Blind detection method based on discrete multilevel hysteresis noise chaotic neural network
A neural network, multi-level technology, applied in the direction of transmission modification based on link quality, shaping network in transmitter/receiver, device dedicated to receiver, etc. Improve the anti-noise ability, reduce the length of the data amount, and avoid the effect of falling into the minimum value point
Active Publication Date: 2021-06-11
NANJING UNIV OF POSTS & TELECOMM +1
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Literature [Zhang Yun, complex Hopfield neural network blind signal detection [D]. Nanjing: Nanjing University of Posts and Telecommunications Library, 2012:102-147.], and literature [Ruan Xiukai, Zhang Zhiyong. Blind detection of QAM signals based on continuous Hopfield neural network [J]. Journal of Electronics and Information Technology, 2011 (July 2011): 1-6.] Proposed discrete multi-level complex number and continuous multi-level complex Hopfield neural network respectively, but both are easy to fall into local minimum points, so The length of required data is large
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0069] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.
[0070] The present invention proposes a signal blind detection method based on a noise chaotic neural network of discrete multi-level hysteresis, and its specific implementation process is as follows:
[0071] When ignoring noise, the receiver equation for a discrete-time channel is defined as
[0072] x N =SΓ T (1)
[0073] In the formula, X N is the received data array, S is the transmitted signal array, Γ is the channel impulse response h jj Constituted block Toeplitz matrix; ( ) T Represents matrix transposition;
[0074] Among them, the sending signal matrix:
[0075] S=[s L+M (k),L,s L+M (k+N-1)] T =[s N (k),L,s N (k-M-L)] N×(L+M+1), M is the channel order, L is the equalize...
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
Login to View More Abstract
The invention discloses a blind detection method based on a discrete multi-level hysteresis noise chaotic neural network, comprising the following steps: constructing a receiving data matrix X N ; For the received data matrix X N Perform singular value decomposition; set weight matrix W RI , and construct the performance function; introduce the subsection annealing function into the chaotic neural network, and construct the discrete multilevel hysteresis chaotic neural network based on the subsection annealing; construct the improved new model of the noise chaotic neural network based on the discrete multilevel hysteresis Dynamic equation, the dynamic equation of the improved new model is iterated, and then the result of each iteration is substituted into the energy function E(t) of the noise chaotic neural network based on discrete multi-level hysteresis, when the energy function When E(t) reaches the minimum value, the discrete multilevel hysteresis chaotic neural network reaches equilibrium, and the iteration ends. The invention improves the activation function to construct a discrete multi-level hysteresis noise chaotic neural network model, which can better prevent the neural network from falling into the minimum value point.
Description
technical field [0001] The invention relates to a blind detection method of a noise chaotic neural network based on discrete multi-level hysteresis, and belongs to the field of wireless communication signal processing, and more specifically belongs to the technical field of Hopfield neural network blind detection. Background technique [0002] With the widespread application of discrete Hopfield neural networks in image restoration, associative memory, etc., the stability of the network is the basis of these applications, and the network must be stable to a fixed point at the end. Literature [Gao H.S., Zhang J., Stability for Discrete Hopfield Neural Networks with Delay [C]. 2008 Fourth International Conference on Natural Computation, Jinan, China, October 18-20, 2008, 560-563.] did some research on the stability of discrete neural networks, but these research results Image processing is limited to binary or two-level signals. Literature[H.J.Liu,Y.Sun.Blind bilevel imageres...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L25/03H04L1/00
CPCH04L1/0038H04L25/03165
Inventor 于舒娟张昀金海红董茜茜何伟朱文峰
Owner NANJING UNIV OF POSTS & TELECOMM