Semi-supervised fingerprint positioning algorithm based on manifold regularization

A fingerprint positioning and semi-supervised technology, applied in computing, computing models, computer components, etc., can solve the problem of high cost and achieve the effect of reducing positioning costs

Inactive Publication Date: 2017-12-01
JIANGNAN UNIV
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the traditional fingerprint location algorithm has a high cost when collecting training data, and propose a semi-supervised fingerprint location algorithm based on manifold regularization (manifold regularizationextreme learning machine, referred to as MR-ELM)

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
  • Semi-supervised fingerprint positioning algorithm based on manifold regularization
  • Semi-supervised fingerprint positioning algorithm based on manifold regularization
  • Semi-supervised fingerprint positioning algorithm based on manifold regularization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described below in conjunction with specific drawings and embodiments.

[0046] The traditional fingerprint localization algorithm is expensive to collect labeled training data, so this paper proposes a semi-supervised fingerprint localization algorithm based on manifold regularization; this algorithm makes full use of a large amount of unlabeled data, reduces the workload of collecting labeled data, and Inherited the advantages of extreme learning machine without iteration and efficient model execution;

[0047] Extreme learning machine or ELM (extreme learning machine) is a machine learning algorithm based on a single hidden layer feedforward neural network proposed by Huang et al.; this algorithm abandons the iterative adjustment strategy of the gradient descent algorithm, and generates implicit The input weight and offset of the layer are used to calculate the corresponding output weight matrix, which is faster than the traditio...

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 provides a semi-supervised fingerprint positioning algorithm based on manifold regularization. The algorithm comprises the following steps: 1, training data with a tag and training data without a tag acquired from an actual environment together serve as a semi-supervised learning training data set; 2, a graph Laplacian operator is built in input space of the training data with the tag and the training data without the tag; 3, a Gauss kernel function is introduced to calculate the weight matrix of an adjacent graph; and 4, a manifold regularization frame and an extreme learning machine with random feature mapping are combined to solve a hidden layer output weight matrix, and a position estimation model is built. The manifold regularization frame and the extreme learning machine are combined, the easily-acquired training data without the tag are used thoroughly, and the positioning cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of wireless sensor networks, and relates to a semi-supervised fingerprint positioning algorithm based on manifold regularization. Background technique [0002] In recent years, as people's demand for indoor location-based services has become increasingly urgent, indoor positioning technology has received extensive attention. Among them, the fingerprint positioning method has gradually become a research hotspot in indoor positioning technology due to its advantages of easy deployment, high precision, and non-line-of-sight. The method is mainly divided into two stages: offline training and online positioning. In the offline training phase, the actual application scene is first divided into regular grids at a certain interval, and then a certain amount of received signal strength (RSS) is collected on each grid to build a location fingerprint database, and use the machine The learning algorithm constructs the...

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): G06K9/62G06N3/04G06N3/08G06N99/00
CPCG06N3/08G06N20/00G06N3/047G06F18/2155
Inventor 卢先领朱顺涛
Owner JIANGNAN 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