RFE-ACO-RF: An approach for Cancer Microarray Data Diagnosis

Abstract

Cancer now a day is playing a vital role in increasing the number of deaths throughout the world. Early detection of cancer increases the degree of recovery. Machine Learning has given various models based on biopsy data and the microarray data for cancer classification. The microarray data is having high dimension. Hence applying machine learning algorithm is directly applied to the microarray data for classification purposes then it will face the Small Sample Size (SSS) problem. So, before classification, the dimension of the dataset has to be reduced by using any available technique. In this research work an integrated approach based on the RFE-ACO-RF method has been proposed as a cancer diagnosis model. The RFE will be used for feature selection purpose, ACO is used for optimization purpose and the RF for classification purpose. The performance of the model will be calculated based on accuracy, F1 score, precision and recall.