<![CDATA[Apple quality is a crucial aspect in the agriculture and food processing industry, quality assessment is essential to meet consumer standards and ensure customer satisfaction. This research explores the use of K-nearest Neighbor (KNN) algorithm optimized with Particle Swarm Optimization (PSO) for apple quality classification based on the attributes of size, weight, sweetness, crispness, juiciness, ripeness, and acidity. The dataset used contains 4000 apple samples that have been measured and evaluated based on these attributes. The results showed that setting the population size and inertia weights in the PSO algorithm successfully optimized the performance of KNN in apple quality classification. The combination of population size and inertia weight in the PSO algorithm can increase KNN's accuracy to 91.15% with a recall value of 89.53% and precision of 92.59%. This research also has a better accuracy value than previous research on apple quality classification.]]>
Copyrights © 2025
