Mobile sensor network noise reduction and calibration method based on Bayesian network

A Bayesian network and mobile sensor technology, applied in network topology, electrical components, wireless communication, etc., can solve problems such as sensor data drift, achieve data recovery rate improvement, system error reduction, and solve the effect of function calibration

Inactive Publication Date: 2017-05-31
德清云浩电子科技有限公司
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a mobile sensor network noise reduction and calibration method based on the Bayesian network, which solves the problems of sensor data drift and function calibration, and at the same time detects and corrects outliers through the correlation of different types of sensors

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
  • Mobile sensor network noise reduction and calibration method based on Bayesian network
  • Mobile sensor network noise reduction and calibration method based on Bayesian network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical scheme of the present invention will be further described below in conjunction with the accompanying drawings of the description:

[0020] like Figure 1~2 As shown, the present invention provides a specific embodiment of a Bayesian network-based mobile sensor network noise reduction and calibration method, specifically comprising the following steps:

[0021] Step 1: Divide the data set into a training set and a verification set, where the training set is represented by A and the verification set is represented by B. The training set A is a set composed of randomly selecting 80% of the data in the entire data set according to defined features (including temperature, humidity, concentration of different pollutants, etc.). It is mainly used to estimate the values ​​of the parameters in the Bayesian network conditional probability table through the maximum likelihood method. The verification set B is composed of the remaining 20% ​​data, which is mainly us...

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 mobile sensor network noise reduction and calibration method based on a Bayesian network. The method comprises the following steps: firstly dividing a data set into a training set and a verifying set, and then preprocessing data (noise reduction and smoothness), and training the Bayesian network at the same time; and processing a produced estimation real value through the Bayesian network, and verifying a sensor through a verifying algorithm. The problems of sensor data drifting and function calibration are solved, and an abnormal value is detected and corrected through the relevancy of different types of sensors. The experimental comparison shows that the system error in the network can be greatly lowered, and the data recovery rate of the sensor is greatly improved.

Description

technical field [0001] The invention relates to the field of mobile sensor networks and the like, and is a noise reduction and calibration method for mobile sensor networks based on Bayesian networks. Background technique [0002] Mobile sensor network is one of the research hotspots in the field of IT at present, and there is a wide market demand for real-time perception and real-time monitoring of object information in various environments. There are some problems in the traditional sensor monitoring system, such as sensor data drift and so on. The drift of the sensor will affect many functions of the sensor, resulting in an exponential increase in error; if the function calibration and data calibration of the sensor are not processed in time, it will cause noise and interference to the monitoring of the entire sensor network ; Outlier detection and correction in the sensor network, correct processing of outliers can ensure more accurate data accuracy of the entire sensor...

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): H04W24/02H04W84/18
CPCH04W24/02H04W84/18
Inventor 翔云
Owner 德清云浩电子科技有限公司
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