Klasifikasi Kedelai Gmo Dan Non-Gmo Menggunakan Metode Convolutional Neural Network

The rapid advancement of Genetically Modified Organisms (GMO) in agriculture raises concerns regarding food safety, labeling, and consumer protection, especially in soybean commodities. Due to the high visual similarity between GMO and and non-GMO soybeans, traditional identification methods such as molecular testing are often impractical for real-time inspection. This research proposes a classification approach using Convolutional Neural Network (CNN) to automatically distinguish between GMO and non-GMO soybean seeds based on digital images. The dataset used consists of 1,000 soybean seed images, evenly divided between GMO and non-GMO categories, collected using a controlled imaging setup. The preprocessing stage involved cropping, resizing images to 128x128 pixels, and pixel normalization. The dataset was then split into a 70% training set, 10% validation set, and 20% test set to ensure robust model evaluation. The CNN model architecture includes convolutional, pooling, and dense layers, trained using the Adam optimizer and categorical crossentropy loss function. The evaluation results show that the model achieved a test accuracy of 99.00%, with high precision, recall, and F1-score for both classes. These findings demonstrate that CNN can be used to classify soybean seeds without manual feature extraction, offering a practical solution for quality control in agriculture and food processing industries.