| dc.description.abstract |
Fruit quality assessment is an important aspect in the agricultural industry, especially in determining selling value and consumer satisfaction. This research aims to apply the K-Nearest Neighbor (KNN) algorithm in assessing the quality of Bali Citrus fruit, focusing on quality classification based on relevant physical and chemical attributes. The KNN algorithm was chosen because of its ability to classify data that does not require certain distribution assumptions and its ease of implementation.In this study, data on Bali Citrus fruit attributes such as fruit pigment, smoothness, softness, weight and skin thickness were collected from various samples. The data was then used to train the KNN model, with the K parameter optimized through a cross-validation process to obtain the most accurate classification results. The results of the KNN model were compared with manual quality assessments conducted by experts to evaluate the effectiveness of the algorithm in determining fruit quality.The results showed that the KNN algorithm can effectively classify the quality of Bali Citrus fruits with high accuracy, although some limitations in terms of sensitivity to the selection of K value and the features used were identified. These findings indicate the potential application of the KNN algorithm in automated systems for fruit quality assessment, which can assist in decision making and improve efficiency in the fruit selection process in the agricultural industry.
Keywords: K-Nearest Neighbor, fruit quality, Bali Citrus, classification,data mining
| en_US |
