Unlock instant, AI-driven research and patent intelligence for your innovation.

A Frequency Recognition System Based on Neural Network

A neural network and frequency recognition technology, applied in the field of frequency recognition systems, can solve the problems of shortening the recognition time and increasing the total time

Active Publication Date: 2020-06-16
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Binary search for sequential sequences is the most efficient way, but when the initial frequency difference is relatively large, repeated execution of binary search is required, which limits the possibility of further shortening the recognition time
[0006] Using the traditional search method, when we identify multiple times, the search process needs to be repeated for each identification, which increases the total time for frequency identification

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
  • A Frequency Recognition System Based on Neural Network
  • A Frequency Recognition System Based on Neural Network
  • A Frequency Recognition System Based on Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0043] combine Figure 5 and Figure 6 , using recurrent neural network structure RNN (Recurrent Neural Networks), LSTM (Long Short Term Memory) algorithm, frequency sampling and phase sampling mode, give a specific implementation example of the present invention applied to phase-locked loop fast locking.

[0044] The topological structure of recurrent neural network (RNN) is as follows: Figure 7 As shown, including input layer, hidden layer and output layer, where the input set is marked as {x0,x1,…,xt,xt+1,…}, and the output level is marked as {y0,y1,…,yt,yt+1 ,…}, the output set of hidden units is marked as {s0,s1,…,st,st+1,…}, these hidden units complete the main work.

[0045] Figure 7 is an incomplete structure diagram of a recurrent neural network. Since the loops of the hidden layer of the cyclic neural network include self-loop...

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 field of integrated circuits, and in particular relates to a frequency identification system based on a neural network. The present invention uses the neural network module to process the samples containing the frequency information. After the sample training is completed, the neural network module saves the current state. When the input frequency is identified later, the search process does not need to be repeated, and the target code of the initial rough range is directly output. Cbit, completes the rapid identification of the frequency. The invention can be used in the phase-locked loop circuit, and the accurate output frequency can be obtained after correction.

Description

technical field [0001] The invention belongs to the field of integrated circuits, and in particular relates to a frequency identification system based on a neural network. Background technique [0002] Frequency identification is to roughly divide a single frequency in a frequency band and identify its initial range so that the circuit can quickly identify it. When identifying the frequency, first encode the roughly divided frequencies in the frequency band. The whole process is to find the corresponding target code from a sequential sequence. Naturally, the most efficient search method is the dichotomy method. Of course, other methods such as sequential search are the same. can accomplish this task. [0003] When using binary search, we provide an initial value, compare it with the input frequency, and then perform multiple binary searches to obtain the frequency range it is in. [0004] For sequential sequence search, since all frequency ranges have to be traversed, the ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06F2218/12G06F18/214
Inventor 刘洋安坤郭睿钱堃魏金平于奇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA