Discriminating Self from Non-Self with Finite Mixtures of Multivariate Bernoulli Distributions
Affinity functions are the core components in negative selection to discriminate self from non-self. It has been shown that affinity functions such as the r-contiguous distance and the Hamming distance are limited applicable for discrimination problems such as anomaly detection. We propose to model self as a discrete probability distribution specified by finite mixtures of multivariate Bernoulli distributions. As by-product one also obtains information of non-self and hence is able to discriminate with probabilities self from non-self. We underpin our proposal with a comparative study between the two affinity functions and the probabilistic discrimination.
Discriminating Self from Non-Self with Finite Mixtures of Multivariate Bernoulli Distributions
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO)
Authors: | Thomas Stibor |
Year/month: | 2008/ |
Booktitle: | Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) |
Publisher: | ACM |
Fulltext: |
Abstract |
|
Affinity functions are the core components in negative selection to discriminate self from non-self. It has been shown that affinity functions such as the r-contiguous distance and the Hamming distance are limited applicable for discrimination problems such as anomaly detection. We propose to model self as a discrete probability distribution specified by finite mixtures of multivariate Bernoulli distributions. As by-product one also obtains information of non-self and hence is able to discriminate with probabilities self from non-self. We underpin our proposal with a comparative study between the two affinity functions and the probabilistic discrimination. |
Bibtex:
@inproceedings {author = { Thomas Stibor},
title = { Discriminating Self from Non-Self with Finite Mixtures of Multivariate Bernoulli Distributions },
year = { 2008 },
booktitle = { Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) },
publisher = { ACM },
}