AMCGWO : An enhanced feature selection based on swarm optimization for effective disease prediction

Abstract

Missing data in datasets remain as a difficulty in terms of data analysis in various research fields, especially in the medical field, as it affects the treatment and diagnosis that the patient should receive. An enhanced imputation model using MFWCP (Mode Fuzzy Weight based Canonical Polyadic) and BN (Bayesian Networks) is proposed with respect to the dependency between the attributes and the type of incomplete attributes in order to especially improve the prediction of breast cancer (BC) and heart disease. The proposed work, Adaptive Mean Chaotic Grey Wolf Optimizer (AMCGWO) helps to identify new subsets of feature including evaluation metrics that are used to score various subset of features from the missing data imputed dataset. Most feasible technique is to analyze each feature set for reduced error rate. The proposed technique outperformed in terms of precision, recall, f-measure, accuracy, specificity and Normalized Root Mean Square Error (NRMSE) values in CNN than existing classifiers like KNN (K-Nearest Neighbour), DT (Decision Tree) and ANFIS (Adaptive Neuro Fuzzy Inference System)

Subject Classification:

• 68W50 Evolutionary algorithms
• genetic algorithms (computational aspects)

Keywords:

• Heart disease
• Breast cancer
• Missing value imputation
• Bayesian network
• Mode Fuzzy Weight based Canonical Polyadic (MFWCP)
• Feature selection
• Adaptive Mean Chaotic Grey Wolf Optimizer (AMCGWO)