Abstract: Building an accurate fuzzy expert system will improvise the classification of microarray data and reduces the complexity. Modern practice in the classification of microarrays’ data has two main limitations: (1) the dependability of the training data sets for building classifiers, (2) the model to be classified does not fit in to any of the existing classes. Medical thermography is very useful in a variety of medical applications as well as the detection of breast cancer by identifying the local temperature and the elevated metabolic commotion of cancer cells. Distinct conventional expert systems, which are mainly symbolic reasoning engines, fuzzy expert systems are oriented toward numerical processing. To address the interpretability-accuracy trade-off, the system proposes hybrid Ant Bee Algorithm (ABA) and it is evaluated using six gene expression data sets.
Keywords: Microarray data, fuzzy expert system, ant colony optimization, artificial bee colony, mutual information.