WLAN indoor positioning method of TebNet neural network model based on deep learning

A neural network model and deep learning technology, applied in the field of WLAN indoor positioning, can solve the problems of over-parameterization of the model and the unsatisfactory performance of DNN in the table data set, and achieve enhanced learning ability, strong environmental adaptability and positioning. Accuracy, the effect of improving positioning accuracy and environmental adaptability

Pending Publication Date: 2021-04-13
BEIJING UNIV OF TECH
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But for traditional DNN, blindly stacking network layers can easily lead to overpara

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
  • WLAN indoor positioning method of TebNet neural network model based on deep learning
  • WLAN indoor positioning method of TebNet neural network model based on deep learning
  • WLAN indoor positioning method of TebNet neural network model based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The preset indoor positioning scenarios are corridors and elevator rooms, with an area of ​​80 square meters.

[0036] The block diagram of the general flow chart of positioning prediction in the present invention can be found in Figure 4 . In the offline phase, the signal strength RSSI data of the access point AP is collected at the reference point and EDA is used to explore the data, and the matplotlib tool is used to generate statistical data and analyze the heat map as shown in figure 2As shown, it can be concluded that there are missing values ​​in the black area and outliers in the white area in the statistical data, so data preprocessing is required. Then perform feature engineering work on the preprocessed data, select specific features and perform feature synthesis, generate statistical features and deliver the TabNet neural network model, and use cross-validation methods to train data. The specific implementation steps are as follows:

[0037] (1) First es...

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 a WLAN indoor positioning method of a TebNet neural network model based on deep learning, and relates to the field of indoor positioning. The method comprises the following steps: carrying out EDA data exploration in an offline stage, exploring data rules and distribution by utilizing a matplotlib data analysis tool, and carrying out feature selection and synthesis by feature engineering to generate statistical features; and data training being carried out by using a cross validation method and the like to finally obtain a positioning prediction model. According to the invention, reinforcement learning can be carried out along with data accumulation; and the method has high environment adaptability and positioning precision.

Description

technical field [0001] The invention relates to the field of WLAN indoor positioning, in particular to a WLAN indoor positioning method. Background technique [0002] In recent years, with the technological breakthroughs in communication technology and smart devices, derivative services of smart mobile terminals have developed rapidly. At the same time, people's demand for stable and effective positioning services is increasing day by day. Statistics show that people spend most of their time indoors. However, the traditional GPS positioning system cannot achieve reliable positioning functions in indoor scenes where buildings are heavily shaded. Therefore, research on indoor positioning has become an increasingly important topic in recent years. The more popular research directions. [0003] Due to the increasing number of Wi-Fi base stations in people's living environment, the equipment is easy to build and low in cost, so WIFI indoor positioning has the advantages of conv...

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): H04W4/021H04W4/33H04W64/00G06N3/04G06N3/08
CPCH04W4/021H04W4/33H04W64/00G06N3/08G06N3/047G06N3/045
Inventor 张会清贾岚云
Owner BEIJING UNIV OF TECH
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