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

Cluster behavior learning method based on gene programming

A learning method and cluster technology, applied in the field of inverse modeling, can solve problems such as no breakthrough in the reverse evolutionary modeling method

Pending Publication Date: 2021-01-26
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The purpose of this patented technology allows for an algorithm called Genetic Programming (GP) to find solutions within certain spaces efficiently while avoids previous data or assumptions about how clusters move around. This makes it possible to better predict future movements based solely on past ones rather than relying only upon previously-existing models.

Problems solved by technology

Technological Problem: Current methods used by groups involved in team work cannot predict how well their members behave when interact with each other without being able to talk about them effectively during training sessions.

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
  • Cluster behavior learning method based on gene programming
  • Cluster behavior learning method based on gene programming
  • Cluster behavior learning method based on gene programming

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] Now in conjunction with example, accompanying drawing, the present invention will be further described:

[0045] Step 1: In order to illustrate the effectiveness of the present invention, this embodiment adopts simulation means to generate swarm movement data and inverts the swarm movement rules on this basis. Firstly, a simulation program is written to generate raw data of swarm movement for learning. The cluster movement model adopted is a variant of the Vicsek model. The movement velocity of each individual in the population described by this model is constant as v, and the individual only changes the direction of velocity during movement. Any individual, denoted as a i , updating its own motion direction at each moment to the average value of neighbor motion directions with random noise. The selection of neighbors is based on the distance ...

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 cluster behavior learning method based on gene programming, which utilizes a gene programming method to carry out heuristic search on a solution space without priori knowledge, and finally gives a neighbor selection mechanism and a behavior decision function which can well reflect a cluster real motion rule. Under the trend that a forward modeling means is generally adopted at present, a new path is found to learn cluster individual motion rules by adopting an inversion mode. Cluster behavior rule learning under the priori knowledge-free condition is achieved, the vacancy of the learning method in the field can be filled up, and the method can be used for learning of unmanned cluster behaviors and can also be used for research of biological cluster behaviors.

Description

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

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
Owner NORTHWESTERN POLYTECHNICAL 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