Generating Compact Classifier Systems Using a Simple Artificial Immune System

Abstract

Abstract-Current artificial immune system (AIS) classifiers have two major problems: 1) their populations of B-cells can grow to huge proportions, and 2) optimizing one B-cell (part of the classifier) at a time does not necessarily guarantee that the B-cell pool (the whole classifier) will be optimized. In this paper, the design of a new AIS algorithm and classifier system called simple AIS is described. It is different from traditional AIS classifiers in that it takes only one B-cell, instead of a B-cell pool, to represent the classifier. This approach ensures global optimization of the whole system, and in addition, no population control mechanism is needed. The classifier was tested on seven benchmark data sets using different classification techniques and was found to be very competitive when compared to other classifiers.

RETRACTED ARTICLE: Diagnosing breast cancer with an improved artificial immune recognition system

“…Using Linear Discriminant Analysis (LDA) method, Ster and Dobnikar (1996) reported an accuracy of 96.8 %. Simplified Artificial Immune System (SAIS) was developed by Leung et al (2007). To ensure global optimization of AIS, this classifier was also tested on WBCD, the classification accuracy that was reported for this data set was 96.6 %.…”

Chaotic-based hybrid negative selection algorithm and its applications in fault and anomaly detection

“…The proposed method is compared to artificial negative selection classifier (ANSC) (Igawa & Ohashi, 2009), simple artificial immune system (SAIS) (Leung et al, 2007), particle swarm based negative selection algorithm (PSNSA) (Gao et al, 2007) and V- detector (Zhou & Dipankar, 2004) for same dataset. We compare two more important features of all immune models: average detection rate or classification accuracy (g-mean in CHNSA) and number of memory cells.…”

“…Three main components of AIS are negative selection algorithm (NSA), clone selection and immune network model (Igawa & Ohashi, 2009). Application domains of AIS are various and include anomaly and fault detection (Aydin, Karakose, & Akin, 2008;Forrest, Perelson, Allen, & Cherukuri, 1994), classification (Leung, Cheong, & Cheong, 2007), pattern recognition and optimization problems (de Castro & Zuben, 2002).…”

“…It has learning and adaptability features (Leung et al, 2007). Each AIS component is applied to a different engineering or scientific problem.…”

Consumer credit scoring using an artificial immune system algorithm

“…More specifically, this is achieved by randomly mutating the attributes of each clone created and storing them in a 3-dimensional array. Such an array is used because it is easier to store the attributes, classes and exemplars [24]. 3) Each mutant is then evaluated by using the classification performance.…”