APPLY OPTIMIZATION TECHNIQUES IN MACHINE LEARNING MODEL FOR BREAST CANCER DETECTION

Abstract

Breast cancer is a serious issue for humans and one of the most common disorders for women. In the era of technology, researchers try to address any complication with ML, AI, Optimization and DL. This study aims to address the breast cancer problem with optimization and ML algorithm. The goal of this work is to identify the best suite ML models and optimization techniques for breast cancer detection. This study employs six optimization techniques and three ML models for breast cancer analysis. Random search, Grid search, Bayesian, Ant Bee Colony, Blue Whale, particle swarm optimization with SVM, XG-Boost, and ANN architecture impose this study to investigate breast cancer. This study utilizes a quantitative correlational approach based on the Mammographic Mass dataset. In SVM and XG Boost, Grid search shows the highest accuracy of 86.46% and 85.93%. However, ANN outperforms the accuracy of 83.13% for the Random search approach. The findings of this work are that Random search and Grid search contain maximum accuracy, but concerning time, Bayesian optimization is superior.