Abstract | ||
---|---|---|
Currently there is contention as to the nature of sea clutter for high resolution radar. Conventionally, sea clutter has been modelled as a compound stochastic k-distribution, originally suggested by Ward et al. However, recent work by Haykin et al. has suggested that the clutter can be modelled as a nonlinear deterministic process, otherwise referred to as a chaotic process. The paper presented here uses a new surrogate test which is designed specifically for this problem. The test is designed with a null hypothesis (H0= The data can be approximated to by a compound stochastic k-distribution). Therefore, acceptance of such a test will accept the conventional k-distribution as a viable model sea clutter. In addition, a new surrogate statistic is introduced which is used to reject/accept the null hypothesis. This statistic is the normalised mean square error(NMSE) from a predictor and is a statistic which can be applied to any type of time-series. An overview of the method is presented together with results for a number a sea clutter data sets. |
Year | DOI | Venue |
---|---|---|
2000 | 10.5281/zenodo.37575 | EUSIPCO |
Keywords | Field | DocType |
chaos,mean square error methods,radar clutter,radar resolution,statistical distributions,statistical testing,stochastic processes,nmse,chaotic process,compound stochastic k-distribution,high resolution radar,improved surrogate-data tests,nonlinear deterministic process,normalised mean square error,null hypothesis,sea clutter data sets,time-series,white noise,clutter,speckle | Statistic,Null hypothesis,Clutter,Algorithm,Mean squared error,White noise,Deterministic system,Constant false alarm rate,Statistics,Surrogate data,Mathematics | Conference |
ISBN | Citations | PageRank |
978-952-1504-43-3 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bernard Mulgrew | 1 | 639 | 89.00 |
Charles P Unsworth | 2 | 14 | 7.47 |
Mark R. Cowper | 3 | 3 | 1.31 |
Stephen McLaughlin | 4 | 168 | 16.62 |