Optical fiber nonlinear equalization method based on KNN algorithm without data auxiliary

A KNN algorithm, a technology without data assistance, applied in baseband systems, digital transmission systems, modulated carrier systems, etc., to achieve the effect of improving system bit error rate, low computational cost, and reducing computational complexity

Active Publication Date: 2018-10-16
SUZHOU UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, this method does not require additional training data, which can be called non-data-assisted DCT-KNN algorithm, a self-training method, and extracts

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
  • Optical fiber nonlinear equalization method based on KNN algorithm without data auxiliary
  • Optical fiber nonlinear equalization method based on KNN algorithm without data auxiliary
  • Optical fiber nonlinear equalization method based on KNN algorithm without data auxiliary

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0046] Embodiment 1: A fiber nonlinear equalization method based on the KNN algorithm without data assistance, the device used is as attached figure 1 As shown, the signal from the transmitting end is transmitted through the long-distance optical fiber, and then received by the receiver. The received optical signal is converted into an electrical signal. After the carrier phase is restored, it enters the nonlinear equalizer (KNN detector) of this embodiment. Perform fiber nonlinear equalization.

[0047] The fiber nonlinear equalization method is: divide the data into training model and test model, use density function to extract less noisy data, label them in the training model, as training samples, and apply KNN algorithm to use more in the test model Noise classifies data.

[0048] See attached image 3 , Specifically including the following steps:

[0049] (a) Training model

[0050] This part includes three steps, extracting data by density, marking data with demodulation and

...

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 an optical fiber nonlinear equalization method based on KNN algorithm without data auxiliary. The method comprises the following steps: acquiring a distribution density parameter of each data point, performing signal modulation by selecting the data point with the distribution density parameter greater than the preset threshold, acquiring labels corresponding to various data points, dividing into M clusters according to the labels so as to acquire the corresponding centroids; reclassifying the data points according to Euclidean distance according to the acquired centroids to construct a training sample set; taking the data point X not acquiring the label, acquiring K closest neighbor point of the data point X from the training sample set; computing the KNN Euclideandistance of the data point X, and finding the label cluster of K closest neighbor points; determining a prediction label of the data point X by using a weighted sum voting rule, and distributing theX to the corresponding cluster; repeating the above steps until accomplishing the processing on all data points. Through the optical fiber nonlinear equalization method disclosed by the invention, thecomputation complexity is greatly reduced, the zero redundancy of the system is realized, the classification performance of the system can be obviously improved, and the system error rate is improved.

Description

technical field [0001] The invention relates to an optical fiber communication method, in particular to a nonlinear equalization method used in an optical fiber communication system. Background technique [0002] For long-distance and large-capacity optical fiber communication systems, the communication capacity and communication distance of the system are the goals pursued by developers. In order to increase the transmission rate, such systems usually have high-order modulation signals with high spectral efficiency. For example, M-ary phase shift keying (M-PSK) and M-ary quadrature amplitude modulation (M-QAM) are competitive Candidate modulation signal. At present, combined with coherent detection and digital signal processing (DSP) technology, 16-QAM is widely used in 200G channels, and 64-QAM is widely used in channels above 400G. These high-order modulation signals increase the data transmission rate, but at the same time, the actual transmission distance is reduced 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
IPC IPC(8): H04B10/61H04L27/38
CPCH04B10/616H04B10/6161H04L27/38H04L27/3818H04L25/03178
Inventor 高明义张俊峰陈伟沈纲祥
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap