Adaptive Neurofuzzy and Positioning Accuracy
Experimental Results
After training of the neural network, to study the efficiency of trained neural network, we used 3000 test data that were collected on the building of Computer Control and Fuzzy Logic Research Lab in the Iran University of Science and Technology. The results from this test data are shown in Table2.
| Statistical Significance Characteristic | x Position Component | y Position Component | z Posisiton Component |
| Error Average [m] | 0.7349 | -0.5167 | 0.4021 |
| Error Variance [m2] | 1.1069 | 1.1433 | 1.2553 |
| Error Standard Deviation [m] | 1.0521 | 1.0693 | 1.1204 |
Conclusion
This paper has described how the positioning accuracy of a low cost GPS receiver can be greatly improved with a neurofuzzy system. Fuzzy logic was used to selection data training according to the measurement or available information. The result is a highly effective estimation technique for accurate positioning. The validity of the proposed neurofuzzy system was confirmed by experimental results on implemented unit in this letter. So, the average errors in prediction of x, y and z are less than 1 meters. Also, the result tests with real data show that the positioning accuracy with adaptive neurofuzzy system is independent of the absence of S/A or its presence.
References
- B Hofmann-Wellenhof, H Lichtenegger and J Collins, "GPS: Theory and Practice", Third Revised Edition, Springer-Verlag, Wien New York, 1994.
- MH Rfefan and K Mohammadi, "Point Averaging of the Position Components, before and after S/A IS Turned off", The Asian GPS Conference 2001, India, pp. 53-58.
- Chung-Jie Lin, Yung-Yaw Chen and Fan-Ren Chang, "Fuzzy Processing on GPS Data to Improve Position Accuracy", IEEE Symposium on Soft Computing Intelligent Systems and Information Processing, Asian, 1996, pp. 557-562.
- MR Mosavi, KMohammadi and MH Refan, "Fuzzy Processing on GPS Data to Improve Positioning Accuracy, before and after S/A Is Turned off", The Asian GPS Conference 2002, India, pp. 117-120.
- Xian-Jun Gao and Yi-Song Dai Ke Wang, "A Study on the Self-Difference GPS Positioning by Dynamic and Fictitious Datum Station", IEEE Conference on Vehicle Electronics, Vol.1, 1999, pp. 16-18.
- Jizhang Sang, Kurt Kubik and Lianggang Zhang, "Prediction of DGPS Corrections with Neural Networks", 1st Int'l Conference on Knowledge-Based Intelligent Electronic Systems, 21-23 May 1997, Australia, pp. 355-361.
- MR Mosavi, K Mohammadi and MH Refan, "Time Varying ARMA Processing on Low Cost GPS Receiver Data to Improve the Position Accuracy", The Asian GPS Conference 2002, India, pp. 125-128.
|
