An RFID indoor positioning method based on a locust algorithm and an extreme learning machine

An extreme learning machine, indoor positioning technology, applied in the field of RFID indoor positioning, can solve the problems of low positioning accuracy and low robustness

Inactive Publication Date: 2019-04-09
GUANGXI UNIV
View PDF10 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its response to complex and changeable environments often leads to low positioning accuracy and poor robustness

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
  • An RFID indoor positioning method based on a locust algorithm and an extreme learning machine
  • An RFID indoor positioning method based on a locust algorithm and an extreme learning machine
  • An RFID indoor positioning method based on a locust algorithm and an extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] figure 1 It is an overall frame diagram of an RFID indoor positioning method based on the locust algorithm and extreme learning machine of the present invention, mainly involving two stages: an offline stage and an online stage. In the offline stage, the RFID reference tags are arranged in the positioning area according to certain rules, and the signal strength value RSSI and specific position coordinates of each tag are received through the RFID antenna and RFID reader terminal, so as to obtain the content required by the Locust Algorithm-Extreme Learning Machine positioning model The original training data set of outliers, after the PC host computer receives the original data, remove the outliers, use the locust algorithm to optimize the hidden layer weight ω and threshold b of the extreme learning machine and construct the locust algorithm-extreme learning machine positioning model . In the online stage, the target tag is carried into the detection area, the reader ...

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 relates to an RFID indoor positioning method based on a locust algorithm and an extreme learning machine. According to the method, a locust algorithm is used for carrying out parameter optimization on a connection weight of an input layer and a hidden layer in the extreme learning machine and a hidden layer neuron threshold value, the performance of the extreme learning machine is improved, and then a reference tag is used for constructing an extreme learning machine positioning model for positioning. The method comprises the following two stages: an offline stage: indoor positioning area reference label data acquisition, original RSSI data preprocessing, training database establishment, positioning model parameter optimization and positioning model construction; And an online stage: target label signal acquisition, data processing prediction and positioning coordinate output. Compared with the prior art, the method has the advantages of being high in positioning precision, high in environment change resistance, low in cost and efficient in performance.

Description

technical field [0001] The invention relates to the technical field of wireless radio frequency positioning, in particular to an RFID indoor positioning method based on a locust algorithm and an extreme learning machine. Background technique [0002] The Internet of Things is a network that extends and expands its client end to any item on the basis of the Internet for information exchange and communication. The key technology of the Internet of Things, radio frequency identification (Radio Frequency Identification, RFID) technology is an automatic identification technology for non-contact identification through radio frequency signals, which can identify identified objects. Indoor positioning in its field has attracted the attention of all parties due to its advantages in indoor navigation, personnel and cargo positioning, and emergency rescue, and has shown a broad market prospect and a wide range of product applications. [0003] Commonly used positioning technologies in...

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): G06K17/00G06N3/00
CPCG06K17/0029G06N3/006
Inventor 郑嘉利王哲
Owner GUANGXI UNIV
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