Information uncertainty condition target intention recognition method based on evidence forest

A technology of target intention and identification method, which is applied in the field of target intention recognition under the information uncertainty condition based on evidence forest, can solve problems such as limited accuracy, and achieve the effect of improving accuracy

Pending Publication Date: 2021-07-27
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Limited accuracy when faced with uncertain classification problems

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
  • Information uncertainty condition target intention recognition method based on evidence forest
  • Information uncertainty condition target intention recognition method based on evidence forest
  • Information uncertainty condition target intention recognition method based on evidence forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Below in conjunction with embodiment the method of the present invention is described in further detail.

[0048] Such as figure 1 Shown, the present invention comprises the following steps:

[0049] Step 1. Data preprocessing:

[0050] Step 101: Input n target training samples, including attribute feature vector X=[X 1 , X 2 ,...,X v ], where v is the number of attributes, X i , i=1, 2, ..., v represents the measurement value of each attribute feature, corresponding to the intention Y of each sample, and the identification frame of Y is Θ Y ={Y 1 , Y 2 ,...,Y w}, w represents the number of intents in the recognition frame;

[0051] In actual use, the attribute characteristics of the target include {speed X 1 , distance X 2 , height X 3 , heading angle X 4}, the categories of intents include {Attack Y 1 , Scout Y 2 , Cruise Y 3 , retreat Y 4 , other Y 5};

[0052] Step 102: establish a Gaussian fuzzy number f[C: (μ, δ)] for each attribute feature, μ a...

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 an information uncertainty condition target intention recognition method based on an evidence forest. The method comprises the following steps: step 1, preprocessing data ; step 2, constructing a reliability decision tree; step 3, constructing an evidence forest based on a reliability decision tree; and 4, performing intention recognition by using the constructed evidence forest. According to the method, an uncertainty information entropy calculation method based on evidence similarity is provided, meanwhile, the influence of the weight of each belief decision tree in an evidence forest is fully considered, a weight calculation method based on the possibility theory is provided, and the result of each belief decision tree is combined through weighted average, and finally, a final result through evidence self-combination is obtained. According to the method, on the premise of ensuring the intention recognition accuracy, the target intention recognition problem with uncertain information can be well solved.

Description

technical field [0001] The invention belongs to the technical field of target intent recognition, and in particular relates to a target intent recognition method based on evidence forests under uncertain information conditions. Background technique [0002] Goal intention refers to the basic assumption and preset behavior that the target hopes to achieve a certain purpose, and the preset behavior here refers to the result that the target plans or is scheduled to achieve. Battlefield target tactical intention recognition is the process of combining target information obtained from various information sources in a special combat environment, and then effectively analyzing the battlefield situation and enemy tactical intentions. In the process of target intention recognition, the information obtained by the information source is largely uncertain, so how to deal with this uncertain information is a current problem. [0003] Among the existing machine learning algorithms, the d...

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): G06K9/62G06N3/00
CPCG06N3/006G06F18/2411G06F18/214
Inventor 蒋雯李新宇邓鑫洋张瑜
Owner NORTHWESTERN POLYTECHNICAL 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