Affiliations: [a] Department of Electronic and Computer Engineering, School of Engineering and Design, Brunel University, West London, UK | [b] Computer Science Department, Gulf University for Science and Technology, Mishref, Kuwait
Correspondence:
[*]
Corresponding author: Jamal Al-Enzi, Department of Electronic and Computer Engineering, School of Engineering and Design, Brunel University, West London UB8 3PH, UK. E-mail: [email protected].
Abstract: This paper introduces a new ensemble based on different artificial immune algorithms and it is optimized by using a Particle Swarm algorithm. The new proposed architecture of the ensemble introduces a major enhancement to the data classification. The main focus of this paper is devoted for building an ensemble model that integrates three different AIS techniques towards achieving better classification results. A new AIS-based ensemble architecture with adaptive learning features is proposed by integrating different learning and adaptation techniques to overcome the limitations of the individual algorithms and to achieve synergistic effects through the combination of these techniques. Furthermore, a new method for measuring confidence level of AIS based classifier is introduced in this work as well. On the other hand and in order to enhance the overall performance of the classification process, an optimizer using particle swarm optimization algorithm is going to be adopted. The performance of the proposed ensemble is tested by running several experiments using different medical datasets.
Keywords: Artificial immune systems, classification and clustering, adaptive learning, PSO
