摘要
使用自回归滑动平均(ARMA)和广义自回归条件异方差(GARCH)过程对金融数据建模是经济学常用手段。文中结合ARMA过程和GARCH过程的非线性化扩展模型,将其扩展到复数域,适合于海杂波建模应用。相比传统的海杂波模型及原始的GARCH模型,文中提出的模型在概率密度函数拟合上具有明显的优势。此外,新模型还可准确地捕获相邻海杂波中存在的强相关性。实际雷达海杂波数据验证了该模型的准确性和有效性。
Autoregressive moving-average( ARMA) process and generalized autoregressive conditional heteroskedasticity(GARCH) process are common tools for modeling financial data in economics. In order to make it suitable for modeling sea clutters,we combine the nonlinear expansion models of ARMA and GARCH,and extend it to the complex domain. Compared with the traditional sea clutter models and the original GARCH model,the proposed model has obvious advantages in probability density function fitting. Besides,the new model can accurately capture the strong correlation in adjacent sea clutters. Empirical studies on actual sea clutter data show the accuracy and effectiveness of our model.
引文
[1]WATTS A,GORDON A J.The searchwater family of airborne radars[C]//IEEE Radar 97.[S.l.]:IEEE Press,1997:334-338.
[2]SKOLNIK M I.An introduction to impulse radar[R].Naval Research Lab Report.Washington,DC:NASA Press,1990.
[3]TRUNK G V,GEORGE S F.Detection of targets in nonGaussian sea clutter[J].IEEE Transactions on Aerospace and Electronic Systems,1970,6(5):620-628.
[4]SEKINE M,MUSHA T,TOMITA Y,et al.Log-weibull distributed sea clutter[J].IEE Proceedings F-Communications,Radar and Signal Processing,1980,127(3):225-228.
[5]SANGSTON K J,GERLACH K R.Coherent detection of radar targets in a non-Gaussian background[J].IEEE Transactions on Aerospace and Electronic Systems,1994,30(2):330-340.
[6]CONTE E,LONGO M.Characterisation of radar clutter as a spherically invariant random process[J].IEEE Proceedings F-Communications Radar and Signal Processing,1987,134(2):191-197.
[7]FARSHCHIAN M,POSNER F L.The pareto distribution for low grazing angle and high resolution X-band sea clutter[J].IEEE Radar Conference,2010,29(16):789-793.
[8]HU J,TUNG W,GAO J.A new way to model nonstationary sea clutter[J].IEEE Signal Processing Letters,2009,16(2):129-132.
[9]GUNAN J,LIU N,HUANG Y,et al.Fractal poisson model for target detection within spiky sea clutter[J].IEEE Geoscience and Remote Sensing Letters,2013,10(2):411-415.
[10]GRECO M,BORDONI F,GINI F.X-band sea-clutter nonstationarity:influence of long waves[J].IEEE Journal of Oceanic Engineering,2004,29(2):269-283.
[11]PASCUAL J P,ELLENRIEDER N V,HURTADO M,et al.Radar detection algorithm for GARCH clutter model[J].Digital Signal Processing,2013,23(4):1255-1264.
[12]ZHANG Y,DENG Z,SHI J,et al.Sea clutter modeling using an autoregressive generalized nonlinear-asymmetric GARCH model[J].Digital Signal Processing,2017,62:52-64.
[13]LING S,LI W K.On fractionally integrated autoregressive moving-average time series models with conditional heteroscedasticity[J].Journal of the American Statistical Association,1997,92(439):1184-1194.
[14]NOCEDAL J,WRIGHT S J.Nurorical optimization[M].USA:Springer,2006.
[15]GINI F,GRECO M V,DIANI M,et al.Performance analysis of two adaptive radar detectors against non-Gaussian real sea clutter data[J].IEEE Transactions on Aerospare and Electronic Systems,2000,36(4):1429-1439.
[16]姜劲,陈希信,陈捷,等.基于特征的海面低速小目标检测工程算法[J].现代雷达,2017,39(1):48-50.JIANG Jin,CHEN Xixin,CHEN Jie,et al.A practical method for low speed small target detection wothin sen clutter based on target feature[J].Modern Radar,2017,39(1):48-50.
[17]SANGSTON K J,GINI F,GRECO M S.Coherent radar target detection in heavy-tailed compound-Gaussian clutter[J].IEEE Transactions on Aerospace and Electronic Systems,2012,48(1):64-77.