Method of Detection Abnormal Features in Ionosphere Critical Frequency Data on the Basis of Wavelet Transformation and Neural Networks Combination

O. V. Mandrikova, Yu. A. Polozov, V. V. Bogdanov, E. A. Zhizhikina

Institute of Cosmophysical Researches and Radio Wave Propagation FEB RAS, Petropavlovsk-Kamchatskij, Russia.
Institute of Cosmophysical Researches and Radio Wave Propagation FEB RAS, Petropavlovsk-Kamchatskij, Russia; Kamchatka State Technical University, Petropavlovsk-Kamchatskij, Russia..
Institute of Cosmophysical Researches and Radio Wave Propagation FEB RAS, Petropavlovsk-Kamchatskij, Russia; Kamchatka State Technical University, Petropavlovsk-Kamchatskij, Russia.
Kamchatka State Technical University, Petropavlovsk-Kamchatskij, Russia.

DOI: 10.4236/jsea.2012.512B035                

Abstract

The research is focused on the development of automatic detection method of abnormal features, that occur in recorded time series of ionosphere critical frequency fOF2 during periods of high solar or seismic activity. The method is based on joint application of wavelet-transformation and neural networks. On the basis of wavelet transformation algorithms for the detection of features and estimation of their parameters were developed. Detection and analysis of characteristic components of time series are performed on the basis of joint application of wavelet transformation and neural networks. Method's approbation is performed on fOF2 data obtained at the observatory “Paratunka” (Paratunka settlement, Kamchatskiy Kray).

Keywords

wavelet transformation, neural networks, critical frequency of ionosphere, abnormalities, earthquakes

