Hybrid ant lion mutated ant colony optimizer technique for Leukemia prediction using microarray gene data

• Published in: Journal of ambient intelligence and humanized computing Vol. 12; no. 2; pp. 2965 - 2973
• Main Authors: Santhakumar, D., Logeswari, S.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2021; Springer Nature B.V
• Subjects: Ant colony optimization; Artificial Intelligence; Cancer; Classification; Computational Intelligence; Data analysis; Engineering; Evolutionary algorithms; Feature selection; Gene expression; Leukemia; Methods; Mutation; Optimization algorithms; Original Research; Robotics and Automation; Searching; Sparsity; User Interfaces and Human Computer Interaction; Microarray data analysis; Ant Lion Optimization (ALO) algorithm; Ant Colony Optimization (ACO); A hybrid ant lion mutated ant colony optimizer technique
• ISSN: 1868-5137; 1868-5145
• DOI: 10.1007/s12652-020-02454-5

The classification of cancers is one of the most vital functions of Microarray data analysis. The classification of the gene expression profile is treated as a NP-Hard problem since it is a very demanding job. Compared to the individual search utilized by conventional algorithms, the population search utilized by Evolutionary Algorithm (EA) is visibly more beneficial. In feasible search areas, EA algorithms also are more likely to detect various optimums instantly. Evolutionary techniques which are inspired by nature perform exceptionally well and are extensively used for Microarray data analysis. Ant Colony Optimization (ACO) is a distinct intelligent optimization algorithm based on iterative optimization which uses ideas like evolution and group. ACO algorithm was developed by studying how ants identify paths while food foraging. Ant Lion Optimization (ALO) algorithm is proposed and employed as muted selection process and the ant lions to hunt process is simulated. A hybrid ant lion mutated ant colony optimizer technique is proposed in this work.