A Hybrid Metaheuristics based technique for Mutation Based Disease Classification

Due to recent advancements in computational biology, DNA microarray technology has evolved as a useful tool the detection of mutation among various complex diseases like cancer. The availability thousands datasets makes this field an active area research. Early cancer can reduce mortality rate and treatment cost. Cancer classification is process provide detailed overview disease microenvironment for better diagnosis. However, gene suffer from curse dimensionality problems also models are prone be overfitted due small sample size large feature space. To address these issues, authors have proposed Improved Binary Competitive Swarm Optimization Whale Algorithm (IBCSOWOA) classification, which IBCSO been employed informative subset originated using minimum redundancy maximum relevance (mRMR) filter method. IBCSOWOA technique tested on artificial neural network (ANN) model whale optimization algorithm (WOA) used parameter tuning model. performance six different mutation-based compared with existing prediction methods. experimental results indicate superiority over nature-inspired methods terms optimal subset, accuracy, convergence rate. illustrated above 98% accuracy all highest 99.45% Lung dataset.