Mining and Interpretation of Critical Aspects of Infant Health Status Using Multi-Objective Evolutionary Feature Selection Approaches

The rate of infant mortality (IMR) in a population under one year age is marker for mortality. It major sensitive community’s overall physical health. Protecting the lives newborns has become challenging issue public health, development programs, and humanitarian initiatives. Almost 10.1% infants died United States America (USA) 2021. Therefore, this paper aims to extract understand various influential factors causing deaths USA. A crowding distance-based multi-objective ant lion optimization (MOALO-CD) proposed here with statistical evidence feature selection. technique compared competitive metaheuristic models such as genetic algorithm based on distance (MOGA-CD), filter approaches, recursive elimination. Various machine learning classifiers are applied selected subset obtained from MOALO-CD USA’s dataset. Extensive experimental results indicate that model outperforms existing approaches terms Generational Distance, Inverted Spread, Hyper volume. Also, comparative analysis reveals random forest achieves significantly better performance MOALO-CD.