An LDPC code iterative decoding method based on deep learning

An LDPC code and iterative decoding technology, which is applied in the field of BP-DNN decoding based on deep learning, can solve the problems of channel noise decoding performance, and achieve the effect of reducing algorithm complexity and improving decoding performance.
CN109728824AActive Publication Date: 2019-05-07HANGZHOU DIANZI UNIV
7 Cites 6 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
HANGZHOU DIANZI UNIV
Publication Date
2019-05-07

Smart Images

  • Figure 1
    Figure 1
Patent Text Reader

Abstract

The invention provides an LDPC code iterative decoding method based on deep learning, and relates to the technical field of information transmission. The method comprises the following steps of: estimating coding bits and channel noise by adopting a standard BP iterative decoder; , obtaining channel noise and information bit estimation values according to the coding bits and channel noise, removing noise estimation errors of a standard BP decoder by using a neural network DNN to obtain more accurate estimation on the channel noise, processing the obtained noise estimation at a channel receiving end, re-inputting the obtained noise estimation into the decoder, and continuously performing iterating. The technical problem that channel noise affects decoding performance in the prior art can besolved. The method has the beneficial effects that more accurate estimation on channel noise is obtained, and the decoding signal to noise ratio is improved, so that the decoding performance is improved, and the algorithm complexity is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of information transmission, in particular to a BP-DNN decoding method based on deep learning. Background technique

[0002] With the development of technology, deep learning has been widely used in computer vision, natural language processing, self-driving vehicles and other fields, and has also achieved good results in information transmission. There are interference problems during the transmission of information, especially noise interference, which makes information errors at the receiving end. Therefore, a coding method with good performance and a suitable decoding algorithm are required. Chinese patent application publication number CN106571831A, the application publication date is April 19, 2017, and the invention patent application document titled "a deep learning-based LDPC hard-decision decoding method and decoder" discloses an LDPC code Hard decision decoding method. Including the foll...

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