Melon Fruit Quality Classification with Hyperparameter Optimization of Random Forest Algorithm Using Grey Wolf Optimizer

Abstract

Machine vision technology has significantly transformed the agricultural sector, particularly fruit classification. Accurate melon classification helps maintain product quality, enhances the supply chain, and reduces waste. Traditionally, determining fruit quality classification was done manually by farmers, which often required time and effort. This study optimizes the hyperparameters of the Random Forest algorithms using Grey Wolf Optimizer (GWO) by combining color features extraction from histograms and texture features from the Grey Level Co-occurrence Matrix (GLCM). The use of GWO significantly improved the precision of the Random Forest algorithm to 92.43%, with hyperparameter optimization on n_estimators, max_features, and max_depth affecting the overall model performance. Consequently, this research makes a valuable contribution to improving the efficiency of melon quality classification through more effective hyperparameter optimization.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint