Classification of Dry Nut Types Using the Support Vector Machine Method

Nuts are vital worldwide in the agricultural and food industry, providing essential nutrients such as vegetable protein, fiber, and other crucial dietary components. Identifying and classifying different types of nuts is crucial due to their unique characteristics. This research aims to employ Support Vector Machine (SVM) techniques to classify various dry nut varieties accurately. SVM, a robust machine learning algorithm, was utilized to distinguish between different types of dry nuts. The model’s performance was enhanced by selecting appropriate kernel functions to handle non-linear data and analyzing the features associated with each nut type. The study successfully classified seven varieties of dry nuts, achieving varying levels of accuracy for each class: Barbunya (98%), Bombay (100%), Cali (98%), Dermason (96%), Horoz (99%), Seker (98%), and Sira (95%). These results demonstrate the effectiveness of SVM in identifying and differentiating dry nut types, indicating its potential applications in the food industry for quality control and product classification.