Feature Selection for Lung and Breast Cancer Disease Prediction Using Machine Learning Techniques

Kanwal, Samina, Rashid, Junaid, Anjum, Nasreen ORCID: 0000-0002-7126-2177, Nisar, Muhammad Wasif and Juneja, Sapna (2022) Feature Selection for Lung and Breast Cancer Disease Prediction Using Machine Learning Techniques. In: 2022 1st IEEE International Conference on Industrial Electronics: Developments & Applications (ICIDeA). IEEE, pp. 163-168. ISBN 9781665421492

Text (Peer Reviewed Version) 11955 Kanwal, Rashid, Anjum and Juneja (2022) Feature_Selection_for_Lung_and_Breast_Cancer_Disease_Prediction_Using_Machine_Learning_Techniques.pdf - Accepted Version Restricted to Repository staff only Available under License All Rights Reserved. Download (928kB)

Abstract

Early detection of cancer is essential for a favorable prognosis because it is the biggest cause of death globally. After lung cancer, breast cancer ranks as the second most prevalent cause of death. With the fast expansion of the populace, the risk of mortality from lung and breast cancer is increasing rapidly. Early cancer prediction is challenging because there are few signs of this disease at an early stage. An automated sickness identification system provide accurate, efficient and quick response while assisting medical workers in identifying disorders and decreases death rates. In this research, we proposed PSO-FS (particle swarm optimization-based feature selection) method to select the features for several machine learning techniques to categorize accessible lung and breast cancer data. The best classifier approach for predicting both cancer diseases is considered to be the forest (RF) and deep learning (DL) classifier, which has high accuracy of 99.7% and 97%, respectively. Hence feature selection approach can increase performance by selecting only significant features.

Item Type:	Book Section
Article Type:	Article
Uncontrolled Keywords:	PSO; Deep Learning; Breast-Cancer; Lung Cancer; Early Detection; Treatment
Subjects:	R Medicine > R Medicine (General)
Divisions:	Schools and Research Institutes > School of Business, Computing and Social Sciences
Research Priority Areas:	Applied Business & Technology
Depositing User:	Kate Greenaway
Date Deposited:	08 Dec 2022 14:32
Last Modified:	31 Oct 2023 12:39
URI:	https://eprints.glos.ac.uk/id/eprint/11955

University Staff: Request a correction | Repository Editors: Update this record