Simultaneous feature weighting and parameter determination of Neural Networks using Ant Lion Optimization for the classification of breast cancer

摘要: Abstract In this paper, feature weighting is used to develop an effective computer-aided diagnosis system for breast cancer. Feature employed because it boosts the classification performance more as compared subset selection. Specifically, a wrapper method utilizing Ant Lion Optimization algorithm presented that searches best weights and parametric values of Multilayer Neural Network simultaneously. The selection hidden neurons backpropagation training algorithms are parameters neural networks. proposed approach evaluated on three cancer datasets. data initially normalized using tanh remove effects dominant features outliers. results show has better ability attain higher accuracy existing techniques. obtained high validates work which potential becoming alternative other well-known