A novel algorithm applied to classify imbalanced data in Breast Cancer Dataset

In today's world, the classification of imbalanced data is of great importance. Classifying such data is in a way that the class which is extremely important, in terms of Application Scope (minority class), includes fewer states compared to a class which is not (majority class). These datasets are called imbalanced data. Several methods have been proposed to classify these types of data. In the classification of these data, we are trying to increase the number of states of the minority class compared to majority class. In this paper, we suggest a new and effective algorithm in classification of 5-years data of cancer patients and there is an Imbalanced property in this dataset. The proposed algorithm is a combination of SMOTE algorithm, Imperialist Competitive Algorithm (ICA) and some well-known classifiers, and also to calculate the performance of the proposed method, some assessments such as GMean, Accuracy, Specificity, Sensitivity, have been used. The results show that combining the SMOTE+ICA+C5 algorithms would have the best result in the classification of imbalanced data. So this is an effective approach in imbalanced data classification.

Keywords:

Breast cancer , Classification , ICA , Synthetic Minority Over-sampling Technique