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

Digital signal processing method and system

A digital signal processing and digital signal technology, applied in character and pattern recognition, signal pattern recognition, instruments, etc., can solve problems such as difficult to find filters, simplify the preprocessing process, and meet the needs of digital signal processing Effect

Active Publication Date: 2019-10-22
上海点积实业有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In related technologies, the preprocessing of digital signals, such as the restoration, enhancement and denoising of digital signals, is generally processed by filters. However, the use of filters When processing, each filter can only solve part of the problem, so dozens of filters may be required, and it is difficult to find a universal filter

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
  • Digital signal processing method and system
  • Digital signal processing method and system
  • Digital signal processing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] Figure 2A It is a flowchart of step S104 in the digital signal processing method of an embodiment of the present invention.

[0083] Such as Figure 2A As shown, in one embodiment, preferably, the above step S102 includes: using a preset type of deep convolutional neural network model to perform signal denoising on digital signals;

[0084] Step S104 includes:

[0085] Step S201, obtaining a first set of training sample signals, the first set of training sample signals includes multiple sets of training sample signals, each set of training sample signals includes standard digital signals and input digital signals, and the input digital signals are superimposed with standard digital signals and random Gaussian noise signal;

[0086] Wherein, the standard digital signal can be different types of waveforms, such as square wave, sine wave or other arbitrary waveforms. The random Gaussian noise signal can be randomly generated and stored in a predetermined storage space...

Embodiment 2

[0115] Figure 5 It is a flow chart of step S104 in the digital signal processing method of another embodiment of the present invention.

[0116] Such as Figure 5 As shown, in one embodiment, preferably, the above step S102 includes: using a preset type of deep convolutional neural network model to perform signal restoration on digital signals;

[0117] Above-mentioned step S104 comprises:

[0118] Step S501, obtaining a second set of training sample signals, the second set of training sample signals includes multiple sets of training sample signals, each set of training sample signals includes an original signal and a digitally converted signal, and the digitally converted signal is converted from the original signal through a predetermined conversion method get;

[0119] Wherein, when generating the second training sample signal set, the signal generation program can be called from the second predetermined storage space, and the multiple original signals generated by the...

Embodiment 3

[0127] Figure 6 It is a flow chart of step S104 in the digital signal processing method of another embodiment of the present invention.

[0128] Such as Figure 6 As shown, in one embodiment, preferably, the above step S102 includes: using a preset type of deep convolutional neural network model to restore the phase of the digital signal;

[0129] The above step S104 includes:

[0130] Step S601, obtain a third set of training sample signals, the third set of training sample signals includes multiple sets of training sample signals, each set of training sample signals includes an original digital signal and a phase-shifted digital signal, and the phase-shifted digital signal is obtained from the original digital signal through The phase offset is obtained;

[0131] Wherein, when generating the third training sample signal set, the signal generation program can be called from the third predetermined storage space to obtain a plurality of original digital signals generated b...

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 digital signal processing method and system. The method comprises the following steps: receiving a digital signal to be processed; performing corresponding preprocessing operation on the digital signal by using a preset type of deep convolutional neural network model to obtain a processed digital signal; and outputting the processed digital signal. Through the technical scheme, signal processing does not need to be carried out through multiple filters, signal processing can be achieved only through the deep convolutional neural network model, the deep convolutional neural network model can contain all the effects of using the filters, and therefore the preprocessing process of digital signals is simplified.

Description

technical field [0001] The present invention relates to the technical field of deep learning algorithms, and more specifically, to a digital signal processing method and system. Background technique [0002] In the related art, for the preprocessing of digital signals, such as the restoration, enhancement and denoising of digital signals, filters are generally used for processing. However, when using filters for processing, each filter can only solve part of the problem, so , may require dozens of filters, and it is difficult to find a universal filter. Contents of the invention [0003] In view of the above problems, the present invention proposes a digital signal processing method and a digital signal processing system, which can process digital signals through a deep convolutional neural network model, and the deep convolutional neural network model can integrate all Effects are included to simplify pre-processing of digital signals. [0004] According to a first aspe...

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): G06K9/00G06N3/04
CPCG06N3/045G06F2218/04
Inventor 夏广武杨建
Owner 上海点积实业有限公司
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