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

Quantized signal reconstruction method based on deep learning and angle of arrival estimation method

A technology of signal reconstruction and deep learning, applied in the direction of physical parameter compensation/prevention, radio transmission system, biological neural network model, etc., can solve the problems of narrow application range and high complexity, reduce cost, reduce network complexity, and apply scene-wide effects

Active Publication Date: 2020-10-27
SOUTHEAST UNIV +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention can be used to solve the deficiencies in the prior art, provides a quantitative signal reconstruction method based on deep learning, solves the problems of high complexity and narrow application range in the existing methods, and achieves Better signal reconstruction level

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
  • Quantized signal reconstruction method based on deep learning and angle of arrival estimation method
  • Quantized signal reconstruction method based on deep learning and angle of arrival estimation method
  • Quantized signal reconstruction method based on deep learning and angle of arrival estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0046] In order to eliminate the quantization noise and reduce the cost of the multi-channel system, the present invention designs a quantization signal reconstruction method based on deep learning, which aims to fully learn the quantization noise structure, and the quantization signal is used as the input of the neural network. Through the training of the neural network, Finally, the reconstructed signal is output, which effectively reduces the requirement of the multi-channel system on the accuracy of the analog-to-digital converter.

[0047] The quantitative signal reconstruction method based on deep learning of the present invention, such as figure 1 shown, including the following steps:

[0048] Step 1: Construct the array model of the received signal;

[0049] Such as figure 2 As shown, by analyzing the received signals of each antenna, the received si...

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 quantized signal reconstruction method based on deep learning and an angle of arrival estimation method. The quantized signal reconstruction method based on deep learning comprises the following steps: establishing a signal model applied to an antenna array; constructing quantized noise models generated by analog-to-digital converters with different number of bits, and applying the noise models to an original signal model to generate a quantized signal; and constructing a neural network model based on deep learning, the network model taking the quantized signal as aninput and outputting a reconstructed signal with the quantized noise removed. The neural network model generally includes an input layer, an output layer, and a plurality of hidden layers. By trainingand learning the neural network, effective reconstruction of the quantized signal under the condition of low complexity can be finally realized.

Description

technical field [0001] The invention relates to a quantitative signal reconstruction method based on deep learning, which belongs to the technical field of array signal processing. Background technique [0002] In large-scale MIMO systems and new smart reflector systems, a large number of antennas and radio frequency channels are often equipped. Reducing the cost of radio frequency links is very important for multi-channel systems. For the above system, it is hoped to remove the quantization noise brought by the analog-to-digital converter as much as possible so as to improve the accuracy of channel estimation and angle-of-arrival estimation, and at the same time, it is hoped to reduce the cost of the analog-to-digital converter. Commonly used methods to remove quantization noise include increasing the sampling rate, rebuilding the covariance matrix, and changing the array configuration. Although the increase in sampling rate can effectively remove quantization noise, the c...

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): H03M1/08G06N3/04H04B7/0413
CPCH03M1/0854H04B7/0413G06N3/045Y02D30/70
Inventor 陈鹏韩蔚峰曹振新
Owner SOUTHEAST UNIV
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