Hybrid Ant Bee Algorithm for Fuzzy Expert System Based Sample Classification

Abstract

Accuracy maximization and complexity minimization are the two main goals of a fuzzy expert system based microarray data classification. Our previous Genetic Swarm Algorithm (GSA) approach has improved the classification accuracy of the fuzzy expert system at the cost of their interpretability. The if-then rules produced by the GSA are lengthy and complex which is difficult for the physician to understand. To address this interpretability-accuracy tradeoff, the rule set is represented using integer numbers and the task of rule generation is treated as a combinatorial optimization task. Ant colony optimization (ACO) with local and global pheromone updations are applied to find out the fuzzy partition based on the gene expression values for generating simpler rule set. In order to address the formless and continuous expression values of a gene, this paper employs artificial bee colony (ABC) algorithm to evolve the points of membership function. Mutual Information is used for idenfication of informative genes. The performance of the proposed hybrid Ant Bee Algorithm (ABA) is evaluated using six gene expression data sets. From the simulation study, it is found that the proposed approach generated an accurate fuzzy system with highly interpretable and compact rules for all the data sets when compared with other approaches.

EMOPS: an enhanced multi-objective pswarm based classifier for poorly understood cancer patterns

“…Hybrid Ant Bee Algorithm (HABA) [4], ii. Kernelized Fuzzy Rough Set Based Semi Supervised Support Vector Machine (KFRS-S3VM) [1] and iii.…”

“…Ant Colony Optimization [1], [4], [10], [26] does maintain a colony of ants and make possible Permissible Ranges (PRs) in association with values proposed for a design model. Here, each and every ant is permitted to select a Permissible Range which will represent the path.…”

“…Gene Expressions based validations have done in this Scheme, which shown in the detailed procedure [5], [25]. The Forward Greedy Search Algorithm based Gaussian Kernel Approximation [4], [18][19][20] was designed as follows.…”

“…These Gene Expressions have been usually used for Gene Pattern Classifications. From the available literature survey [1][2][3][4][5][6], it was noticed that the Data Mining Techniques are facilitating to classify and predict various Cancer Gene Patterns. The Classifiers are used to classify microarray samples for pattern classification.…”

“…ie the normal microarray sample data set and cancer pattern samples can be classified with the help of Classifiers [12][13][14][15][16]. If the samples had a few subtypes of cancer pattern, then we needed multiclass cancer pattern classifiers [1][2][3][4]. From the literature survey, it was noticed that the Multi-Class Cancer Pattern Classifier can be employed to improve the classification accuracy [17].…”