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

WCDMA cell searching method based on machine learning

A technology of machine learning and cell search, which is applied in the field of WCDMA communication, can solve the problems of complex and ineffective cell search, and achieve the effect of fast frame synchronization and flexible cell search

Active Publication Date: 2021-06-15
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The process of cell search is relatively complicated, and the secondary synchronization code pattern stipulated in the agreement must correspond to the primary scrambling code before processing. If the pattern table is changed or the secondary synchronization code is changed, subsequent processing cannot be performed.

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
  • WCDMA cell searching method based on machine learning
  • WCDMA cell searching method based on machine learning
  • WCDMA cell searching method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The specific process of the cell search of the embodiment is as follows: image 3 Shown:

[0042] 1) Network construction

[0043] Because the structure of the WCDMA downlink signal in each time slot is basically the same, a 38400 GOLD code truncated sequence is used to scramble a frame of signal, and the GOLD code itself is a pseudo-random sequence generated by certain rules. The way to train and learn the corresponding features, and the RNN network family is suitable for learning sequence data, and has excellent effects in the field of natural language processing and time series processing, so RNN neurons are used to build the network.

[0044] Network structure such as Figure 4 As shown, it includes the input layer InputLayer (Simple_rnn_1_input), the hidden layer SimpleRNN (Simple_rnn_1) built by the cyclic neural network layer, the fully connected layer Dense (Dense_1) and the output layer Activation (Activation_1); the data format is (batch size, number of chan...

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 WCDMA cell searching method based on machine learning, and the method comprises the following steps: in a training stage, generating a WCDMA downlink signal which does not contain an auxiliary synchronous code to manufacture a training data set, and getting rid of the dependency relationship between a main scrambling code and the auxiliary synchronous code; in a test stage, on the basis of a signal after time slot synchronization, making corresponding to-be-identified prediction data according to 15 positions where a frame header may appear, carrying out main scrambling code identification, obtaining main scrambling code classification results and corresponding probabilities of the 15 pieces of to-be-identified prediction data in the group, and finally, searching the maximum value of the 15 prediction probabilities, and obtaining a frame header position and a main scrambling code used by the signal. According to the method, an auxiliary synchronization code and a pattern table corresponding to a main scrambling code do not need to be known, and rapid frame synchronization and classified identification of 512 scrambling codes are achieved in a machine learning mode, so that cell search is completed more flexibly.

Description

technical field [0001] The invention relates to WCDMA communication technology, in particular to WCDMA signal scrambling code identification technology. Background technique [0002] A WCDMA frame consists of 38400 chips, which are divided into 15 time slots, and each time slot contains 2560 chips. In the main synchronization process, the position of a time slot can be determined, and the next step is to determine the position of a radio frame header. The secondary synchronization process can determine the frame header, that is, the position of the 0th time slot and the number of the scrambling code group. There are 512 primary scrambling codes for the downlink, divided into 64 groups of 8. Each cell is assigned only one primary scrambling code. [0003] The structure design of the secondary synchronization channel S-SCH channel is as follows figure 1 shown. The structure of the S-SCH channel is very similar to the channel structure of the primary synchronization channe...

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): H04J11/00H04B7/26G06N20/00
CPCG06N20/00H04B7/2668H04J11/0069
Inventor 张雄潘晔王沙飞邵怀宗林静然利强
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com