Weiguo Guan
College of Electronic and Information Engineering, Liaoning University of Technology, Jinzhou, 121001, Liaoning, China
Baochun Lu
College of Electrical Engineering, Liaoning University of Technology, Jinzhou, 121001, Liaoning, China
Baoguo Li
College of Electrical Engineering, Liaoning University of Technology, Jinzhou, 121001, Liaoning, China
Pijie Jiang
College of Electrical Engineering, Liaoning University of Technology, Jinzhou, 121001, Liaoning, China
ABSTRACT
The Non-Line-of-Sight (NLOS) error caused by positioning signal reflection and refraction has always been obstacles to improve TDOA positioning performance in mobile localization. Although many researches have invented to mitigate the NLOS influence and some of them has improved the positioning accuracy effectively. However, they were impeded to provide the accurate estimate of NLOS. In this study, TDOA ranging error model is analyzed and a novel localization algorithm based on Elman neural network is proposed to estimate and mitigate NLOS error in TDOA positioning, The estimation and correction for NLOS errors is achieved by Elman neural network without NLOS prior information firstly, then the TDOA data are reconstructed to mitigate the NLOS errors, finally, position solution is estimated by the two-step Weighted Least Squares. The simulation results show that the proposed algorithm has better localization performance in localization precision than the basic positioning algorithm and existing improved even in serious NLOS environment.
PDF References Citation
How to cite this article
Weiguo Guan, Baochun Lu, Baoguo Li and Pijie Jiang, 2013. A TDOA localization Algorithm Based on Elman Neural Network for Cellular
networks. Information Technology Journal, 12: 7143-7147.
DOI: 10.3923/itj.2013.7143.7147
URL: https://scialert.net/abstract/?doi=itj.2013.7143.7147
DOI: 10.3923/itj.2013.7143.7147
URL: https://scialert.net/abstract/?doi=itj.2013.7143.7147
REFERENCES
- Boccadoro, M., G. de Angelis and P. Valigi, 2012. TDOA positioning in NLOS scenarios by particle filtering. Wireless Networks, 18: 579-589.
CrossRef - Cheng, Y.C., W.M. Qi and W.Y. Cai, 2002. Dynamic properties of Elman and modified Elman neural network. Proceedings of the International Conference on Machine Learning and Cybernetics, Volume 2, November 2002, Beijing, China, pp: 637-640.
CrossRef - Gao, X., D. You and S. Katayama, 2012. Seam tracking monitoring based on adaptive kalman filter embedded elman neural network during high-power fiber laser welding. IEEE Trans. Ind. Electronics, 59: 4315-4325.
CrossRef - Lisien, B., D. Morales, D. Silver and G. Kantor, 2003. Hierarchical simultaneous localization and mapping. Proceedings of the International Conference on Intelligent Robots and Systems, Volume 1, October 27-31, 2003, Las Vegas, US., pp: 448-453.
CrossRef - Liu, Z., M. Liu and F. Qian, 2004. The application of one improved niche genetic algorithm for Elman recurrent neural networks. Proceedings of the 5th World Congress on Intelligent Control and Automation, June 15-19, 2004, Hangzhou, China, pp: 1978-1981.
CrossRef - Sun, G. and B. Hu, 2009. A minimum entropy estimation based mobile positioning algorithm. IEEE Trans. Wireless Commun., 8: 24-27.
CrossRef - Yu, K. and Y.J. Guo, 2008. Improved positioning algorithms for non-line-of-sight environments. IEEE Trans. Vehicular Technol., 57: 2342-2353.
CrossRef