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	M.G. Dyomin, “Ionosphere of the Earth. Plasma Helio-physics,” PhysMathlit, Moscow, 2008.
[2]	V.V. Bogdanov, V.V. Geppener and O.V. Mandrikova, “Modeling of Non-Stationary Time Series of Geophysical Parameters with a Complex Structure,” St.-Petersburg, 2006.
[3]	O. V Mandrikova, Yu.A. Polozov and A.S. Perezhogin, “Wavelet-Technology of the Ionospheric Data Analysis,” Scientific Notes of the Belgorod State University, a Series "History. Political Science. Economy. Computer Science", Belgorod, No. 19, 2011, pp. 113-118.
[4]	O. V Mandrikova and Yu.A. Polozov, “Criteria of Wavelet-Function Choice in Problems of Approximation Natural Time Series of Complex Struc-ture,” Information Technology, Moscow, No. 1, 2012, pp. 31 - 36.
[5]	O. V. Mandrikova, “Multicomponent Mod-el of a Signal with Complex Structure,” Problems of Evolution of Open Systems, Issue 10, Vol. 2, 2008, pp.161-172.
[6]	Yu. A. Polozov, “Method of Training Set Formation for a Neural Network on the Basis of a Wavelet-Filtration,” News of High Schools, the North Caucasian Region, a Series Natural Sciences, No. 3, 2010, pp. 12-16.
[7]	E.V. Liperovskaja, V. А. Lipe-rovsky and O. A. Pokhotelov, “About Disturbances in Ionosphere F-Area before Earthquakes,” Geophysical researches, No. 6, 2006, pp. 51-58.
[8]	A. A. Namga-ladze, “The Physical Mechanism and Mathematical Modeling of Ionospheris Harbingers of the Earthquakes Recorded in Full Electronic Maintenance,” Geomagnet-ism and Aeronomia, Vol. 49, No. 2, -2009, pp. 267-277.
[9]	O. V. Mandrikova, Yu. A. Polozov and T. L. Zaliaev, “Methods of Analysis and Interpretation of Ionospheric Critical Frequency FOf2 Data Based on Wavelet Transform and Neural Networks,” European Seismological Commission 33-rd General Assembly (GA ESC 2012), 19-24 August 2012, Thesis, Moscow.
[10]	Y. Polozov, O. Mandrikova and V. Bogdanov, “Detection of Anomalies in Ionospheric Increased Seismic Activity,” International Union of Geodesy and Geophysics (IUGG), 28 June – 07 July 2011, Thesis, Melbourne.
[11]	O. V Mandrikova, Yu. A. Polozov, N.V. Glushkova and T.L. Zalyaev, “Technology of Allocation of Anomalies in Ionospheric Data on the Basis of Combination Wavelet-Transformation and Neural Networks,” International Conference ?Intelligent Information Processing? (IIP-2012), Montenegro, Budva,16-22 September 2012, pp. 524-527.
[12]	O. V Mandrikova and Yu. A. Polozov, "Method of Allocation and Classifi-cation of Anomalies in Ionospheric Parameters on the Basis of Combination of Wavelet-Transformation and Neural Networks," 14 International Conference ?Digital Signal Procssing? (DSPA - 2012), Moscow, 28-30 March 2012, pp. 353-356.
[13]	O.V. Mandrikova, ‘Optimization of a Neural Network Training Procession on The Basis of Application of a Design of Wavelet-Transformation (on an Example of Modeling Ionospheric Signal Representa-tion),” Automation and Modern Technologies, No. 3, 2009, pp.14-17.
[14]	S. Mallat, “A Wavelet Tour of Signal Processing,” World, Moscow, 2005.
[15]	O. V. Mandrikova, I. S. Solovjev, V. V. Geppener and D. M. Klionskiy, “Analyzing Subtle Features of Natural Time Series by Means of a Wavelet–Based Approach,” Pattern Recognition and Image Analysis, Vol. 22, No. 2, 2012, pp. 323–332. doi:10.1134/S1054661812020083
[16]	O.V. Mandrikova , I.S. Solovyev, V.V.Geppener, D.M. Klionskiy and R. T. Al-Kasasbeh, “Analysis of the Earth's magnetic field variations on the basis of a wavelet-based approach,” Digital Signal Processing, In Press.
[17]	C. K. Chui and J. Z. Wang, “A general framework of compactly supported splines and wavelets,” CAT Report 219, Texas A&M Univ., 1990.
[18]	Ali G. Hafez and Essam Ghamry, “Automatic detection of geomagnetic sudden Commencements via Time Frequency Clusters,” Ad-vances Space Research, Vol. 48, Issue 9, 2011, pp. 1537–1544. doi:10.1016/j.asr.2011.05.025
[19]	Ali G. Hafez, Tahir A. Khan and T. Kohda, “Clear P-wave Ar-rival of Weak Events and Automatic Onset Determination Using Wavelet Filter Banks,” Digital Signal Processing, Vol. 20, Issue 3, 2010, pp. 715-723. doi:10.1016/j.dsp.2009.10.002
[20]	D. B. Percival and A. T. Walden, “Wavelet Methods for Time Series Analysis,” (Cambridge Series in Statistical and Probabilistic Ma-thematics), Cambridge University Press, 2000.
[21]	A.D. Ageev, “Neuromatematika: Studies. The Grant for High Schools,” IPRJR, Moscow, 2002.
[22]	H.A. Barhatov and C.E. Revunov, “Forecasting of Critical Frequency Ionospheric Layer F2 a Method of Artificial Neural Networks,” VIII Nizhniy Novgorod Session of Young Scientists. Natural-Science Disciplines, Thesis, Dzerz-hinsk, 2003.
[23]	H.A. Barhatov, C.E. Revunov and V.P. Urjadov, “Technology of Artificial Neural Networks for Forecasting of Critical Frequency Ionospheric Layer F2,” News of HIGH SCHOOLS "Radio Physicists", Vol. 48, 2005, pp.1-15.
[24]	I. Daubechies, “Ten Lectures on Wavelets,” ?Regular and Chaotic Dynamics?, Izhevsk, 2001