An Optimal Feature Selection by Using Differential Evolution for Effective Breast Cancer Diagnosis

With the development of clinical technologies, different tumor features have been collected for breast cancer diagnosis. The purpose of this study was breast cancer diagnosis based on the feature selection. Feature extraction and selection are critical to the quality of classifiers founded through data mining methods. Differential evolution lot of attention as a way to attract the powerful search and successfully used in a variety of applications including pattern recognition. One of the most important tasks in many pattern recognition systems to identify a subset of useful features that can effectively represent the problem. More specifically, the large number of features can affect the accuracy of the classification and the learning system. To solve these problems, we have to identify the subset of breast cancer features, differential evolution and a wheel based search strategy have been used. Use Feature selection to reduce search space and get the best features of breast cancer to get the best classification accuracy is made.

Keywords:

Feature Selection , Differential Evolution , Breast Cancer , Classification