Prognosis of Thoracic Cancer Using the Bierman Random Committee Machine Learning

Authors

  • Ezzat A. Mansour Information Science Department, Faculty of Arts and Humanities King Abdulaziz University, Jeddah, Saudi Arabia

DOI:

https://doi.org/10.3991/ijoe.v17i12.27573

Keywords:

Thoracic Cancer, Random Committee forest, Machine learning algorithm.

Abstract


Thoracic most cancers are a prime problem in the clinical field. Unexpected occur-ring cannot be predicted earlier but if the strategy is fine-tuned properly then the prognosis of cancer is not a major issue. But the problem is how to find out the proper layout with all possible features. The sector of Thoracic Surgery is offering a source of the dataset with all feasible attributes of thoracic cancer. All the features suggested by this medical sector were approved by the Consortium of Tuberculosis and Pulmonary Diseases. The random committee is a novel hybrid algorithm that utilizes the benefit of both random forests with committee concepts. Many random forests are created as the result of the iteration. But anyone can be created and the committee analyses and retains any one optimal solution. Brei man, the first researcher to propose the general concept of Radio Frequency following the same he proposed the famous and most popular forest RF algorithm. 

Downloads

Published

2021-11-29

How to Cite

Mansour, E. A. (2021). Prognosis of Thoracic Cancer Using the Bierman Random Committee Machine Learning. International Journal of Online and Biomedical Engineering (iJOE), 17(12), pp. 135–150. https://doi.org/10.3991/ijoe.v17i12.27573

Issue

Section

Papers