NSSAC: Negative selection-based self adaptive classifier

In this paper, a novel algorithm for classification called "NSSAC" is proposed, which is based on negative selection method in the human immune system. Artificial immune based classifiers have two important challenges: (1) the recognition distance threshold which choosing an appropriate re...

Full description

Saved in:
Bibliographic Details
Main Authors: Fakhari, S. N. S., Moghadam, A. M. E.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Artificial immune system (AIS)
classification
Classification algorithms
detector generation algorithm
Detectors
Immune system
Machine learning algorithms
negative selection algorithm
recognition distance threshold
Testing
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a novel algorithm for classification called "NSSAC" is proposed, which is based on negative selection method in the human immune system. Artificial immune based classifiers have two important challenges: (1) the recognition distance threshold which choosing an appropriate recognition distance threshold is a difficult task because it necessitates the understanding of the data set in detail, (2) A detector generation algorithm that all classifiers used randomized algorithm to generate memory cell. In this paper for resolve above problems a deterministic algorithm is used to generate memory cell and an adaptive method is used for calculation the recognition distance threshold. Therefore the generated detectors have a good quality of the distribution and on the other hand, NSSAC can be adapted automatically to each data set. The classifier was tested on three benchmark data sets and the results show that our algorithm is useful for classification problems.
DOI:10.1109/INISTA.2011.5946064