Breast Cancer Prediction using Genetic Algorithm via Mixed Radial Basis Function Neural Network

Predicting breast cancer poses a challenge in the field of medical data analysis. Healthcare professionals, including doctors and pathologists, necessitate automated tools to aid in decision-making and to distinguish between malignant and benign tumors. The radial basis function neural network is a feedforward artificial neural network employing radial basis functions as activation functions in the hidden layer. In this paper, we present a novel model aimed at optimizing the selection of radial basis functions, centers, variances, and weights for the output layer. The optimization problem is structured as a mixed-variable optimization problem with linear constraints. To address this challenge, the authors suggest employing a genetic algorithm-based approach. Subsequently, this methodology is applied to breast cancer prediction, utilizing the optimized parameters to enhance the overall performance of the model.