Classification of Orange Features for Quality Assessment Using Machine Learning Methods

Authors : Talha Alperen Cengel, Bunyamin Gencturk, Elham Yasin, Müslüme Beyza Yıldız, Ilkay Cinar, Osman Özbek, Murat Koklu

Pages : 403-413

View : 97 | Download : 67

Publication Date : 2024-12-16

Article Type : Research Paper

Abstract :Oranges are a member of the citrus family and are eaten in large quantities due to their high vitamin C content, sweet and tart taste, and useful fiber and antioxidant qualities. Orange quality assurance is essential to market competitiveness and customer satisfaction. Conventional approaches to evaluating quality are costly and susceptible to mistakes made by people. This research aims to investigate how well different machine learning algorithms automate and improve the orange quality assessment procedure. A dataset containing 241 samples and 11 features (size, weight, sweetness (Brix), acidity (pH), and color) was used to evaluate the effectiveness of the Random Forest (RF), XGBoost, and k-Nearest Neighbors (k-NN) algorithms. According to the findings, k-NN acquired the maximum accuracy of 69.38%, with RF coming in second at 67.34% and XGBoost third at 63.26%. These results demonstrate how machine learning models may be used to improve quality control in the orange industry by offering a more dependable and effective approach. According to this study, machine learning can greatly improve the quality control procedures for oranges, resulting in higher-quality goods for customers and more productivity for providers. The orange sector can enhance product quality and expedite operations by utilizing these technologies, which will eventually benefit both producers and consumers.
Keywords : Yapay Zeka, Kalite Sınıflandırma, Portakal Kalitesi, Makine Öğrenmesi Algoritmaları

ORIGINAL ARTICLE URL