A two-stage feature selection approach using hybrid quasi-opposition self-adaptive coati optimization algorithm for breast cancer classification

Abstract

Breast cancer (BC) is one of the leading causes of high mortality rates among women. An early disease diagnosis is crucial in breast cancer’s treatment for improving the survival rate of people who have been afflicted. Human error, incorrect diagnoses, and insufficient time make manual techniques for breast cancer diagnosis ineffective and inefficient. An automated breast cancer diagnosis system assists the medical expert in diagnosing the cancer at its earliest stage. When attempting to investigate all aspects (high dimensionality) of the medical records, the automated diagnosis system faces significant challenges. It reduces the success rate of the diagnosis system. This study presents a two-stage feature subset selection approach using quasi-opposition self-adaptive coati optimization algorithm for breast cancer classification. The proposed scheme’s fitness function aims to maximize the success rate and minimize the feature selection ratio. We used the three benchmark datasets (Breast Cancer Wisconsin Diagnostic Dataset (WDBC), Breast Cancer Wisconsin Prognostic Dataset (WPBC), and Breast Cancer Wisconsin Original Dataset (WBCD)) to examine the proposed scheme’s performance. The comparison analysis results show that the proposed scheme outperforms the other competitor schemes.