Supercharge Your Innovation With Domain-Expert AI Agents!

Airborne object recognition method based on feature weighted Bayesian optimization algorithm

A feature weighting and optimization algorithm technology, applied in the field of machine learning, can solve the problems of low accuracy rate, achieve the effect of improving accuracy rate, reducing condition dependence, and improving target type recognition accuracy rate

Active Publication Date: 2022-05-17
HARBIN ENG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is aimed at the limitations of the conditional independence assumptions between the features of the Naive Bayesian network, taking the distribution of feature overlapping parts as the basis for feature weighting, and optimizing the Bayesian network by means of feature weighting, intending to solve The existing methods for identifying flying objects in the air have the problem of low accuracy

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
  • Airborne object recognition method based on feature weighted Bayesian optimization algorithm
  • Airborne object recognition method based on feature weighted Bayesian optimization algorithm
  • Airborne object recognition method based on feature weighted Bayesian optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0033] Specific implementation mode one: combine figure 1 Describe this implementation mode:

[0034] The method for identifying flying objects in the air based on the feature weighted Bayesian optimization algorithm described in this embodiment comprises the following steps:

[0035] Step 1. Construct a naive Bayesian network structure, and determine the features and flying object category targets included in the model:

[0036] The constructed network structure is an undirected graph G of a root node, G=(V, E) is composed of a network node set V and an edge set E between nodes, and the node set V={v i |0≤i≤n}, n>0; edge set E={e i |1≤i≤m}, m>0, the edge is used to represent the relationship between nodes; where v0 is the root node of the network structure, representing the target category of the flying object, and the category target set includes rotary-wing aircraft, fixed-wing aircraft, jet aircraft, etc.; i≥1 corresponds to v i The leaf nodes in the network structure r...

Embodiment

[0049] The category target is identified through the input features. In this embodiment, the input features include the flying speed, height and image entropy of the time-frequency domain map of the flying object.

[0050] First, analyze the data distribution characteristics of the corresponding features of the flying objects in the air. It is not difficult to find that the distribution intervals formed by targets of different categories on the same feature may overlap, they may overlap with each other, or there may be overlapping parts at the same time, of course, there may be non-overlapping situations between features, specifically The situation needs to be analyzed with real data. If the data density of the overlapping part is smaller than the data density of the non-overlapping part, although there is an overlapping part, most of the data are still in their own independent distribution, the category target is clear, and easy to identify, then using this feature as the cla...

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

A method for identifying flying objects in the air based on a feature-weighted Bayesian optimization algorithm relates to a method for identifying flying objects in the air. The invention aims to solve the problem of low accuracy existing in the existing methods for identifying flying objects in the air. The present invention analyzes the distribution of feature data of flying objects in the air, uses the distribution span and distribution density in the distribution of feature overlapping parts as the basis for calculating the weight of features, and uses them as the weight of input features of the naive Bayesian recognition model , and then based on the results of the feature-weighted Bayesian optimization algorithm, the recognition of flying objects in the air is realized. The main purpose is identification of flying objects.

Description

technical field [0001] The invention belongs to the field of machine learning, and in particular relates to a method for identifying flying objects in the air. Background technique [0002] The identification of flying objects in the air is realized based on the target characteristics of the flying objects in the air, mainly by obtaining the data of the flying objects in the air through various sensors, and then converting them into numerical target characteristics through signal processing technology, and analyzing the target characteristics Get the category target it belongs to. The main problems in this process are huge data volume, complex data format, data processing speed and other issues that need to be solved urgently. Therefore, some methods based on template recognition, expert system, supervised learning, and statistics have been applied to the process of aerial object recognition, which has greatly improved the data processing speed and improved the analysis eff...

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): G06K9/62G06N20/10
CPCG06N20/10G06F18/2411G06F18/29Y02T90/00
Inventor 周连科邵璐张耘王红滨王念滨张毅赵昱杰崔琎
Owner HARBIN ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com