Использование рекуррентных нейронных сетей и генетического алгоритма для предсказания дифференциальных поправок к псевдодальностям GPS
https://doi.org/10.17285/0869-7035.2015.23.2.092-105
Abstract
It has been suggested to compensate the signal absence and transmission delay of differential corrections in the real-time system (Real Time Differential GPS, RTDGPS) by estimating future values of the pseudorange corrections (PRC). Recurrent neural network (RNN) and genetic algorithm (GA) are used for the estimation. RTDGPS system using two inexpensive receivers in reference and user stations has been considered. Simulation and experimental results presented indicate that predicting the PRC future values improves RTDGPS accuracy.
About the Authors
М. Рефан
Педагогический институт Шахид Раджи, факультет электротехники и вычислительной техники (Тегеран)
Islamic Republic of Iran
Islamic Republic of Iran
A. Дамешги
Педагогический институт Шахид Раджи, факультет электротехники и вычислительной техники (Тегеран)
Islamic Republic of Iran
Islamic Republic of Iran
М. Камарзаррин
Университет Шахид Бехешти, факультет электротехники и вычислительной техники (Тегеран)
Islamic Republic of Iran
Islamic Republic of Iran
References
1. Seong Y. Ch., and Wan S. Ch. Performance enhancement of low-cost land navigation system for location-based service, ETRIJ Journal, 2006, vol. 28, no. 2, pp. 131-144.
2. Bock H., Dach R., Yoon Y., and Montenbruck O. GPS clock correction estimation for near realtime orbit determination applications, AEROSP SCI TECHNOL, 2009, vol. 13, no. 7, pp. 415–422.
3. Mosavi M. R., Mohammadi K., and Refan M. H. A new approach for improving of GPS positioning accuracy by using an adaptive neurofuzzy system, before and after S/A is turned off,” IJEEE, 2004, vol. 15, no. 1, pp. 95-108.
4. Kawamura K. and Tanaka T. Study on the improvement of measurement accuracy in GPS, SICE-ICASE Int. Joint Conf., 2006, pp. 1372-1375.
5. McDonald K. D. The modernization of GPS: plans, new capabilities, and the future, JGPS, 2002, vol. 1, no. 3, pp. 1-17.
6. Mohasseb M., Rabbany A., Alim O., and Rashad R. DGPS correction prediction using artificial neural networks, Journal of Navigation, 2007, vol. 60, no. 2, pp. 291-301.
7. Zhang J., Zhang J., Zhang K., Grenfel R., Deakin R. GPS satellite velocity and acceleration determination using the broadcast ephemeris, Journal of Navigation, 2006, vol. 59, pp. 293–305.
8. Mosavi M. R. Comparing DGPS corrections prediction using neural network, fuzzy neural network, and Kalman filter, GPS Solut., 2006, vol. 10, no. 2, pp. 97-107.
9. Mosavi M. R. A wavelet based neural network for DGPS corrections prediction, WSEAS transactions on systems, Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 2004, vol. 3, no. 10, pp. 3070-3075.
10. Mosavi M. R. Estimation of pseudo-range DGPS corrections using neural networks trained by evolutionary algorithms, RIEE, 2010, vol. 5, no. 6, pp. 2715-272.
11. Jwo D., Lee, T., and Tseng Y. W. ARMA neural networks for predicting DGPS pseudo range correction, Journal of Navigation, 2004, vol. 57, no. 2, pp. 275–28.
12. Geng Y. Online DGPS correction prediction using recurrent neural networks with unscented Kalman filter, International Global Navigation Satellite Systems Society IGNSS symposium, the University of New South Wales, Sydney, Australia, 2007.
13. Indriyatmoko A., Kang T., Jae Lee J., Jee G., Cho Y. B., and Kim J. Artificial neural network for predicting DGPS carrier phase and pseudo-range correction, GPS Solut., 2008, vol. 12, no. 4, pp. 237-247.
