Red Fox Optimizer with Data-Science-Enabled Microarray Gene Expression Classification Model

Microarray data examination is a relatively new technology that intends to determine the proper treatment for various diseases and precise medical diagnosis by analyzing massive number of genes in experimental conditions. The conventional classification techniques suffer from overfitting high dimensionality gene expression data. Therefore, feature (gene) selection approach plays vital role handling Data science concepts can be widely employed several problems, they identify different class labels. In this aspect, we developed novel red fox optimizer with deep-learning-enabled microarray (RFODL-MGEC) model. presented RFODL-MGEC model aims improve performance selecting appropriate features. uses (RFO)-based deriving an optimal subset Moreover, involves bidirectional cascaded deep neural network (BCDNN) classification. parameters involved BCDNN technique were tuned using chaos game optimization (CGO) algorithm. Comprehensive experiments on benchmark datasets indicated accomplished superior results subtype classifications. was found effective identification classes high-dimensional small-scale