23–26 April, pp 158–165

  • Yousef A, Mohammed A, Martha K, Ahmed M, Amit K, Esam E (2016) Impact of indoor environment quality on occupant well-being and comfort: a review of the literature. Int J Sustain Built Environ 5(1):1–11

    Article  Google Scholar 

  • Ziedan NI (2012) Multipath channel estimation and pattern recognition for environment-based adaptive tracking. In: Proceedings of ION GNSS 2012, Institute of Navigation, Nashville, TN, 17–21 Sept, pp 394–407

  • Ziedan NI (2016) Multipath and NLOS signals identification and satellite selection algorithms for multi-constellation receivers. In: Proceedings of ION GNSS + 2016, Institute of Navigation, Portland, OR, 12–16 Sept, pp 521–533

  • Ziedan NI (2017) Urban positioning accuracy enhancement utilizing 3D buildings model and accelerated ray tracing algorithm. In: Proceedings of ION GNSS + 2017, Institute of Navigation, Portland, OR, 25–29 Sept, pp 3253–3268

Download references

Author information

Authors and Affiliations

  1. School of Electronic and Information Engineering, Beihang University, Beijing, 100083, China

    Qing Liu & Zhigang Huang

  2. School of Civil and Environmental Engineering, The University of New South Wales, Sydney, 2052, Australia

    Qing Liu & Jinling Wang

Authors
  1. Qing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhigang Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jinling Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qing Liu.

Additional information

Publisher's Note

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

Appendix: Confusion matrix

Appendix: Confusion matrix

Tables 5 and 6 show the confusion matrixes for various algorithms that run on three variables.

Table 5 Confusion matrix for SVM with RBF and linear kernels based on three variables
Full size table
Table 6 Confusion matrix for NMDN with three variables
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Q., Huang, Z. & Wang, J. Indoor non-line-of-sight and multipath detection using deep learning approach. GPS Solut 23, 75 (2019). https://doi.org/10.1007/s10291-019-0869-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10291-019-0869-4

Keywords

Search

Navigation