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

SVM equalization method and system for maximum variance data selection of low bandwidth highspeed optical communication

A technology of data selection and equalization method, applied in baseband systems, digital transmission systems, baseband system components, etc., can solve the problems of further improvement in comprehensive performance, high computational complexity, and high equalization expenses, and achieve improved accuracy and performance. , Improve system performance, equalize the effect of fast speed

Active Publication Date: 2018-09-11
HANGZHOU DIANZI UNIV
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this solution uses a traditional electric domain equalizer, which requires a long training sequence, high equalization expenses, and high computational complexity, so the overall performance needs to be further 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
  • SVM equalization method and system for maximum variance data selection of low bandwidth highspeed optical communication
  • SVM equalization method and system for maximum variance data selection of low bandwidth highspeed optical communication
  • SVM equalization method and system for maximum variance data selection of low bandwidth highspeed optical communication

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0039] Such as figure 1 As shown, the present embodiment provides a low-cost maximum variance data selection and SVM discrimination system for low-bandwidth high-speed optical communication, including: an optical NRZ signal transmitting module, a receiving module and an optical fiber, and the optical NRZ signal transmitting The module sends the optical NRZ signal containing the training sequence to the receiving module through the optical fiber, and the receiving module converts the optical signal into ...

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 provides a maximum variance data selection and SVM equalization method for low bandwidth highspeed optical communication, which comprises the following steps: step 1, inserting a set number of training sequences into a transmitted digital signal data header, generating an electrical NRZ signal through highspeed NRZ modulation, and converting the electrical NRZ signal into a light NRZsignal by an optical modulator; step 2: transmitting the signal to a receiving end through an optical fiber, and converting the received light NRZ signal into an electrical NRZ signal via the receiving end; step 3, sampling the electrical NRZ signal, and then carrying out time synchronization; step 4, extracting the training sequence from the time-synchronized data; step 5, extracting an optimumdiscriminant sample point in each code symbol sample point in each segment by using the method of maximizing variance, and constructing a feature vector for each training sequence; step 6, using the feature vector of the training sequence, and adopting the SVM algorithm to train an optimal classification hyperplane; step 7, constructing a feature vector for each new unknown code symbol; step 8, using the optimal classification hyperplane to classify the NRZ electrical signals.

Description

technical field [0001] The invention belongs to the technical field of low-bandwidth high-speed optical communication systems, and in particular relates to an SVM (support vector machine) equalization method and system for maximizing variance data selection of low-bandwidth high-speed optical communication. Background technique [0002] In recent years, with the development of various emerging services, the bandwidth requirements of end users are increasing rapidly. This makes the requirements for the wavelength rate of optical communication higher and higher, and the rate of a single wavelength is developing towards 40Gb / s, or even 100Gb / s. At present, the operating wavelength of the laid G.652 standard optical fiber is C-band, which has relatively large dispersion, and the impact of dispersion will become more serious as the speed increases. Dispersion will lead to pulse broadening, causing crosstalk between symbols, causing signal distortion, resulting in an increase in ...

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): H04L25/03H04B10/2513
CPCH04B10/2513H04L25/03057
Inventor 毕美华姜伟俞嘉生卓先好杨国伟周雪芳胡淼骆懿李齐良
Owner HANGZHOU DIANZI UNIV
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