Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Single-bit Spatial Spectrum Estimation Method Based on Support Vector Machine

A space spectrum estimation and support vector machine technology, applied in the field of support vector machines, can solve problems such as large amount of calculation and poor accuracy, and achieve the effects of low requirements, reduced cost and complexity, and good angle estimation accuracy

Inactive Publication Date: 2019-02-22
HARBIN INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem that the traditional spatial spectrum estimation algorithm not only has a large amount of calculation, but also has poor precision in the case of single-bit extreme quantization and ultra-large-scale antenna arrays

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
  • A Single-bit Spatial Spectrum Estimation Method Based on Support Vector Machine
  • A Single-bit Spatial Spectrum Estimation Method Based on Support Vector Machine
  • A Single-bit Spatial Spectrum Estimation Method Based on Support Vector Machine

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0055] Specific implementation mode one: see figure 1 Describe this embodiment mode, a kind of single-bit spatial spectrum estimation method based on logistic regression described in this embodiment mode, this method comprises the following steps:

[0056] Step 1: Construct a sample training model according to the single-bit received data;

[0057] Step 2: For the input and output of the construction sample training model, use the support vector machine algorithm to calculate the classification coefficient vector t, where t=[t 1 ,t 2 ,...,t i ,...,t 2m ] T ;

[0058] Step 3: According to the classification coefficient vector t and the following formula 1:

[0059] S i = t i +j×t i+m(Formula 1);

[0060] Obtain the spatial spectrum S=[S 1 ,S 2 ,...,S m ] T , so as to complete the estimation of the spatial spectrum S;

[0061] Among them, i and m are both integers, t i is the ith component of the classification coefficient vector t, t i+m is the i+mth component ...

specific Embodiment approach 2

[0071] Specific implementation mode two: see figure 1 Describe this embodiment. The difference between this embodiment and the method for estimating a single-bit spatial spectrum based on a support vector machine described in the first embodiment is that in the first step, the sample training model is constructed according to the single-bit received data. The specific process is:

[0072] Step one, train the model on the original sample:

[0073]

[0074] Perform sparse representation and obtain the original sample training model after sparse representation:

[0075] x=FS (Formula 3),

[0076] Steps 1 and 2, perform single-bit quantization on the original sample training model after sparse representation, and obtain the model after single-bit quantization:

[0077]

[0078] In step 13, the single-bit quantized model is expressed in the real number domain as,

[0079] q=sign(Φt+e′) (Formula 5),

[0080] The single-bit quantized model is a sample training model constr...

specific Embodiment approach 3

[0101] Specific embodiment three: the difference between this embodiment and the single-bit spatial spectrum estimation method based on support vector machine described in specific embodiment one or two is that the output of the constructed sample training model is the observation vector q, and the constructed sample The input to the training model is the row of the flow pattern matrix Φ.

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 provides a single-bit spatial spectrum estimation method based on a support vector machine and relates to the field of support vectors in spatial spectrum estimation field and artificial intelligence in array signal processing. Problems of complicated calculation and quite low precision in conditions of single-bit extreme quantization and super-large scale antenna arrays are solved. The single-bit spatial spectrum estimation in a large-scale antenna array is modeled into a classification problem in artificial intelligence and the spatial spectrum of wave signals is solved by use of the support vector machine method. Compared with the traditional algorithm, the provided estimation method is advantageous in that estimation precision of the spatial spectrum is improved; the structure of a receiving machine is simplified; and angles of multiple signal resources can be simultaneously estimated. The estimation method is used for estimation of the spatial spectrums.

Description

technical field [0001] The invention relates to the field of space spectrum estimation in array signal processing and the field of support vector machine in artificial intelligence. Background technique [0002] In the fields of radar, communication, sonar, meteorology, etc., array signal processing has extensive and important applications. In array signal processing, spatial spectrum estimation is the basis for beamforming and other array signal processing algorithms. In the research of 5G mobile communication, massive MIMO has become a hot spot of attention. In the case of very large-scale antenna arrays, low-complexity and high-precision spatial spectrum estimation is the basis for other algorithm processing. When a real receiver performs direction finding processing, quantization processing will reduce the accuracy of the algorithm. The present invention considers the single-bit extreme quantization situation, that is, each array element only retains the symbol inform...

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 Patents(China)
IPC IPC(8): G01S7/41G01S3/14
CPCG01S3/14G01S7/41
Inventor 高玉龙胡德顺陈艳平许康马永奎
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com