Unlock instant, AI-driven research and patent intelligence for your innovation.

Underwater acoustic target classification method based on dual space optimization

A dual space, target classification technology, applied in instruments, character and pattern recognition, computer parts and other directions, can solve the problem of not considering the performance of support vector machines, and achieve the best classification and recognition rate.

Pending Publication Date: 2020-12-22
QINGHAI NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art, provide a dual-space-based optimal underwater acoustic target classification method, and solve the shortcomings of the existing research and analysis that do not consider the performance of the support vector machine itself

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
  • Underwater acoustic target classification method based on dual space optimization
  • Underwater acoustic target classification method based on dual space optimization
  • Underwater acoustic target classification method based on dual space optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following description.

[0030] The invention relates to a method for classifying underwater acoustic targets based on dual space optimization, which specifically includes the following contents:

[0031] Such as figure 1 As shown, consider the underwater acoustic sample set as S={(x, di)|x∈R n , d i ∈{1,-1}, i=1, 2,...,n} represents the feature set of the underwater target object. where n is the dimension of the underwater acoustic feature space, and at the same time it is stipulated that when x belongs to a metal cylinder, d i is 1, when x belongs to rock, d i is -1.

[0032] Using the support vector method to classify two types of underwater objects, the most important thing is to find a hyperplane that can separate the two types of underwater objects to the maximum extent, and get:

[0033]...

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 relates to an underwater acoustic target classification method based on dual space optimization. The classification method comprises the steps that hyperplane classification is conductedon two types of underwater objects through a support vector machine classifier, and the interval between sample points and a hyperplane is trained; and an original problem is converted into a dual problem, and a Lagrange dual space and a KKT constraint condition are combined to solve an optimal value. The method has the advantages that the recognition rate is better than that of a random forest classifier on the whole, and it is verified that the support vector machine using the dual space method has wide prospects in underwater target intelligent recognition. In the process of solving the optimal classification hyperplane of the support vector machine, the Lagrange space duality is used for solving the optimal solution of the secondary target function, and therefore the optimal classification hyperplane is obtained through solving. Under the linear separable constraint condition, the classification recognition rate of the support vector machine can be optimal.

Description

technical field [0001] The invention relates to the technical field of underwater acoustic target intelligent recognition, in particular to an underwater acoustic target classification method based on dual space optimization. Background technique [0002] Intelligent underwater target recognition technology is mainly used in military intrusion monitoring, submarine resource development, fish positioning and protection and other fields. Due to the complexity of the water's own environment (such as acoustic medium constraints and heterogeneity), the diversity of recognition targets, and the difficulty of obtaining underwater target signals (such as sensitive equipment data such as military ships), the difficulties encountered in intelligent recognition of underwater targets are far greater Much higher than other object recognition. The main research direction of underwater acoustic target recognition is the statistical recognition method based on underwater acoustic signal an...

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
IPC IPC(8): G06K9/62
CPCG06F18/2411G06F18/214
Inventor 杜秀娟姚路
Owner QINGHAI NORMAL UNIV