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

A spatial complexity classification method and device based on unsupervised learning

An unsupervised learning and complexity technology, applied in the direction of instrumentation, computing, character and pattern recognition, etc., can solve problems such as uninterpretable, training overfitting, sparse samples, etc., to avoid the curse of dimensionality, dense data distribution, reduce The effect of small dependencies

Active Publication Date: 2021-03-23
BEIHANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In short, the existing technology relies on the prior knowledge of manual calibration. Although it can learn and classify the complexity of the airspace, this classification is not interpretable, and it is impossible to understand the inherent characteristics and structure of the airspace situation data.
In addition, due to the high dimensionality of 28-dimensional data, existing methods that directly learn and train 28-dimensional data are prone to problems such as disaster of dimensionality, sparse samples, and training overfitting.
Relying on controllers for sample calibration will also consume a lot of manpower and time resources

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
  • A spatial complexity classification method and device based on unsupervised learning
  • A spatial complexity classification method and device based on unsupervised learning
  • A spatial complexity classification method and device based on unsupervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032]The invention will be described in detail below with reference to the accompanying drawings and examples.

[0033](1) Airspace complexity classification method based on non-supervised learning, such asfigure 1 ,3Down:

[0034]Step 1: Collect the airspace trend sample set;

[0035]Get the null domain sample sample to be processed, form a null sample sample set (simply sample set), the sample set, the sample set, the sample is a sample (k is the positive integer starting from 1), where each sample contains a nozzle to be processed in one 28 empty field status value X in unit timei(Specifications) (1 ≤ i ≤ 28, i∈z), the feature described herein refers to the attribute factors that reflect the flight track distribution, airspace route structure, air traffic operation rules, etc. Expressed with a continuous or discrete number value, it is also referred to as a complexity factor descriptive diameter complexity. Each sample is calibrated with a complexity classification label (referred to as ...

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 relates to an airspace complexity classification method and device based on unsupervised learning, which belongs to the technical field of airspace situation assessment and classification, and includes the following steps: step 1, collecting a sample set of airspace situation to be processed; step 2, removing deviation and standardizing the airspace Situation sample set; Step 3, perform PCA dimension reduction processing on the airspace situation sample set; Step 4, perform k-Means clustering processing on the low-dimensional sample set; Step 5, define the complexity category of the clustered data cluster. The device includes: sample input module; feature extraction module; feature dimensionality reduction module; prototype comparison module; complexity output module. The evaluation of airspace complexity through the present invention does not depend on the prior knowledge of calibration, and can directly learn the internal characteristics and structure of airspace situation data, so that the classification of airspace complexity can be interpreted, greatly reducing the manpower and time of calibration data cost.

Description

Technical field[0001]The present invention belongs to the field of null domain situation assessment classification, involving a classification method and apparatus for airspace complexity, specifically, refers to a diastomy complexity classification method and apparatus based on an undo-monitoring learning.Background technique[0002]With the rapid development of my country's aviation transportation industry, the amount of aviation traffic increased by the flight, the flight year-on-year, the air traffic flow continues to grow, and the aerial operation trend is more complicated. These circumstances have enabled air traffic control staff to increase the risk of operations, and thereby become an important reason for flight delays and regulatory accidents.[0003]In the current air traffic management system, the sector is a fundamental basic unit that controls the aircraft. In order to ensure efficient operation of the entire air pipe system, the existing means is to take regulation and co...

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): G06K9/62
CPCG06F18/2135G06F18/23213
Inventor 曹先彬杜文博朱熙李碧月李宇萌
Owner BEIHANG 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