Supercharge Your Innovation With Domain-Expert AI Agents!

A Deep Learning Signal Detection Method Based on Conjugate Gradient Descent

A technology of conjugate gradient and signal detection, applied in neural learning methods, transmission monitoring, biological neural network models, etc., can solve the problems of large computing resources, consumption, etc., and achieve simple network structure, shorten time, and reduce computational complexity Effect

Active Publication Date: 2020-11-24
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the MIMO scale is large, the large matrix inversion operation contained in the linear detector still consumes large computing resources

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 Deep Learning Signal Detection Method Based on Conjugate Gradient Descent
  • A Deep Learning Signal Detection Method Based on Conjugate Gradient Descent
  • A Deep Learning Signal Detection Method Based on Conjugate Gradient Descent

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the technical solution and advantages of the present invention clearer, the specific implementation manner of the technical solution will be described in more detail with reference to the accompanying drawings.

[0032] In the considered massive MIMO system, a vertical hierarchical space-time structure is adopted, with 64 antennas at the receiving end and 32 antennas at the transmitting end, and the channel is modeled according to the application scenario. A deep learning signal detection method based on the conjugate gradient descent method proposed for this system includes the following steps:

[0033] Step 1. Construct the deep learning network LcgNetV. The invention expands the iterative process of the conjugate gradient descent method into a network, transforms the step scalar of each iteration into network parameters to be learned, and increases the dimension of these scalar parameters to vector parameters.

[0034] The conjugate gradient descent...

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 present invention provides a deep learning signal detection method based on a conjugate gradient descent method, mainly for a massive MIMO system. The method comprises the following steps: (1) constructing a model-driven deep learning network LcgNet on the basis of a conjugate gradient descent method, converting a step scalar of each iteration into a network parameter needing to be learned, and improving the dimension of the parameter; (2) modeling a channel environment, and generating a large amount of training data with different signal-to-noise ratios according to an MIMO system model; (3) carrying out offline training on the network by using the large amount of training data; and (4) carrying out online real-time signal detection according to a received signal and assumed perfectly known channel state information. By means of the power of deep learning, the present invention can improve the signal detection precision, and further reduce the calculation complexity. Besides, the deep learning network is easy to train due to the limited number of parameters requiring to be optimized, and has low requirements for time and hardware in the training stage.

Description

technical field [0001] The invention belongs to the field of wireless communication, and relates to a deep learning signal detection method based on a conjugate gradient descent method. Background technique [0002] With the rise of the Internet of Things and the increasing variety of mobile Internet services, people have put forward higher requirements for the data transmission rate and service quality of cellular mobile communications. Because it can fully tap the degree of freedom of the spatial dimension, and obtain better power utilization while improving spectral efficiency, massive MIMO systems have attracted widespread attention at home and abroad. The large-scale antenna array configured by the massive MIMO system not only brings performance gain, but also brings a sharp increase in system hardware complexity and computational complexity. Therefore, a detector with low complexity and good bit error rate performance is very important for the design of MIMO receiver....

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): H04B7/0413H04B17/336H04B17/391G06N3/08
CPCG06N3/08H04B7/0413H04B17/336H04B17/391
Inventor 韦逸赵明敏赵民建雷鸣
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com