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

Multi-user shared access receiver based on neural network and communication method thereof

A neural network and shared access technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as high complexity, receiver bit error rate performance and detection performance need to be improved

Inactive Publication Date: 2021-03-26
HARBIN INST OF TECH +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, interference cancellation technology often brings high complexity. Considering the excellent performance of deep neural network, neural network is used for receiver design
[0005] The bit error rate performance and detection performance of existing receivers need to be improved

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
  • Multi-user shared access receiver based on neural network and communication method thereof
  • Multi-user shared access receiver based on neural network and communication method thereof
  • Multi-user shared access receiver based on neural network and communication method thereof

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0031] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS 1. A neural network-based multi-user shared access receiver, a neural network-based multi-user shared access receiver, which includes: a DNN model, the DNN model is located at the signal receiving end, and the DNN model includes an input layer, hidden layer and output layer;

[0032] The input layer is used to input data of K users;

[0033] The hidden layer is used to hide the data of K users;

[0034] The output layer is used to output data of K users;

[0035] Its characteristics are: the number of hidden layers in the DNN model is L, L is a positive integer l=1,...L, and the hidden layer of the first layer contains the connection weight matrix W l , bias vector b l and the activation function σ l , neurons in each layer use the same σ l The structure of the DNN model is expressed as:

[0036] σ L (W L σ L-1 (...σ 1 (W 1 x+b 1 )…)+b L ),

[0037] In the formula: x represents the input data to be processe...

specific Embodiment approach 2

[0040] Specific embodiment two, the communication method of multi-user shared access receiver based on the neural network described in specific embodiment one: it is characterized in that: its signal transmission method:

[0041] Step 1. K users perform constellation mapping respectively to obtain K mapping results;

[0042] Step 2, respectively performing expansion processing on the K mapping results obtained in step 1 to obtain K expansion processing results;

[0043] Step 3. Transmitting the K extended processing results obtained in the step as transmission signals to the multi-user shared channel;

[0044] Its signal receiving method: the receiving end receives the transmitting signal transmitted by the transmitting end in the multi-user shared channel and sends it to the DNN model for processing;

[0045] Step 4: The DNN model outputs the original data of K users, and completes a neural network-based multi-user shared access receiver communication.

[0046] Principle: A...

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 multi-user shared access receiver based on a neural network and a communication method thereof, relates to the technical field of communication and the field of artificial intelligence, and provides a multi-user shared access receiver better than a traditional MMSE-SIC receiver and a communication method thereof in order to improve the bit error rate performance and detection performance of an existing receiver. The bit error rate and other detection performances of the MMSE-SIC receiver are better than those of a traditional MMSE-SIC receiver no matter under a Gaussian channel or a Rayleigh fading channel.

Description

technical field [0001] This application relates to the field of communication technology and the field of artificial intelligence, in particular to the neural network receiver technology under the non-orthogonal multiple access technology. Background technique [0002] MUSA [0003] With the development of communication technology, the number of wireless access devices and the consumption of data traffic will show explosive growth. In previous wireless communication systems, Orthogonal Multiple Access (OMA) is used. However, since the resources allocated to different users in the OMA technology need to be kept orthogonal, the number of users who can share the same channel resource is limited. In order to deal with such limitations, researchers have proposed Non-Orthogonal Multiple Access (NOMA) technology. This technology can increase the capacity of the system and improve the spectrum efficiency of the system at the same time, so that communication can be completed with ...

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): H04B1/16G06N3/08G06N3/04
CPCH04B1/16G06N3/084G06N3/045
Inventor 吴少川张浩然李壮
Owner HARBIN INST OF TECH
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