No abstract

Non-Small Cell Lung Cancer (NSCLC) developed as a malignant cell cancer in the major regions of lungs thus identified as one of the life-threatening diseases. Many factors constitute to the development of this type of cancer in human lungs in both active or passive form. The major objective of this research paper is to identify the irrelevant factors or symptoms from a high dimensional clinical NSCLC dataset with 31 features using a novel Reverse Feature Elimination Dimensionality Reduction (RFEDR) algorithm designed for identifying worst features through Best Cost ranking technique applied in the dataset. In the initial stage pre-processing, 3 features (Admission-ID, Age and Gender) were removed in three filter stages and Feature Elimination method is applied. At the end of the implementation process with 40 iterations, the line of convergence was obtained Iteration 7 to 27. The best cost was determined to be 1.0042e-26 and the worst features through reverse elimination algorithm was identified as rare Alcohol Intake (Feature 2), Work Threats (Feature-4), Smoking Habit (Feature-9), Cold (Feature-20), Snoring (Feature-22) and Headache (Feature-27) respectively. The research sublimated the importance of eliminating irrelevant features apart from selecting best features for better prediction.

This electronic document is a "live" template. The various components of your paper [title, text, heads, etc.] are already defined on the style sheet, as illustrated by the portions given in this document. Do not use special characters, symbols, or math in your title or abstract. The authors must follow the instructions given in the document for the papers to be published. You can use this document as both an instruction set and as a template into which you can type your own text.

No abstract

No abstract