Vol. 103
Latest Volume
All Volumes
PIERL 108 [2023] PIERL 107 [2022] PIERL 106 [2022] PIERL 105 [2022] PIERL 104 [2022] PIERL 103 [2022] PIERL 102 [2022] PIERL 101 [2021] PIERL 100 [2021] PIERL 99 [2021] PIERL 98 [2021] PIERL 97 [2021] PIERL 96 [2021] PIERL 95 [2021] PIERL 94 [2020] PIERL 93 [2020] PIERL 92 [2020] PIERL 91 [2020] PIERL 90 [2020] PIERL 89 [2020] PIERL 88 [2020] PIERL 87 [2019] PIERL 86 [2019] PIERL 85 [2019] PIERL 84 [2019] PIERL 83 [2019] PIERL 82 [2019] PIERL 81 [2019] PIERL 80 [2018] PIERL 79 [2018] PIERL 78 [2018] PIERL 77 [2018] PIERL 76 [2018] PIERL 75 [2018] PIERL 74 [2018] PIERL 73 [2018] PIERL 72 [2018] PIERL 71 [2017] PIERL 70 [2017] PIERL 69 [2017] PIERL 68 [2017] PIERL 67 [2017] PIERL 66 [2017] PIERL 65 [2017] PIERL 64 [2016] PIERL 63 [2016] PIERL 62 [2016] PIERL 61 [2016] PIERL 60 [2016] PIERL 59 [2016] PIERL 58 [2016] PIERL 57 [2015] PIERL 56 [2015] PIERL 55 [2015] PIERL 54 [2015] PIERL 53 [2015] PIERL 52 [2015] PIERL 51 [2015] PIERL 50 [2014] PIERL 49 [2014] PIERL 48 [2014] PIERL 47 [2014] PIERL 46 [2014] PIERL 45 [2014] PIERL 44 [2014] PIERL 43 [2013] PIERL 42 [2013] PIERL 41 [2013] PIERL 40 [2013] PIERL 39 [2013] PIERL 38 [2013] PIERL 37 [2013] PIERL 36 [2013] PIERL 35 [2012] PIERL 34 [2012] PIERL 33 [2012] PIERL 32 [2012] PIERL 31 [2012] PIERL 30 [2012] PIERL 29 [2012] PIERL 28 [2012] PIERL 27 [2011] PIERL 26 [2011] PIERL 25 [2011] PIERL 24 [2011] PIERL 23 [2011] PIERL 22 [2011] PIERL 21 [2011] PIERL 20 [2011] PIERL 19 [2010] PIERL 18 [2010] PIERL 17 [2010] PIERL 16 [2010] PIERL 15 [2010] PIERL 14 [2010] PIERL 13 [2010] PIERL 12 [2009] PIERL 11 [2009] PIERL 10 [2009] PIERL 9 [2009] PIERL 8 [2009] PIERL 7 [2009] PIERL 6 [2009] PIERL 5 [2008] PIERL 4 [2008] PIERL 3 [2008] PIERL 2 [2008] PIERL 1 [2008]
2022-04-22
AgileDARN Radar Echo Automatic Classification Algorithm Using Support Vector Machine
By
Progress In Electromagnetics Research Letters, Vol. 103, 151-160, 2022
Abstract
In this paper, an AgileDARN (Agile Dual Auroral Radar Network) radar echo classification method based on support vector machine is proposed. AgileDARN radar echo includes ionospheric backscattering echo, meteor echo, noise interference, etc. With the continuous operation of AgileDARN radar, the amount of data increases rapidly, requiring efficient and reliable classification methods. In order to efficiently classify the echoes of AgileDARN radar, this paper proposes an echo classification method based on support vector machine. By analyzing the characteristics of the autocorrelation function (ACF) of the sampled data and extracting the features, the support vector machine(SVM) classification method is adopted to classify AgileDARN echo into ionospheric backscattering echo, meteor echo and noise interference. The data analysis shows that the classification accuracy of training data set is more than 99%, and that of test data set is more than 95%. Using this classification model to classify 1800 echo data of AgileDARN radar, the classification accuracy is more than 91% compared with the result of manual interpretation.
Citation
Guangming Li , "AgileDARN Radar Echo Automatic Classification Algorithm Using Support Vector Machine," Progress In Electromagnetics Research Letters, Vol. 103, 151-160, 2022.
doi:10.2528/PIERL22011807
http://www.jpier.org/PIERL/pier.php?paper=22011807
References

1. Greenwald, R. A., et al., "Darn superdarn --- A global view of the dynamics of high-latitude convection," Space Science Reviews, Vol. 71, No. 1-4, 761-796, 1995.
doi:10.1007/BF00751350

2. Ribeiro, A. J., et al., "A comparison of SuperDARN ACF tting methods," Radio Science, Vol. 48, No. 3, 274-282, 2013.
doi:10.1002/rds.20031

3. Greenwald, R. A., et al., "An HF phased-array radar for studying small-scale structure in the high-latitude ionosphere," Radio Science, Vol. 20, 63-79, 1985.
doi:10.1029/RS020i001p00063

4. Berngardt, O. I., et al., "Attenuation of decameter wavelength sky noise during X-ray solar ares in 2013{2017 based on the observations of midlatitude HF radars," Journal of Atmospheric and Solar-Terrestrial Physics, Vol. 173, 1-13, 2018.
doi:10.1016/j.jastp.2018.03.022

5. Ruohoniemi, J. M., et al., "Coherent HF radar backscatter from small-scale irregularities in the dusk sector of the subauroral ionosphere," Journal of Geophysical Research-Space Physics, Vol. 93, No. A11, 12871-12882, 1988.
doi:10.1029/JA093iA11p12871

6. Milan, S. E., et al., "Initial backscatter occurrence statistics from the CUTLASS HF radars," Annales Geophysicae-Atmospheres Hydrospheres and Space Sciences, Vol. 15, No. 6, 703-718, 1997.

