An Indoor Positioning Method Based on Deep Adaptive Network

An adaptive network and indoor positioning technology, which is applied in the field of indoor positioning based on a deep adaptive network, can solve problems such as difficult to form accurate, real-time, and stable positioning, achieve high positioning accuracy, improve accuracy and robustness, and be robust good sex effect

Active Publication Date: 2022-02-08
成都电科慧安科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can improve the positioning accuracy to a certain extent, its shortcomings are also obvious. This method mainly maps the source domain and the target domain to the subspace by learning a shallow mapping, and the shallow mapping can only learn shallow Layer representation features, which are clearly insufficient for reducing domain variance
Therefore, due to the existence of the above problems, it is difficult for this type of method to form accurate, real-time and stable positioning in complex indoor environments.

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 Indoor Positioning Method Based on Deep Adaptive Network
  • An Indoor Positioning Method Based on Deep Adaptive Network
  • An Indoor Positioning Method Based on Deep Adaptive Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A Deep Adaptive Network Based Indoor Localization Method.

[0051] A kind of indoor localization method based on deep adaptive network, it is characterized in that comprising the following steps:

[0052] Step 1. Divide the indoor environment to be positioned into grid areas of equal size, and record the corresponding coordinate information;

[0053] Step 2. Place the mobile device at each grid point in the positioning environment in turn, and record the RSS value and the corresponding grid point coordinate information from each access point at the moment to form an RSS offline fingerprint database, which is the source domain;

[0054] Step 3. collect the RSS value of the mobile equipment to be located, form the target field;

[0055] Step 4. Knowledge transfer;

[0056] Step 5. Input the target domain data into the trained network to obtain the position.

Embodiment 2

[0058] A kind of indoor localization method based on deep adaptive network, it is characterized in that comprising the following steps:

[0059] Step 1. Divide the indoor environment to be positioned into grid areas of equal size, and record the corresponding coordinate information;

[0060] Step 2. Place the mobile device at each grid point in the positioning environment in turn, and record the RSS value and the corresponding grid point coordinate information from each access point at the moment to form an RSS offline fingerprint database, which is the source domain;

[0061] Step 3. collect the RSS value of the mobile equipment to be located, form the target field;

[0062] Step 4. Knowledge transfer;

[0063] Step 5. Input the target domain data into the trained network to obtain the position.

[0064] The detailed steps of step 2 are as follows: acquire data and form an RSS fingerprint library, place the mobile device in each grid point in turn, record the grid point num...

Embodiment 3

[0074] A kind of indoor localization method based on deep adaptive network, it is characterized in that comprising the following steps:

[0075] Step 1. Divide the indoor environment to be positioned into grid areas of equal size, and record the corresponding coordinate information;

[0076] Step 2. Place the mobile device at each grid point in the positioning environment in turn, and record the RSS value and the corresponding grid point coordinate information from each access point at the moment to form an RSS offline fingerprint database, which is the source domain;

[0077] Step 3. collect the RSS value of the mobile equipment to be located, form the target field;

[0078] Step 4. Knowledge transfer;

[0079] Step 5. Input the target domain data into the trained network to obtain the position.

[0080] The detailed steps of step 2 are as follows: acquire data and form an RSS fingerprint library, place the mobile device in each grid point in turn, record the grid point num...

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 present invention belongs to the category of solving the RSS volatility problem by using a deep transfer learning method in a complex indoor environment, and is specifically an indoor positioning method based on a deep self-adaptive network, which is characterized in that it includes the following steps: Step 1. Divide the indoor environment into grid areas of equal size, and record the corresponding coordinate information; Step 2. Place the mobile device in each grid point in the positioning environment in turn, and record the RSS value from each access point at the moment and the corresponding Grid point coordinate information forms the RSS offline fingerprint database, which is the source domain; Step 3. Collect the RSS value of the mobile device to be located to form the target domain; Step 4. Knowledge transfer; Step 5. Input the target domain data into the trained in the network to get the location.

Description

technical field [0001] The invention belongs to a method for positioning by using received signal strength in an indoor environment, in particular a technology for positioning a wireless device in a complex indoor environment by using a deep transfer learning method, specifically an indoor positioning method based on a deep self-adaptive network. Background technique [0002] In recent years, due to the wide application of mobile devices and the rapid development of social networks, the demand for indoor positioning services is increasing. For example, navigation in large airports and stations, real-time monitoring of workers' positions in factories, and rescue of indoor personnel in emergency situations are too numerous to mention. Therefore, under the influence of huge market traction, seeking a high-precision real-time positioning system suitable for complex indoor positioning environments has become the research focus of the industry. [0003] Generally, the WiFi-based ...

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): H04W4/33H04W4/02H04W4/021H04W64/00G06N3/04G06N3/08
CPCH04W4/33H04W4/023H04W64/006G06N3/08G06N3/045
Inventor 殷光强郭贤生李耶王磊
Owner 成都电科慧安科技有限公司
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