The level of rice productivity is influenced by several inhibiting factors, for example disease attack in rice plants. The slow and inappropriate treatment of rice plant can make the crop failure so that rice production and farmers' income decrease. The symptoms of rice disease are difficult to distinguish, especially in severe symptoms. Collaboration with other fields, especially computer science, is needed to classify diseases automatically so that the farmers can take action for plant treatment and the spread of disease can be controlled quickly. The classification of diseases based on images requires the best features/characteristics so that the disease can be classified. In this research, Deep Learning method, especially Convolutional Neural Network with EfficientNet B3 architecture, can extract features very well. In this research, the classification of brown spot and bacterial leaf disease by applying EfficientNet B3 with transfer learning reached 79.53% accuracy and 0.012 loss/error.

Ship identification on satellite imagery can be used for fisheries management, monitoring of smuggling activities, ship traffic services, and naval warfare. However, high-resolution satellite imagery also makes the segmentation of the ship difficult in the background, so that to handle it requires reliable features so that it can be identified adequately between large vessels, small vessels and not ships. The Convolutional Neural Network (CNN) method, which has the advantage of being able to extract features automatically and produce reliable features that facilitate ship identification. This study combines CNN ZFNet architecture with the Random Forest method. The training was conducted with the aim of knowing the accuracy of the ZFNet layers to produce the best features, which are characterized by high accuracy, combined with the Random Forest method. Testing the combination of this method is done with two parameters, namely batch size and a number of trees. The test results identify large vessels with an accuracy of 87.5% and small vessels with an accuracy of not up to 50%.