Feature selection using differential evolution for microarray data classification

• DOI: 10.1007/s43926-023-00042-5
• Publication Date: 2023-10-05T16:01:56Z
• Authors: Sanjay Prajapati; Himansu Das; Mahendra Kumar Go...
• Keywords: Feature (linguistics); Differential Evolution

Abstract The dimensions of microarray datasets are very large, containing noise and redundancy. problem with is the presence more features compared to number samples, which adversely affects algorithm performance. In other words, columns exceeds rows. Therefore, extract precise information from datasets, a robust technique required. Microarray play critical role in detecting various diseases, including cancer tumors. This where feature selection techniques come into play. recent times, (FS) has gained significant importance as data preparation method, particularly for high-dimensional data. It preferable address classification problems fewer while maintaining high accuracy, not all necessary achieve this goal. primary objective identify optimal subset features. context, we will employ Differential Evolution (DE) algorithm. DE population-based stochastic search approach that found widespread use scientific technical domains solve optimization continuous spaces. our approach, combine three different algorithms: Random Forest (RF), Decision Tree (DT), Logistic Regression (LR). Our analysis include comparison accuracy achieved by each algorithmic model on dataset, well fitness error model. results indicate when was used were better used.