14. Yinglei X., Li Q., Xie S., and Zhang L. Study on algorithm and communication protocol of differential GPS positioning based on pseudo range, International Forum on Information Technology and Applications, 2009.
15. Refan M. H., Dameshghi A., and Kamarzarrin M. Improving RTDGPS accuracy using hybrid PSOSVM prediction model, Aerospace Science and Technology, 2014, vol. 37, pp. 55–69.
16. Park B., Kim J., and Kee J. RRC unnecessary for DGPS messages, IEEE Trans. Aerosp. Electron. Syst., 2006, vol. 42, no. 3, pp. 1149-1160.
17. Aris W. A., Musa T. A., Omar K., Abdullah K. A., and Othman R. Performance of local DGPS without RRC in equatorial area, International Symposium on GPS/GNSS, Taipei, Taiwan, 2010.
18. Bod´en M. A guide to recurrent neural networks and backpropagation, In the Dallas project, SICS Technical Report, 2002.
19. Cai X., Zhang N., Venayagamoorthy G. K., and Wunsch D. C. Time series prediction with recurrent neural networks trained by a hybrid PSO-EA algorithm, NEUROCOMPUTING Journal, 2007, vol. 70, no. 13, pp. 2342-2353.
20. Graves A. and Schmidhuber J. Offline handwriting recognition with multi-dimensional recurrent neural networks, in Advances in Neural Information Processing Systems, 2009.
21. Wells D., Beck N., Delikaraoglou D., Kleusberg A., Krakiwsky E. J., Lachapelle G., Langley R. B., Nakiboglu M., Schwarz K. P., Tranquilla J. M., and Vanicek P. Guide to GPS positioning. Canadian GPS associates, Fredericton N. B. Canada, 1986.
22. RTCM Special Committee No. 104, “RTCM recommended standards for differential NAVSTAR GPS service”. Radio Technical Committee for Maritime Services. Paper 134-89/SC104- 68. Washington DC (USA), 1990.
23. I-Lotus GPS Products - M12M User's Guide.
24. Giles C. L., Lawrence S., and Tsoi A. C. Noisy time series prediction using a recurrent neural network and grammatical inference, JMLR, 2001, vol. 44, no. 2, pp. 161–183.
25. Pettersson J. and Wahde M. Generating balancing behavior using recurrent neural networks and biologically inspired computation methods, IEEE Transactions of Evolutionary Computation, Sep. 2003.
26. Williams R. J., and Zipser D. A learning algorithm for continually running fully recurrent neural networks, Neural Computation, 1989, vol. 1, no. 2, pp. 270–280.
27. Dharmistha M. S. and Vishwakarma D. Genetic algorithm based weights optimization of artificial neural network, International IJAREEIE, 2012, vol. 3, no. 3, pp. 206-211, [Online]. Available: http://www.ijareeie.com/volume-1-issue-3
28. Changyu S., Lixia W., and Qian L. Optimization of injection molding process parameters was using combination of artificial neural network and genetic algorithm method, J MATER PROCESS TECH, 2007, vol.183, no. 2, pp. 412–418.
29. Leung H. F., Lam H. K., Ling S. H., and Tam P. K. S. Tuning of the structure and parameters of a neural network using an improved genetic algorithm, IEEE Trans. Neural Networks, vol.1, pp. 79-88, 2003.
30. Sara G. S., Devi S. P., and Sridharan D. A genetic-algorithm-based optimized clustering for energy-efficient routing in MWSN, ETRI Journal, 2012, vol. 34, no. 6, pp. 922-931.
31. ZigBee Serial Adapter ProBee-ZS10 User Guide Sena Technologie. 32. u-blox 6 Receiver Description Including Protocol Specification.
Review
For citations:
, , . Giroskopiya i Navigatsiya. 2015;23(2):92-105. (In Russ.) https://doi.org/10.17285/0869-7035.2015.23.2.092-105
Views:
6
Email this article 