Cancer classification using Fuzzy C-Means with feature selection

For many years, cancer classification to detect cancer at early stage of treatment has improved. Cancer classification is used for the treatment of cancer has entered the challenge to target specific therapy for each type of cancer pathogens in an effort to maximize efficacy and minimize toxicity. In general, cancer data consists of many features. However, not all of these features are informative. Therefore, among these features, Fisher's Ratio is applied to select the most informative features which form new data. Data on which feature selection has not been and has been performed are classified using Fuzzy C-Means. The experiment reveals that optimization which based on classification with feature selection increases the accuracy. Results show that, without doing feature selection, the accuracy is 82.92 % while with feature selection, the best accuracy is 89.68 % obtained by using 150 features. The results show the difference between all the dataset used and the dataset using feature selection.