Meta-heuristic optimization algorithms based feature selection for clinical breast cancer diagnosis

TL;DR: This study proposes a two-step system using meta-heuristic algorithms (whale, greywolf, flower pollination, and moth flame) for feature selection in breast cancer diagnosis, achieving high accuracy and efficiency in classification tasks.

Abstract: Breast cancer is the leading cause of cancer death among women in the whole world. Meanwhile, early detection andaccurate diagnosis can increase the chances of making the right decision on a successful treatment process. This articlepresents a two-step system that rst uses four dierent swarm algorithms namely; whale optimization algorithm, greywolf optimizer, ower pollination algorithm, and moth ame optimization for feature selection purpose. Then, severalclassiers are applied including support vector machines, k-nearest neighbor, and decision tree. The performance of eachalgorithm is evaluated using ve dierent aspects; classication based measurements, convergence, computational time,statistical measurements and stability. The obtained results from the proposed algorithms are compared and analyzedwith other algorithms published in breast cancer diagnosis. The experimental using Wisconsin breast cancer diagnosisand Wisconsin prognosis breast cancer (WPBC) datasets outcomes positively that the proposed system was eective inundertaking breast cancer data classication and features selection tasks