Abstract
Classification of Apple Varieties: Comparison of Ensemble Learning and Naive Bayes Algorithms in H2O Framework
In this study, H2O machine learning classification techniques were used to classify the apples according to skin color of the fruits. For each variety 60 samples were used at evaluations of the fruits. Fruit color values were based on L *, a * and b * color space and measured by a portable spectrophotometer. Randomly, Red Delicious, Golden Delicious and Granny Smith apple varieties were studied to create the database. H2O Gradient Boosting Machine, H2O Random Forest and H2O Naive Bayes Algorithms were used to for data analysis. The data set was partitioned to 30% for testing and 70% for training. The classifier performance which accuracy (%), error percentage (%), F-Measure, Cohen’s Kappa, recall, precision, true positive (TP), false positive (FP), true negative (TN), false negative (FN) values were given at the conclusion section of the research. The results found that 100,0 % accuracy for H2O Gradient Boosting Machine, 98,4 % accuracy for H2O Random Forest and 100,0 % accuracy for H2O Naive Bayes.
Keywords
Apple classification, H2O machine learning, Gradient Boosting Machine, Random Forest, Naive Bayes
