Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Combination Method of Evidence Based on Evidence Measurement Criteria

A technology of measurement standards and combination methods, applied in the field of multi-sensor information fusion, can solve the problems of unreasonable evidence distribution, fusion results and factual results, and achieve the effect of reasonable distribution

Inactive Publication Date: 2021-06-25
JILIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to overcome the unreasonable distribution of evidence in the DS evidence combination and the conflict between the fusion result and the factual result of the DS evidence theory when merging high-conflict evidence, and provide an evidence based on evidence measurement standard combination method

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
  • Combination Method of Evidence Based on Evidence Measurement Criteria
  • Combination Method of Evidence Based on Evidence Measurement Criteria
  • Combination Method of Evidence Based on Evidence Measurement Criteria

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0090] 1. Deployment of sensors

[0091] Install a sensor group consisting of temperature sensor, humidity sensor, smoke concentration sensor, carbon monoxide concentration sensor and infrared sensor in the corner of a room;

[0092] The sensor group uploads the collected data to the control layer through the ZigBee network, and the ZigBee coordinator in the control layer sends the data in the sensor group to the main control board STM32F103. processing, and then carry out evidence combination; preprocessing first organizes the data transmitted by each type of sensor into a fire identification framework Θ={A=no fire, B=fire, C=uncertain} based on empirical data, and each type of sensor The collected data will eventually be processed into the probability of occurrence of elements within the fire identification framework;

[0093] Temperature sensor: m 1 (A) = 0.5, m 1 (B)=0.2, m 1 (C)=0.3;

[0094] Smoke density sensor: m 2 (A) = 0.0, m 2 (B) = 0.8, m 2 (C)=0.2;

[009...

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 combination method of evidence based on a new evidence measurement standard, which overcomes the problems of unreasonable distribution of evidence in the prior art and the contradiction between combination results and factual results. The method: 1. Deployment of sensors: in the room A sensor group composed of various types of sensors is installed in the corner of the wall, among which various types of sensors include temperature sensors, humidity sensors, smoke concentration sensors, carbon dioxide concentration sensors, and infrared sensors; 2. Establish a new evidence conflict measurement standard Pcor: 3. Determine the weight coefficient of each evidence: construct a support matrix according to the Pcor value of each evidence conflict measurement standard, establish the trust degree according to the support matrix, and finally use the trust degree to establish the weight coefficient of each evidence; 4. Evidence combination: adjust the basic probability assignment vector according to the weight coefficient, and combine through DS evidence theory to get a more reasonable conclusion.

Description

technical field [0001] The invention relates to a method belonging to the field of multi-sensor information fusion, more precisely, the invention relates to an evidence combination method based on the evidence measurement standard. Background technique [0002] Multi-sensor information fusion technology is to optimize and comprehensively process the data provided by each sensor, so as to achieve a more accurate and reliable judgment of the observation target. Due to the increasing and complex measurement data of the monitoring system, the data provided by only one sensor cannot meet the reliability requirements. In addition, the monitoring work is sometimes carried out in a harsh environment, and the sensor may not work properly. . Therefore, people naturally think of using multiple sensors to monitor different physical quantities, such as using temperature sensors to monitor temperature changes, and vibration sensors to monitor vibrations. Then how to combine the data prov...

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): G06K9/62H04W4/38
CPCH04W4/38G06F18/25
Inventor 杨晓萍廉伟健李孟杰李娟陈雪莹李莉
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com