Improved Malnutrition Classification: A Grey Wolf Optimization-Based Feature Selection Approach with Random Forest Model

Malnutrition remains a critical health issue, especially among children, necessitating an effective and accurate classification model for early identification and intervention. In response to this challenge, this research proposes a novel approach for feature selection using the Grey Wolf Optimization (GWO) algorithm in the context of the Random Forest (RF) model. This study aims to enhance the accuracy of malnutrition classification by optimizing feature selection, considering varied configurations of Search Agent (SA) in the GWO algorithm. Comparative evaluations are conducted with different SA settings (SA=5, SA=20, SA=50) to assess their impact on the performance of the RF model. The results indicate that the proposed model, especially with SA=50, outperforms other configurations, achieving a significant accuracy improvement of 74%. These findings underscore the importance of optimal feature selection in enhancing the classification accuracy of the RF model for malnutrition, providing valuable insights for early detection efforts and targeted interventions.