Authors D.A. Bespalov
Month, Year 05, 2017 @en
Index UDC 004.067
Abstract This article describes the way in which time series of parameters of information systems are processed when detecting anomalies in the work of wavelet analysis methods. This task is relevant in connection with the need to develop and implement adaptive methods for analyzing the security of information systems in real time for the timely prevention of various threats. The proposed method for processing time series is intended for application in complex approaches to analyzing the security of information systems using plastic cards for pre-processing for the purpose of noise reduction, highlighting the peculiarities and characteristic features of data sequences, and im-proving the efficiency of methods for recognizing behavior anomalies which work with the results of the proposed algorithm. In contrast to the existing approaches, herein used is the approach that involves a multiscale representation of time series and allows one to distinguish its specific char-acteristics inherent in different levels of signal representation. Further processing is performed based on the wavelet maxima of the signal decomposition, which exist in a number of scales of the representation and reveal regular features appearing at most levels of the multiscale analysis. Also, in this paper, we propose a method for the optimal calculation of the threshold for processing wavelet coefficients in the stage of noise reduction based on the statistical analysis of time series and determining the balance between the level of useful signal and the noise level, and these calculations are performed directly in the basis of the wavelet coefficients. Moreover, in the algorithmic and computational plan, the proposed method is more advantageous, since it relies on a limited set of computational operations associated with a hierarchy of quadrature-mirror filters having a regular computational structure, that is, independent of the signal size and the level of its decomposition in the basis of wavelet coefficients. The proposed algorithms are well implemented both at the software and hardware level due to natural parallelism and are symmetric in the computational plan due to the same complexity of all branches of the algorithm.

Download PDF

Keywords Anomaly of behavior; analysis; plastic card; information system; time series; weilvt analysis.
References 1. Malla S. Veyvlety v obrabotke signalov [Wavelets in signal processing]. Moscow: Mir, 2005, 672 p.
2. Polovinkin E.S., Balashov M.V. Elementy vypuklogo i sil'no vypuklogo analiza [Elements of convex and strongly convex analysis]. Moscow: Fizmatlit, 2004, 416 p.
3. Bozhokin C., Parshin D. Fraktaly i mul'tifraktaly [Fractals and multifractal]. Izhevsk, 2001, 128 p.
4. Van De Ville D., Nachtegael M, Van der Weken D, Kerre E.E., Philips W., Lemahieu I. Noise Reduction by Fuzzy Image Filtering, IEEE Transaction on fuzzy system, August 2003, Vol. 11, No. 4.
5. Harten A. Discrete Multi-Resolution Analysis and Generalized Wavelets, J. App. Num. Math.,1993, Vol. 12, pp. 153-193.
6. Ali Akansu and Richard Haddad. Multiresolution Signal Decomposition: Transforms, Subbands, Wavelets, Academic Press, 1992.
7. Tony F. Chan and "Jackie (Jianhong) Shen". Image Processing and Analysis – Variational, PDE, Wavelet, and Stochastic Methods, Society of Applied Mathematics.
8. Ingrid Daubechies. Ten Lectures on Wavelets, Society for Industrial and Applied Mathematics, 1992.
9. Ramazan Gençay, Faruk Selçuk and Brandon Whitcher. An Introduction to Wavelets and Other Filtering Methods in Finance and Economics, Academic Press, 2001.
10. Percival Donald B. and Walden Andrew T. Wavelet Methods for Time Series Analysis, Cam-bridge University Press, 2000.
11. Mladen Victor Wickerhauser. Adapted Wavelet Analysis From Theory to Software, A K Peters Ltd, 1994.
12. Martin Vetterli and Jelena Kovačević. Wavelets and Subband Coding. Prentice Hall, 1999.
13. Xia T. and Jiang Q. Optimal multifilter banks: design, related symmetric extension transform, and application to image compression, IEEE Trans. Signal Process, 1999, Vol. 47,
pp. 1878-1889.
14. Zhang J.-K., Davidson T.N., Luo Z.-Q., and Wong K.M. Design of interpolating biorthogonal multiwavelet systems with compact support, Appl. Comput. Harmon. Anal., 2001, No. 11,
pp. 420-438.
15. Tian J. and Wells R.O. Jr. An algebraic structure of orthogonal wavelet space, Appl. Comput. Harmon. Anal., 2000, No. 8, pp. 223-248.
16. Bespalov D.A. Parallel'naya realizatsiya algoritmov veyvlet-analiza na mnogoprotsessornykh klasterakh [Parallel implementation of algorithms for wavelet analysis on multiprocessor clus-ters], Izvestiya vysshikh uchebnykh zavedeniy. Severo-Kavkazskiy region. Seriya: Tekhnicheskie nauki [University News. North-Caucasian Region. Technical Sciences Series], 2007, No. 1, pp. 11-14.
17. Bespalov D.A. Veyvlet-fil'tratsiya signalov adaptivnymi porogami [Wavelet filtering of sig-nals and adaptive thresholds], Izvestiya vysshikh uchebnykh zavedeniy. Severo-Kavkazskiy region. Seriya: Tekhnicheskie nauki [University News. North-Caucasian Region. Technical Sciences Series], 2007, No. 2, pp. 13-15.
18. Veitch D. & Abry P. A wavelet-based joint estimator of the parameters of long-range depend-ence, IEEE Trans. Info. Theo., 1999, Vol. 45, pp. 878-897.
19. Paladin G. & Vulpiani A. Anomalous scaling laws in multifractal objects, Phys. Rep., 1987, Vol. 156, pp. 147-225.
20. Muzy J.-F., Bacry E. & Arneodo A. Wavelets and multifractal formalism for singular signals: Application to turbulence data, Phys. Rev. Lett., 1991, Vol. 67, pp. 3515-3518.

Comments are closed.