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

Indoor location fingerprint positioning method based on joint deep learning and weighted k-neighborhood algorithm

A proximity algorithm and indoor location technology, applied in neural learning methods, location information-based services, and computing, etc., can solve the problems of reduced positioning accuracy, affecting the accuracy of fingerprint features of fingerprint points, and errors in feature relationships, so as to reduce positioning accuracy. The effect of accuracy, small network coverage, and low network power consumption

Active Publication Date: 2022-05-13
NANTONG UNIVERSITY +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complex and changeable indoor environment, the obstruction of multi-wall groups and indoor noise interference will affect the accuracy of fingerprint features, the feature relationship found by the deep learning model will have errors, resulting in reduced positioning accuracy

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
  • Indoor location fingerprint positioning method based on joint deep learning and weighted k-neighborhood algorithm
  • Indoor location fingerprint positioning method based on joint deep learning and weighted k-neighborhood algorithm
  • Indoor location fingerprint positioning method based on joint deep learning and weighted k-neighborhood algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0054] see figure 1 , the present invention provides a technical solution: an indoor position fingerprint positioning method combined with deep learning and weighted K-neighborhood algorithm, in figure 1 In the 20m×20m positioning area, 4 anchor nodes are arranged at the top of the edge of the positioning area, the secondary relay nodes are arranged at the corner or center of the room in the positioning area, and the main relay node is arranged at the center o...

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 discloses an indoor position fingerprint positioning method combined with deep learning and weighted K-proximity algorithm. The method first collects WLAN signal feature data in the positioning area to establish a fingerprint library to train a convolutional neural network, and then based on the trained CNN network The model performs the initial positioning of the user's position, and then determines the theoretical range of the user in the positioning area according to the user's initial positioning position coordinates, and applies the weighted K proximity algorithm in the local Bluetooth Mesh network to locate the user's precise position, and finally feeds back the user's precise position coordinates to user equipment. The present invention jointly applies the deep learning model and the weighted K-neighborhood algorithm to optimize the position fingerprint positioning algorithm, improves the positioning accuracy of the algorithm, and at the same time jointly applies the Bluetooth Mesh and WiFi technology to build the main network, which is convenient for user equipment networking and can realize Indoor high-precision positioning.

Description

technical field [0001] The invention relates to the technical field of wireless communication and artificial intelligence, in particular to an indoor position fingerprint positioning method combined with deep learning and weighted K-neighborhood algorithm. Background technique [0002] In the context of the continuous development of wireless communication technology, users' demand for high-precision location positioning services is increasing. As a commonly used indoor positioning algorithm, the position fingerprint positioning algorithm has the advantage that it does not need high-precision time synchronization ranging, but its positioning accuracy is too dependent on the distribution density of fingerprint points. When the distribution density of fingerprint points is too low, the positioning accuracy drops sharply. Although the application of deep learning in indoor positioning can find out the characteristic relationship between fingerprint features and position coordina...

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): H04W4/02H04W4/021H04W4/33H04W64/00G06K9/62G06N3/04G06N3/08G06V10/764G06V10/82
CPCH04W4/021H04W4/023H04W4/33H04W64/00G06N3/08G06N3/045G06F18/24147
Inventor 孙强曹埔铭张子涵李翔宇李良程陈晓敏黄勋
Owner NANTONG UNIVERSITY