<![CDATA[Indonesia is an agrarian country with an economy that heavily relies on the agricultural sector, including the sugarcane plantation sub-sector for sugar production. Although domestic sugar production continues to increase, the demand for sugar consumption also grows, leading to dependency on imports and fluctuating sugar prices in the domestic market. Therefore, efforts to maintain and enhance the productivity of sugarcane crops are crucial. One of the main challenges in sugarcane cultivation is the attack of pests and diseases such as yellow disease, redrot, mosaic, and rust, which often affect sugarcane plants and reduce their productivity. These diseases must be detected promptly as they significantly impact the quality and quantity of the sugarcane to be harvested. However, manual identification processes are prone to human error and are inefficient for large-scale plantations. To address this, machine learning technology using Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) was employed. This approach uses CNN for feature extraction and SVM for classification. Through a series of experiments, the study shows that the CNN and SVM models can achieve high accuracy of 90.32% with a computational time of 181.53 seconds.]]>
