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

Parallel reconstruction method for joint sparse vector based on convolutional deep stacking network

A stacking network and joint sparse technology, applied in image data processing, instrumentation, computing and other directions, can solve problems such as the influence of calculation amount, and achieve the effect of improving accuracy, accelerating convergence speed, and speeding up convergence speed.

Inactive Publication Date: 2018-02-09
HUBEI UNIV OF TECH
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such algorithms are affected by the amount of calculation of sparse Bayesian learning, and the calculation efficiency is a problem worthy of further study.

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
  • Parallel reconstruction method for joint sparse vector based on convolutional deep stacking network
  • Parallel reconstruction method for joint sparse vector based on convolutional deep stacking network
  • Parallel reconstruction method for joint sparse vector based on convolutional deep stacking network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the examples. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0036] Inspired by the successful application of deep learning technology to pattern classification problems, the convolutional deep stacking network can be used to obtain the joint sparse structure of each channel signal, and the atom selection problem can be transformed into an atom classification problem. Multiple candidate atoms are selected in each iteration, effectively Solve the signal reconstruction problem under the multi-measurement vector model and keep the complexity of the algorithm low.

[0037] Based on this, an embodiment of the present invention provides a joint sp...

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 belongs to the technical field of compressed sensing of a multi-measurement vector model, and specifically relates to a parallel reconstruction method for a joint sparse vector based ona convolutional deep stacking network. Inspired by the successful application of a deep learning technology to a pattern classification problem, the parallel reconstruction method acquires a joint sparse structure of channel signals by using the convolutional deep stacking network, converts an atom selection problem into an atom classification problem and selects a plurality of candidate atoms ateach iteration, thereby effectively solving a problem of signal reconstruction under the multi-measurement vector model, and keeping low complexity of the algorithm.

Description

technical field [0001] The invention belongs to the technical field of compressed sensing of multi-measurement vector models, and in particular relates to a method for parallel reconstruction of joint sparse vectors based on convolution depth stacking network. Background technique [0002] With the rapid development of information technology, society has entered the era of big data with information explosion, and massive information sampling, transmission and storage have brought unprecedented pressure and challenges to existing technologies. The traditional signal processing technology mainly includes four steps of high-rate sampling, transformation, compression, and reconstruction. Compression is realized by retaining larger transform base coefficients and setting other transform base coefficients to zero. This high-speed sampling and recompression process wastes a lot of sampling resources, especially in the case of high sampling cost, large sampling data and complex samp...

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): G06T3/40
CPCG06T3/40G06T2207/20081
Inventor 曾春艳武明虎万相奎熊炜刘敏赵楠朱莉李利荣王娟饶哲恒
Owner HUBEI UNIV OF TECH
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