CSI fingerprint passive positioning method based on depth separable convolution

A positioning method and passive technology, applied in positioning, neural learning methods, biological neural network models, etc., can solve the problems of high online positioning delay and time-consuming, and achieve the effect of low positioning delay and high positioning accuracy

Inactive Publication Date: 2020-11-10
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing CSI fingerprint positioning schemes based on deep learning take a lot of time in the offline training phase of the model, and the online positioning delay is high, which cannot meet people's requirements for real-time positioning services.

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
  • CSI fingerprint passive positioning method based on depth separable convolution
  • CSI fingerprint passive positioning method based on depth separable convolution
  • CSI fingerprint passive positioning method based on depth separable convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0027] The present invention provides a CSI fingerprint passive positioning method based on depth separable convolution, the process of which is as follows:

[0028] Step 1: If figure 2 As shown in , the indoor scene area is divided and the reference point is selected, and the reference point coordinates and CSI data are collected.

[0029] Step 2: Construct CSI feature images using the CSI data of different antenna pairs of the transmitter and receiver. For the data at each location, 3000 data packets are collected, multiple groups of time-continuous data packets are selected using a sliding window of size 30, and the amplitude of the CSI subcarrier in each data packet is extracted. The magnitude of the ith CSI subcarrier of packet j is Calculate the amplitude difference of adjacent subcarriers And construct CSI feature image...

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

According to the CSI fingerprint passive positioning method based on depth separable convolution, a CSI data construction feature image is used as a position fingerprint, different positions are identified through a convolutional neural network, and the CSI fingerprint passive positioning method based on depth separable convolution is realized. The method comprises the following steps: an offlinetraining stage: extracting the amplitude of CSI in the MIMO system, then constructing a CSI feature map similar to an RGB three-channel image as position fingerprints of different positions, and learning CSI features of different positions by using a deep separable convolution design convolutional neural network. In the online positioning stage, CSI data of a target position are collected to construct a target position feature image, and then the trained convolutional neural network is used to predict the position of the target. According to the method, based on the fusion of the position fingerprints of the CSI time domain, the frequency domain and the space domain, and the adoption of depth separable convolution, a higher position recognition rate and lower positioning delay can be obtained.

Description

technical field [0001] The invention relates to the technical field of indoor positioning, in particular to a CSI fingerprint passive positioning method based on depth separable convolution. Background technique [0002] Mobile smart devices and wireless networks have penetrated into all aspects of human production and life, and location-based services (Location Based Service, LBS) have gradually become an indispensable service in people's lives. Although the Global Positioning System (Global Positioning System, GPS) has been thriving in the field of outdoor navigation and positioning, the severe fading of GPS signals caused by reinforced concrete makes it difficult to use in indoor navigation and positioning. Indoor positioning has important research significance and practical value, and has attracted the research enthusiasm of a large number of researchers at home and abroad. At the same time, a large number of indoor positioning solutions have emerged. Currently, the main...

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 Applications(China)
IPC IPC(8): H04W64/00H04B17/309G01S5/02G06N3/04G06N3/08
CPCH04W64/006H04B17/309G01S5/0252G06N3/08G06N3/045
Inventor 孙力娟荀文婧韩崇郭剑肖甫王娟周剑
Owner NANJING UNIV OF POSTS & TELECOMM
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