Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Signal modulation identification method of complex valued neural network based on structure optimization algorithm

A neural network and optimization algorithm technology, applied in the field of wireless communication technology and artificial intelligence, can solve the problems of unsatisfactory training results of first-order complex-valued optimization algorithm training speed and convergence speed.

Active Publication Date: 2021-11-12
SUZHOU UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the training speed, convergence speed and training results of the first-order complex-valued optimization algorithm are unsatisfactory, and there is currently no accurate mathematical model to solve the structural problems of the feed-forward complex-valued neural network

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
  • Signal modulation identification method of complex valued neural network based on structure optimization algorithm
  • Signal modulation identification method of complex valued neural network based on structure optimization algorithm
  • Signal modulation identification method of complex valued neural network based on structure optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The specific calculation process of the complex-valued structure optimization algorithm proposed by this patent will be further described below in conjunction with the accompanying drawings and specific embodiments of the present invention.

[0032]In the realization of signal modulation identification, artificial neural network is a relatively common method. For the processing of signal modulation identification, the forward complex-valued neural network is an efficient means. Forward complex-valued neural network has attracted the attention of scholars due to its fast learning and ability to directly process complex signals, and there are more and more researches related to it. In some application areas such as radar signal processing, medical image processing, channel state prediction, EEG, etc.

[0033] For the forward complex number neural network, how to quickly determine the network structure and network parameters is a big problem. The complex-valued structure ...

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 signal modulation identification method of a complex valued neural network based on a structure optimization algorithm. The method comprises the following steps: initializing the structure and parameters of a forward complex valued neural network; adjusting parameters in the complex-valued neural network by using a complex-valued structure optimization algorithm, verifying the generalization performance of the forward complex-valued neural network, storing the number of current hidden layer neurons and all parameter values of the forward complex-valued neural network, and judging whether training is trapped in a local minimum point or not; if yes, adding a hidden layer neuron to the current model by using a complex value increment construction algorithm, calculating a weight of a newly added neuron, a hidden layer output matrix and a loss function value on the basis of current training, and continuing to train a new model; if not, keeping the model structure unchanged, and continuing training until an algorithm stopping condition is met. According to the method, the forward complex value neural network model with the optimal structure can be adaptively constructed, the method is used for identifying the communication signal modulation mode, and a satisfactory effect is achieved.

Description

technical field [0001] The invention relates to the fields of wireless communication technology and artificial intelligence, in particular to a communication signal modulation recognition method based on a structure optimization algorithm-based complex-valued neural network in a complex environment. Background technique [0002] The identification of the communication signal modulation mode is the prerequisite for obtaining the communication signal. Modulation recognition technology is a hot research topic in the field of signal processing in recent years. With the rapid development of communication technology, the modulation patterns of communication signals have become more complex and diverse, making it impossible for conventional identification methods and theories to effectively identify modulated signals, which also puts forward higher requirements for the identification research of modulation methods. [0003] Typical signal modulation recognition algorithms can be d...

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 Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/2414G06F18/214
Inventor 黄鹤王志东
Owner SUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products