Article Dans Une Revue Informatica Année : 2025

Cancer Classification through Gene Selection Using the Social Spider Optimization Algorithm

Résumé

Cancer is a leading cause of global mortality, underscoring the need for advanced diagnostic tools to enable early and accurate detection. Microarray technology allows for the simultaneous analysis of thousands of genes, offering valuable insights into cancer biology. However, the high dimensionality of microarray data presents significant challenges for classification tasks. In this study, we propose a novel approach that integrates the Social Spider Optimization (SSO) algorithm with mutual information-based feature selection to identify the most discriminative genes for cancer classification. We evaluate the performance of four machine learning classifiers-Decision Tree (DT), K-Nearest Neighbors (K-NN), Neural Networks (NN), and Support Vector Machines (SVM)-with and without feature selection. Our results demonstrate that the SSO algorithm significantly enhances classification accuracy, with SVM achieving near-perfect performance on leukemia and lymphoma datasets when combined with Max-Relevance Min-Redundancy (MRMR) feature selection. This hybrid approach provides a robust solution for cancer diagnosis by addressing key challenges such as data redundancy and computational complexity.

Fichier principal
Vignette du fichier
9126-34098-1-PB.pdf (534.77 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05328837 , version 1 (23-10-2025)

Licence

Identifiants

Citer

Chahira Cherif, Mohammed Maiza, Samira Chouraqui, Abdelmalik Taleb-Ahmed. Cancer Classification through Gene Selection Using the Social Spider Optimization Algorithm. Informatica, 2025, 49 (3), ⟨10.31449/inf.v49i3.9126⟩. ⟨hal-05328837⟩
265 Consultations
145 Téléchargements

Altmetric

Partager

  • More