Skip to main content
Log in

Comparing DGPS corrections prediction using neural network, fuzzy neural network, and Kalman filter

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

Abstract

Position information obtained from standard global positioning system (GPS) receivers has time variant errors. For effective use of GPS information in a navigation system, it is essential to model these errors. A new approach is presented for improving positioning accuracy using neural network (NN), fuzzy neural network (FNN), and Kalman filter (KF). These methods predict the position components’ errors that are used as differential GPS (DGPS) corrections in real-time positioning. Method validity is verified with experimental data from an actual data collection, before and after selective availability (SA) error. The result is a highly effective estimation technique for accurate positioning, so that positioning accuracy is drastically improved to less than 0.40 m, independent of SA error. The experimental test results with real data emphasize that the total performance of NN is better than FNN and KF considering the trade-off between accuracy and speed for DGPS corrections prediction.

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

Access this article

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

Similar content being viewed by others

References

  • Abbott E, Powell D (1999) Land-vehicle navigation using GPS. Proc IEEE 87(1):145–162

    Article  Google Scholar 

  • Hu C, Chen C, Chen Y, Liu D (2003) Adaptive Kalman filtering for vehicle navigation. J Global Position Syst 2(1):42–47

    Google Scholar 

  • Jang J-SR (1993) ANFIS: adaptive-network-based fuzzy interface system. IEEE Trans Syst Man Cybernet 23(3):665–685

    Article  Google Scholar 

  • Kobayashi K, Cheok KC, Watanabe K, Munekata F (1998) Accurate differential global positioning system via fuzzy logic Kalman filter sensor fusion technique. IEEE Trans Ind Electron 45(3):510–518

    Article  Google Scholar 

  • Ku C-C, Lee KY, Edwards RM (1992) Improved nuclear reactor temperature control using diagonal recurrent neural networks. IEEE Trans Nucl Sci 39(6):2298–2308

    Article  Google Scholar 

  • Morgan-Owen GJ, Johnston GT (1995) Differential GPS positioning. IEEE Trans Electron Commun Eng 7(1):11–21

    Article  Google Scholar 

  • Mosavi MR (2004) A comparative study between performance of recurrent neural network and Kalman filter for DGPS correction prediction. In: IEEE conference on signal processing, Beijing, China, 1 August –4 September, 2004

  • Mosavi MR, Mohammadi K, Refan MH (2002) Time varying ARMA processing on GPS data to improve positioning accuracy. In: The Asian GPS conference 2002, New Delhi, India, 24–25 October, 2002, pp 125–128

  • Mosavi MR, Mohammadi K, Refan MH (2004) A new approach for improving of GPS positioning accuracy by using an adaptive neurofuzzy system, before and after S/A is turned off. Int J Eng Sci 15(1):101–114

    Google Scholar 

  • Nebot E, Durrant-Whyte H, Scheding S (1998) Frequency domain modeling of aided GPS for vehicle navigation systems. J Rob Auton Syst 25:73–82

    Article  Google Scholar 

  • Refan MH (2003) Satellite positioning sensors in past, present, and future. In: IEEE conference on sensors, Kuala Lumpur, Malaysia, 14–18 July, 2003, pp 37–46

  • Refan MH, Mohammadi K, Mosavi MR (2003) Improvement on a low cost positioning sensor accuracy. In: IEEE conference on sensors, Kuala Lumpur, Malaysia, 14–18 July, 2003, pp 9–14

  • Sato G, Asai T, Sakamoto T, Hase T (2000) Improvement of the positioning accuracy of a software-based GPS receiver using a 32-bit embedded microprocessor. IEEE Trans Consum Electron 46(3):521–530

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to M. R. Mosavi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mosavi, M.R. Comparing DGPS corrections prediction using neural network, fuzzy neural network, and Kalman filter. GPS Solut 10, 97–107 (2006). https://doi.org/10.1007/s10291-005-0011-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10291-005-0011-7

Keywords

Navigation