Data restoration method for wireless sensor networks based on spatio-temporal feature fusion

A wireless sensor and network data technology, which is applied to services based on specific environments, organization of data transmission to avoid errors, wireless communication, etc. It can solve the problems of many iterations and low repair accuracy, and achieve the effect of good repair performance.

Active Publication Date: 2021-11-09
GUILIN UNIV OF ELECTRONIC TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the existing sensor network data repair method has many iterations and low repair accuracy, the present invention provides a wireless sensor network data repair method based on spatio-temporal feature fusion

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
  • Data restoration method for wireless sensor networks based on spatio-temporal feature fusion
  • Data restoration method for wireless sensor networks based on spatio-temporal feature fusion
  • Data restoration method for wireless sensor networks based on spatio-temporal feature fusion

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0081] The first experimental data set is the hourly temperature data of major cities in the United States on August 1, 2010. The spatial domain graph signal model of the dataset is as figure 2 As shown in , the length of the vertical line in the vertical direction of each node indicates the signal strength of the node. There are 218 nodes (cities) in the network, including temperature values ​​at 24 moments, the minimum value is 49.3℉, and the maximum value is 103.9℉. We connect each node in the sensor network with its 5 nearest nodes, and select a certain moment to connect with the previous 4 consecutive moments, so as to establish a joint domain graph model of the test data. Randomly select a certain moment, and test 50 times under different loss ratios. The method of the present invention is compared with a network data restoration method (GTVM method) based on a total variation minimization of graph signals proposed by Siheng Chen et al. in 2016. The simulation result...

example 2

[0088] The second experimental data set is data from some sea surface temperature monitoring stations around the world. There are 100 detection stations in the network, and the data collected at 1733 moments, ranging from 0.01°C to 30.72°C, the spatial domain diagram signal model of the data set is as follows: image 3 shown. The joint domain graph model of network data is the same as the design in Simulation Example 1. The simulation experiment also compares the restoration methods in the case of 5 different loss ratios. The method of the present invention is compared with a network data repair method (GTVM method) based on a total variation minimization of graph signals proposed by Siheng Chen, AliakseiSandryhaila, etc. in 2016. The results of the experimental simulation are shown in Table 3 and Table 4.

[0089] The root mean square error (RMSE) contrast of table 3 inventive method and GTVM method

[0090]

[0091] Table 4 Convergence iterations (CIC) comparison betw...

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 wireless sensor network data restoration method based on spatio-temporal feature fusion. First, a joint domain graph model is established based on the fusion of the time domain graph model and the space domain graph model of network data, and then the joint domain graph model is established according to the network data in the joint domain graph model. Based on the strong correlation of node data, an iterative convergence algorithm is designed to achieve the goal of repairing wireless sensor network data. The simulation experiment shows that, compared with the prior art, the network data restoration algorithm introduced by the present invention has higher restoration accuracy and fewer convergence iterations, and has good restoration performance. The invention provides a simple and effective solution for realizing data restoration in the wireless sensor network.

Description

technical field [0001] The invention relates to the technical field of wireless sensor networks, in particular to a method for repairing wireless sensor network data based on spatio-temporal feature fusion. Background technique [0002] In recent years, the application of wireless sensor networks has become more and more extensive, and it is gradually becoming an indispensable part of people's production and life. The wireless sensor network is generally composed of a large number of low-cost micro-monitoring sensor nodes, which can monitor the environmental indicators of the target within a certain area, and transmit the measurement indicators obtained by each sensor to the database of the central processing unit through the wireless network, so that Realize tasks such as scene monitoring and analysis. However, due to various reasons such as limited capabilities of sensor nodes and electromagnetic interference, data collected by sensor networks may be lost. In order to en...

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): H04W4/38H04W28/04H04L1/00
CPCH04L1/0078H04W28/04H04W4/38
Inventor 蒋俊正杨杰赵海兵杨圣李龙斌李杨剑
Owner GUILIN UNIV OF ELECTRONIC 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