Performance of Naïve Bayes and Support Vector Machine for solid waste classification in automated sorting systems

This study evaluates the performance of two traditional machine learning models - Naïve Bayes and Support Vector Machines (SVM) - for classifying solid waste materials in an automated sorting system. A dataset of 284 JPEG images, categorized into five classes (cardboard, glass, metal, paper, and plastic), was utilized. Preprocessing involved resizing images to 512 × 384 pixels, normalizing pixel values, and extracting features using Histograms of Oriented Gradients (HOG) and Color Histograms. Based on the results, Naïve Bayes exhibited computational efficiency, achieving an accuracy of 98.90% and an F1-score of 0.908. However, it struggled with overlapping features, particularly between glass and metal, leading to misclassifications. In contrast, SVM outperformed Naïve Bayes, achieving an accuracy of 99.80% and an F1-score of 0.965 by effectively handling complex and overlapping features through optimal decision boundaries. The findings highlight SVM’s superior performance for complex datasets, whereas Naïve Bayes remains a viable option for more straightforward classification tasks. This study underscores the potential of traditional machine learning in waste classification. Still, it suggests that integrating deep learning models may improve accuracy, scalability, and adaptability in real-world waste sorting systems.