基于最小二乘支持向量機(jī)的衰落信道預(yù)測(cè)算法

相征; 張?zhí)?/>
	<meta name=

基于最小二乘支持向量機(jī)的衰落信道預(yù)測(cè)算法

孫建成

計(jì)量
- 文章訪問數(shù): 2299
- HTML全文瀏覽量: 82
- PDF下載量: 985
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2005-06-24
- 修回日期: 2006-01-11
- 刊出日期: 2006-04-19

Prediction Algorithm for Fast Fading Channels Based on Recurrent Least Squares Support Vector Machines

摘要

摘要: 該文探討了利用相空間重構(gòu)和支持向量機(jī)進(jìn)行衰落信道非線性預(yù)測(cè)算法。該算法基于多徑衰落信道具有混沌行為，利用坐標(biāo)延遲理論，重建衰落信道系數(shù)的相空間，再根據(jù)混沌吸引子的穩(wěn)定性和分形性，在相空間中通過遞歸最小二乘支持向量機(jī)(RLS-SVM)進(jìn)行預(yù)測(cè)。該算法對(duì)原始數(shù)據(jù)可以進(jìn)行更平滑的處理，在噪聲環(huán)境下預(yù)測(cè)的時(shí)間范圍更長。對(duì)時(shí)間跨度為63.829ms的衰落系數(shù)進(jìn)行了預(yù)測(cè)，仿真結(jié)果表明，在信噪比為15dB時(shí)，預(yù)測(cè)結(jié)果優(yōu)于AR算法。
- 衰落信道;信道預(yù)測(cè);支持向量機(jī);混沌吸引子
Abstract: An new method for fast fading channel prediction using Recurrent Least Squares Support Vector Machines (RLS-SVM) combined with reconstructed embedding phase space is investigated. This algorithm is based on the chaotic behavior of the mobile multipath fading channel.The phase space of these mobile multipath fading channel coefficients are reconstructed by the theory of time delays. Based on the stability and the fractal of the chaotic attractor, the fast fading channel coefficients are predicted in their phase space based on the RLS-SVM.The proposed algorithm is a better candidate for long range prediction of the fading channel in the noise context . The experiment is carried out by utilizing fading channel data which spanes 63.829 ms. The simulation results show that the better prediction performance is acquired than the AR method when the signal to noise ratio is 15dB.

HTML全文

參考文獻(xiàn)(1)

胡剛, 朱世華, 謝波. 基于混沌、分形理論的多徑衰落分析[J].電子學(xué)報(bào)，2003，31(7): 1039-1042.[2]Tannous C, Davies R, Angus A. Strange attractors in multipath propagation [J].IEEE Trans. on Comm.1991, 39(5):629-631[3]Eyceoz T, Duel-Hallen A, Hallen H. Prediction of fast fading parameters by resolving the interference pattern. Proceedings of the 31st ASILOMAR Conference on Signals, Systems, and Computers[C]. Pacific Grove, CA, 1997: 167-171.[4]Ekman T, Kubin G.Nonlinear prediction of mobile radio channels: Measurements and MARS model designs, In Proc. Int. Conf. Acoust. Speech Sig. Process[C]. Phoenix, AZ, March 1999: 2667-2670.[5]Gao X M, Tanskanen J M A, Ovaska S J. Comparison of linear and neural network-based power prediction schemes for mobile DS/CDMA systems.VTC96[C]. Atlanta: IEEE press,1996: 61-65.[6]Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer, 1995: 91-108.[7]Wang L P(Ed.). Support Vector Machines: Theory and Application[M]. New York, Berlin, Heidelberg: Springer, 2005: 51-123.[8]Vapnik V. The Nature of Statistical Learning Theory[M]. Translated by Zhang Xuegong. Beijing: Tsinghua University Press, 2000: 91-108.[9]Suykens J A K, Vandewalle J. Least squares support vector machines[J].Neurel Processing Letters.1999, 9(3):293-300[10]Suykens J A K, Vandewalle J. Recurrent least squares support sector machines[J].IEEE Trans. on Circuits and System-I: Fundamental Theory and Applications.2000, 47(7):1109-1114[11]Takens F . Detecting strange attractors in fluid turbulence. In D. Rand and L.S.Young, editors, Dynamical systems and Turbulence [M]. Berlin: Springer-Verlag, 1981: 366-381.[12]Jakes W C. Microwave Mobile Communications[M]. Piscataway, USA: IEEE Press, 1974, chapter1: 13-77.[13]Cao L. Practical method for determining the minimum embedding dimension of a scalar time series[J].Physcai D.1997, 110(7):43-50[14]Grassberger P, Procaccia I. Characterization of strange attractors[J].Physical Review Letters.1983, 50(5):346-349[15]Wolf A, Swift J B, Swinney H L. Determining Lyapunov exponents from a time series[J].Physica D.1985, 16(2):285-317

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)