Trimmed Mean-based Automatic Censoring and Detection in Pareto background

Mehanaoui, Ali; Laroussi, Toufik; Chabbi, Souad; Mezache, Amar

doi:10.1109/intee.2015.7416798

Cited by 5 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in order to improve the switching algorithm of the PI‐CFAR, it is possible to extent the automatic censoring procedure introduced in [37 and references therein] to the TM‐CFAR detector with a priori unknown scale parameter and an unknown number of interfering targets and unknown of the clutter position.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

“…It is mainly based on the set of CFAR detectors introduced in Section 2, in which the detector selection is governed by the statistical tests performed on the PI and the LGMR. Note that when both reference sub‐windows include interfering targets, the

X_{i} normals

can also be rank‐ordered to get the

X_{()(, i)}, i = 1, \dots, N

, to be eventually treated by the TM‐CFAR detector [30, 37].…”

Section: Pi‐based Cfar Processormentioning

confidence: 99%

See 1 more Smart Citation

Pietra index based processor for a heterogeneous Pareto background

Mehanaoui

Laroussi

Mezache

2019

IET Radar, Sonar & Navigation

Self Cite

View full text Add to dashboard Cite

This study addresses the problem of automatic target detection in a heterogeneous Pareto background. To achieve this, the Pietra index based and constant false alarm rate processor (CFAR) is conceived. Specifically, assuming a nonstationary Pareto background with the presence or not of any clutter edge or interfering targets, the Pietra index and the log geometric mean ratio statistic tests are concomitantly used to allow the proposed processor to switch dynamically to the appropriate detector; i.e. the geometric mean-CFAR, the greatest of-CFAR or the trimmed mean-CFAR, where all of these detectors assume a priori unknown scale parameter. That is, according to the outcomes of the Window Selection Probability, the background level is systematically estimated through the preselected detector. The detection performances of the proposed processor are assessed, via Monte Carlo simulations, in multiple target and clutter edge situations.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

X_{i} normals

can also be rank‐ordered to get the

X_{()(, i)}, i = 1, \dots, N

, to be eventually treated by the TM‐CFAR detector [30, 37].…”

Section: Pi‐based Cfar Processormentioning

confidence: 99%

Pietra index based processor for a heterogeneous Pareto background

Mehanaoui

Laroussi

Mezache

2019

IET Radar, Sonar & Navigation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Contour Ω (solid line) of complex integral in (14) in comparison with contour Ω (dashed line) adopted in [30].…”

Section: Derivation Via Characteristic Functionmentioning

confidence: 99%

“…Similarly, the right-censored Pareto distribution is more adequate to represent observations that can incur in saturation or clipping effects, hence accumulate at the upper edge of the data range. Such more physicallyplausible Pareto distributions with bounded support have indeed attracted interest in recent years, as numerous evidence shows their suitability to model the statistical behaviour of phenomena arising in radar detection [14,15], modelling of communication network [16], survival analysis [17], hydrology and atmospheric science [18,19], and natural systems at large [20].…”

Section: Introductionmentioning

confidence: 99%

On the Sum of Random Samples with Bounded Pareto Distribution

Grassi¹,

Coluccia²

2021

Preprint

View full text Add to dashboard Cite

Heavy-tailed random samples, as well as their sum or average, are encountered in a number of signal processing applications in radar, communications, finance, and natural sciences. Modeling such data through the Pareto distribution is particularly attractive due to its simple analytical form, but may lead to infinite variance and/or mean, which is not physically plausible: in fact, samples are always bounded in practice, namely because of clipping during the signal acquisition or deliberate censoring or trimming (truncation) at the processing stage. Based on this motivation, the paper derives and analyzes the distribution of the sum of right-censored Pareto Type-II variables, which generalizes the conventional Pareto (Type-I) and Lomax distributions. The distribution of the sum of truncated Pareto is also obtained, and an analytical connection is drawn with the unbounded case. A numerical analysis illustrates the findings, providing insights on several aspects including the intimate mixture structure of the obtained expressions.

show abstract