K distribution sea clutter shape parameter estimation method based on neural network

A shape parameter and neural network technology, applied in the field of signal processing, can solve problems such as difficulty in obtaining sea clutter data, and achieve high precision, good robustness, and high efficiency

Active Publication Date: 2017-10-13
XIDIAN UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to address the deficiencies of the prior art, to solve the problem of difficulty in obtaining independent and identically distributed samples of sea clutter data in the prior art, and to improve the estimation of the K distribution shape parameter when the number of samples is small and there are abnormal samples Accuracy, a neural network-based method for estimating shape parameters of K-distributed sea clutter

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • K distribution sea clutter shape parameter estimation method based on neural network
  • K distribution sea clutter shape parameter estimation method based on neural network
  • K distribution sea clutter shape parameter estimation method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Improving the accuracy of sea clutter shape parameter estimation in the presence of abnormal samples can better reflect the actual situation of sea conditions, reduce the false alarm rate and missed detection rate in sea clutter target detection, and improve detection performance. Efficient and fast estimation of sea clutter shape parameters under sample conditions is an urgent problem to be solved. The existing estimation methods estimate the sea clutter shape parameters by combining all the amplitude characteristics, ignoring the influence of abnormal samples. In view of this shortcoming, the present invention conducts research and discussion, and proposes a neural network-based K Distributed sea clutter shape parameter estimation method, see figure 1 , including the following steps:

[0029] (1) Acquisition of ideal pure sea clutter data: under the condition of ensuring power normalization, the simulation software is used to generate multiple sets of independent K-d...

Embodiment 2

[0040] The K distribution sea clutter shape parameter estimation method based on neural network is the same as embodiment 1, and step (1) acquires the ideal pure sea clutter data, including the following steps:

[0041] 1a) The probability density function ρ of the K distribution x Expressed as:

[0042]

[0043] Among them, v represents the shape parameter (v>0), b represents the scale parameter (b>0), K v (·) represents the v-order modified Bessel function of the second kind.

[0044] Get K distribution power E(x 2 )for:

[0045] E(x 2 ) = vb.

[0046] 1b) at In the case of , 10 groups of clutter samples are generated for each shape parameter with an interval of 0.01 and a range of 0.1-5, and the representation of the clutter sample sequence Z is as follows:

[0047]

[0048] in is the clutter sample sequence with a as the shape parameter and b as the group number, a(a=0.1,0.11,,5) represents the shape parameter, b(b=1,2,…,10) represents the group number, z ...

Embodiment 3

[0052] The K distribution sea clutter shape parameter estimation method based on neural network is the same as embodiment 1-2, and step (2) trains neural network, comprising the following steps:

[0053] 2a) The K distribution is used to simulate each group of amplitude sequences in the clutter data Sort the elements in the sequence from small to large to obtain multiple sets of sequence sequences, and divide the sequence sequence into 26 subsequences evenly. If the division cannot be performed accurately, the default element in the first subsequence is the least , and take the last element of each subsequence in the first 25 subsequences as the value of the quantile point, so that the magnitude values ​​of the 25 quantile points are taken in turn as the input of the neural network; the hidden layer is designed to be 50 nodes; the expectation The output is the shape parameter value a corresponding to the clutter sample group. Such a set of inputs and outputs constitutes a sa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a K distribution sea clutter shape parameter estimation method based on a neural network, and a problem of poor shape parameter estimation performance of an existing method in the condition of the presence of a small sample of an abnormal sample is mainly solved. The technical scheme comprises a step of generating K distribution power normalized sea clutter amplitude data of different shape parameters, a step of uniformly extracting multiple quantile amplitude values of the data as input and designing an appropriate neural network structure to train a large number of ideal data, a step of obtaining radar sea clutter data to carry out power normalization, and a step of applying an existing neural network and bringing the multiple quantile amplitude values of the data in to obtain a shape parameter estimation value. According to the method, partial sea clutter amplitude characteristics are used, through training the neural network, the shape parameter estimation performance in the condition of the presence of the small sample of the abnormal sample is improved, at the same time, the calculation of all data is not needed, and the efficiency of the method is much higher than that of a traditional method. The method is mainly applied to sea state exploration, target detection and other fields.

Description

technical field [0001] The invention belongs to the technical field of signal processing and relates to target detection, in particular to a neural network-based K-distribution sea clutter shape parameter estimation method, which can be used for effective and fast estimation of sea clutter shape parameters. Background technique [0002] Target detection technology under sea clutter background is a crucial research direction in radar application technology, and has been widely used in military and civilian fields. The accurate analysis of the statistical characteristics of sea clutter is an important factor for the target detection technology to achieve good results in the background of sea clutter. Therefore, proposing a suitable model and accurately estimating its model parameters when there are abnormal samples become an important guarantee for target detection. [0003] As an important model in the study of ground-sea clutter theory, the K distribution has obvious advant...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01S7/41
CPCG01S7/414G01S7/417
Inventor 水鹏朗芦凯曾威良
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap