Chicken Swarm-Based Feature Selection with Optimal Deep Belief Network for Thyroid Cancer Detection and Classification

Abstract

The combination of machine-learning (ML) approaches in health care is a massive advantage designed to cure the illness of millions of people. Several efforts are used by researchers to detect and provide primary phase insights into cancer analysis. Thyroid cancer is one of the worst forms of cancer, and the chances of survival for those who are diagnosed with it is bleak even today. Early stage detection of cancer is not an easy task; however, if it can be detected, it can be curable. This study develops a Chicken Swarm Optimization Feature Selection (CSOFS) with Optimal Deep Belief Network (ODBN) model named CSOFS-ODBN for Thyroid Cancer Detection and Classification. The proposed CSOFS-ODBN model aims to identify and classify the presence of thyroid cancer. Initially, the CSOFS-ODBN model undergoes a min-max data normalization approach to pre-process the input data. Besides, the CSOFS algorithm gets executed to choose an optimal subset of features. In addition, the DBN model receives the chosen features and performs thyroid cancer classification. Finally, the Adam optimizer is utilized for hyperparameter optimization of the DBN model. In order to report the enhanced performance of the CSOFS-ODBN model, a wide-ranging experimental analysis is performed, and the results report the supremacy of the CSOFS-ODBN model, and the tool used for evaluation is named python.