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

Method for estimating RSS missing value based on adaptive context generative adversarial model

A contextual and self-adaptive technology, applied in the field of deep learning and indoor positioning, can solve the problems of high cost of measurement data and heavy tasks, and achieve the effect of saving labor costs, construction and maintenance time

Inactive Publication Date: 2019-11-15
TIANJIN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The purpose of the present invention is to solve the problem of high cost of measurement data in the offline stage and heavy tasks, and propose a method for estimating RSS missing values ​​based on the Adaptive Context Generative Adversarial Networks Model (ACOGAN). Under the environment, the fingerprint database is self-updated

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
  • Method for estimating RSS missing value based on adaptive context generative adversarial model
  • Method for estimating RSS missing value based on adaptive context generative adversarial model
  • Method for estimating RSS missing value based on adaptive context generative adversarial model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0043] Generative Adversarial Networks Model (GAN) is popular because of its great potential to learn high-dimensional, complex real-world data. For scenarios with missing data, it can be used to generate more sample data, which is currently the best way to solve the problem of missing information. Facing the high cost of building and maintaining a fingerprint database, missing fingerprints at specific locations can be predicted by learning partial reference point distributions. In fact, the missing fingerprint problem is equivalent in nature to missing information. Therefore, in this embodiment, the GAN model is used to solve the above problems, and supplement the fingerprint datab...

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 method for estimating an RSS missing value based on an adaptive context generative adversarial model. The method comprises the following steps of (1) establishing an adaptivecontext generative adversarial model, namely, an ACOGAN model, in combination with an Auto Encoder model and a GAN model, wherein the ACOGAN model comprises a generator and a discriminator, and the generator is formed by connecting an encoder and a decoder through a channel full connection layer; (2) generating RSS fingerprint simulation data through the ray tracing technology to serve as a training set and a test set of an ACOGAN model; (3) preprocessing the training set, and converting the training set into an input format required by an ACOGAN model; (4) training an ACOGAN model; (5) exporting training parameters of the ACOGAN model; (6) preprocessing the test set, and converting the test set into an input format required by the ACOGAN model; and (7) predicting the RSS fingerprint of the specific position with fingerprint loss through the ACOGAN model.

Description

technical field [0001] The present invention mainly relates to the fields of deep learning and indoor positioning, and in particular to a method for estimating RSS missing values ​​based on an adaptive context generation confrontation model. Background technique [0002] In next-generation social applications, accurate, reliable and real-time indoor positioning protocols and services are required. With mobile devices, positioning systems can help determine the user's location and obtain feedback for location-based services such as tracking, monitoring, and navigation [1]. Although the Global Positioning System (GPS) is very mature in outdoor positioning, it is not suitable for indoor positioning, because the signal sent by GPS satellites will become very weak after passing through many buildings and walls. For accurate positioning [2]. Therefore, many indoor positioning technologies have been proposed such as infrared ultra-wideband (ultrawideband, UWB), ultrasonic (ultras...

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): H04W16/22H04W24/02H04W24/06
CPCH04W16/22H04W24/02H04W24/06
Inventor 任晓琪陶文源翁仲铭
Owner TIANJIN UNIV