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

Novel artificial immune system and ant colony optimization-based detector set optimization method

A technology of artificial immunity and optimization method, applied in the field of artificial intelligence, can solve the problems of high time and space overhead and difficulty in guaranteeing accuracy, achieve the effect of small time and space overhead, improve accuracy, and avoid a lot of time and space overhead

Inactive Publication Date: 2011-05-25
JIANGSU UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the problems of the existing detector set optimization algorithm in the artificial immune system, such as large time and space overhead and difficulty in ensuring accuracy, provide an efficient detector set optimization method, and construct a new artificial immune system

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
  • Novel artificial immune system and ant colony optimization-based detector set optimization method
  • Novel artificial immune system and ant colony optimization-based detector set optimization method
  • Novel artificial immune system and ant colony optimization-based detector set optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 As shown, a new type of artificial immune system, including a candidate detector set generation device, a candidate detector pheromone management device, a detector set optimization device, an autologous set storage device, an initial detector set storage device, and a candidate detector set storage device , the antigen management device to be inspected and the detector set storage device required for antigen inspection.

[0043] The candidate detector set generation device includes an initial detector generation module and a candidate detector selection module, and the initial detector generation module is used to generate a non-repetitive binary string of length L as the initial detector. The candidate detector selection module is used to select those initial detectors that do not match the self to form a candidate detector set.

[0044] The candidate detector pheromone management device includes a candidate detector pheromone calculation module and ...

Embodiment 2

[0052] A detector set optimization method based on ant colony optimization, comprising the following steps:

[0053] 1) Generate all possible detectors to construct a candidate detector set;

[0054] 2) Calculate the pheromone for each candidate detector;

[0055] 3) Part of the candidate detectors are regularly selected as the detectors used to check the antigen.

[0056] Step 1) specifically comprises the following steps, as figure 2 Shown:

[0057] 1.1) Define the variable L to represent the length of the detector, which is assumed to be 8;

[0058] 1.2) Set the matching degree threshold P as the basis for judging whether the detector is effective, assuming it is 6;

[0059] 1.3) Randomly build a binary string whose length is L (value 8) as the initial detector;

[0060] 1.4) Generate an initial detector;

[0061] 1.5) Calculate the maximum length of the corresponding position and the same substring between all self-body and the initial detector, if there is no occur...

Embodiment 3

[0076] Suppose the known self is: self A: 000; self B: 001;

[0077] According to step 1, it is assumed that the detector length L is 3; the matching degree threshold P is 2;

[0078] Assuming that the initial detector 000 is generated first, the maximum lengths of the corresponding and identical substrings between the self AB and the initial detector are 3 and 2, respectively.

[0079] Since there is a value not less than P, go to step 1.3, assume that the initial detector 001 is generated, and the maximum lengths of the corresponding and identical substrings between the self AB and the initial detector are 2 and 2 respectively.

[0080] Since there is a value not less than P, go to step 1.3, assume that the initial detector 010 is generated, and the maximum lengths of the corresponding and identical substrings between the self AB and the initial detector are 1 and 1 respectively. Since there is no value not less than P, the initial detector 010 is taken as a candidate detec...

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 aims to solve the problem that pay expenses of time and space are high, the problem that the accuracy is difficult to ensure and the like in the conventional detector set optimization algorithm in an artificial immune system, provides a high-efficiency detector set optimization method and constructs a novel artificial immune system.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, relates to an artificial immune system therein, and in particular relates to an optimization method of a detector in the artificial immune system. Background technique [0002] The artificial immune system uses detectors to identify non-self, so how to generate and optimize the detector set is the main problem related to the performance and accuracy of the artificial immune system. At present, there are many mature methods for generating detector sets, but there are still few optimization algorithms for detector sets. [0003] The current artificial immune system mainly uses the immune feedback algorithm when optimizing the detector set, periodically changes the detector according to the matching between the checked antigen and each detector, and regenerates a new detector with a higher matching degree with the checked antigen Replace existing detectors. When generating a new detector, it...

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): G06N3/00
Inventor 蔡涛牛德姣刘扬宽
Owner JIANGSU 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