7. Hall, G. E., et al., "Super dual auroral radar network observations of meteor echoes," Journal of Geophysical Research-Space Physics, Vol. 102, No. A7, 14603-14614, 1997.
doi:10.1029/97JA00517

8. Hussey, G. C., et al., "A comparison of Northern Hemisphere winds using SuperDARN meteor trail and MF radar wind measurements," Journal of Geophysical Research- Atmospheres, Vol. 105, No. D14, 18053-18066, 2000.
doi:10.1029/2000JD900272

9. Hibbins, R. E., M. P. Freeman, S. E. Milan, and J. M. Ruohoniemi, "Winds and tides in the mid-latitude Southern Hemisphere upper mesosphere recorded with the Falkland Islands SuperDARN radar," Annales Geophysicae, Vol. 29, No. 11, 1985-1996, 2011.
doi:10.5194/angeo-29-1985-2011

10. Baker, K. B. and R. A. Greenwald, "The vertical angle of arrival of highfrequency signals propagating from thule to goose bay," Johns Hopkins APL Technical Digest, Vol. 9, No. 2, 121-130, 1988.

11. Chisham, G. and M. Pinnock, "Assessing the contamination of SuperDARN global convection maps by non-F-region backscatter," Annales Geophysicae, Vol. 20, No. 1, 13-28, 2002.
doi:10.5194/angeo-20-13-2002

12. Andre, R., M. Pinnock, J. P. Villain, and C. Hanuise, "Influence of magnetospheric processes on winter HF radar spectra characteristics," Annales Geophysicae, Vol. 20, No. 11, 1783-1793, 2002.
doi:10.5194/angeo-20-1783-2002

13. Blanchard, G. T., S. Sundeen, and K. B. Baker, "Probabilistic identification of high-frequency radar backscatter from the ground and ionosphere based on spectral characteristics," Radio Science, Vol. 44, No. 5, 1-9, 2009.
doi:10.1029/2009RS004141

14. Berngardt, O. I., A. L. Voronov, and K. V. Grkovich, "Optimal signals of Golomb ruler class for spectral measurements at EKB SuperDARN radar: Theory and experiment," Radio Science, Vol. 50, No. 6, 486-500, 2015.
doi:10.1002/2014RS005589

15. Barthes, L., R. Andre, J. C. Cerisier, and J.-P. Villain, "Separation of multiple echoes using a high-resolution spectral analysis for SuperDARN HF radars," Radio Science, Vol. 33, No. 4, 1005-1017, 1998.
doi:10.1029/98RS00714

16. Liu, E. X., et al., "An adjusted location model for SuperDARN backscatter echoes," Annales Geophysicae, Vol. 30, No. 12, 1769-1779, 2012.
doi:10.5194/angeo-30-1769-2012

17. Ribeiro, A. J., et al., "A new approach for identifying ionospheric backscatter in midlatitude SuperDARN HF radar observations," Radio Science, Vol. 46, No. 4, 2011.
doi:10.1029/2011RS004676

18. Lavygin, I. A., et al., "Identifying ground scatter and ionospheric scatter signals by using their ne structure at Ekaterinburg decameter coherent radar,", Cornell University Library, Ithaca, 2018.

19. Matthews, D. M., et al., "Optimising estimates of mesospheric neutral wind using the TIGER SuperDARN radar," Advances in Space Research, Vol. 38, No. 11, 2353-2360, 2006.
doi:10.1016/j.asr.2005.07.046

20. Yukimatu, A. S. and M. Tsutsumi, "A new SuperDARN meteor wind measurement: Raw time series analysis method and its application to mesopause region dynamics," Geophysical Research Letters, Vol. 29, No. 20, 2002.
doi:10.1029/2002GL015210

21. Tsutsumi, M., et al., "Advanced SuperDARN meteor wind observations based on raw time series analysis technique," Radio Science, Vol. 44, No. 2, 1-11, 2009.
doi:10.1029/2008RS003994

22. Parris, R. T., "Design and implementation of a meteor tracking retro t system for the HF radar at Kodiak Island, Alaska,", 110, University of Alaska Fairbanks, Ann Arbor, 2003.

23. Song, J., et al., "Analysis of FPGA implementation for AgileDARN radar digital system," Remote Sensing Technology and Application, Vol. 32, No. 6, 1064-1070, 2017.

24. Farley, D. T., "Multiple-pulse incoherent-scatter correlation function measurements," Radio Science, Vol. 7, No. 6, 661-666, 1972.
doi:10.1029/RS007i006p00661

25. Hanuise, C., R. A. Greenwald, and K. B. Baker, "Drift motions of very high latitude F region irregularities: Azimuthal Doppler analysis," Journal of Geophysical Research, Vol. 90, No. A10, 1985.
doi:10.1029/JA090iA10p09717

26. Baker, J. B., et al., "spectral characteristics of high frequency backscatter from high latitude ionospheric irregularities | Preliminary analysis of statistical properties," Interim Rep., RADC-TR-87-284, Rome Air Dev. Cent., Briffis Air Force Base, 1988.

27. Cristianini, J. S.-T. N., An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, 2000.
doi:10.1017/CBO9780511801389

28. Burges, C. J., "A tutorial on support vector machines for pattern recognition," Data Mining Knowledge Discovery, 1998.