Modified Genetic Folding Algorithm for Breast Cancer Classification Dataset

Cancer is a disease that develops in the human body due to gene mutation. Because of various factors, cells can become cancerous and grow rapidly, destroying normal cells at the same time. Support vector machines allow for accurate classification and detection of the classes. The advantage of kernel selection is to derive global learning rates for SVMs using the Genetic Folding algorithm. The developed GF algorithm outperforms traditional SVMs in the UCI Breast Cancer Wisconsin Diagnostic (BCWD) dataset under a certain comparative analysis, which is conducted under a set of conditions that describe the behavior of the compared algorithms. The observation that relates the GF performance appears to be comparable with SVM. The statistical analysis relies on a careful analysis of the ROC curve. Moreover, the GF algorithm shows that accuracy rates are obtained adaptively, that is, without knowing the parameters resulting from the margin conditions. The experimental results show that the one GF operator produces superior classification accuracy. The proposed method plays an important role in the detection of breast cancer in an efficient time frame.