Citation

Ali, Nursabillilah Mohd and Kamarudin, Fahmie and Ghani, Johar Akbar Mohamat and Shair, Ezreen Farina and Johan, Nurul Fatiha and Shamsudin, Nur Hazahsha and Abidin, Amar Faiz Zainal and Razi, Atikah and Shah, Hairol Nizam Mohd and Besar, Rosli (2025) Hybrid feature selection methods for microarray colon cancer diagnostic system. Multidisciplinary Science Journal, 8 (4). p. 2026246. ISSN 2675-1240

Full text not available from this repository.

Abstract

Even though deoxyribonucleic acid (DNA) microarrays play a crucial role in cancer diagnosis, their high dimensionality necessitates the application of a feature selection method to identify the optimal subset for further analysis. A hybrid feature selection method integrates the strengths of filter and wrapper methods, enhancing the selection process for distinct features. In this study, hybrid feature selection methods (Pasi Luukka filter + genetic algorithm (PL + GA), Pasi Luukka filter + ant colony optimization (PL + ACO), and Pasi Luukka filter + particle swarm optimization (PSO)) were used to extract features from cancer datasets, such as colon cancer dataset. The primary objective of this study is to assess the performance of hybrid feature selection methods based on the training accuracy, testing accuracy, and number of selected features. Python programming language in Visual Studio Code was used to develop the hybrid feature selection methods. To determine the effectiveness of the proposed hybrid feature selection methods, their performance was tested across various colon cancer datasets. The findings of this study provide valuable insights into the effectiveness of the PL filter for colon cancer detection.

Item Type:	Article
Uncontrolled Keywords:	microarray data, genetic algorithm, ant colony optimization, particle swarm optimization, support vector machine, random forest
Subjects:	R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	10 Feb 2026 06:36
Last Modified:	10 Feb 2026 06:36
URII:	http://shdl.mmu.edu.my/id/eprint/15308

Downloads

Edit (login required)