<![CDATA[Corn plays a critical role in Indonesia’s agricultural sector, functioning as both a staple food for human consumption and a key component of livestock feed. However, its quality is frequently compromised by factors such as mechanical damage during harvesting, fungal contamination, and fluctuating climate conditions, all of which pose challenges to maintaining consistent standards. Traditionally, corn quality classification relies on manual methods, which are not only time-consuming but also prone to human error and inconsistency. To address these limitations, this study employs a Neural Network approach to classify corn into two distinct categories: breeder and commercial grades. The research utilizes a dataset of 2,026 records, meticulously divided into 70% for training, 20% for validation, and 10% for testing, ensuring robust model evaluation. The methodology includes comprehensive data preprocessing, feature standardization to normalize input variables, and hyperparameter optimization, with the model trained over 100 epochs using a batch size of 32 and a learning rate of 0.001. The results demonstrate exceptional performance, achieving an accuracy of 99.5%, precision of 98.3%, recall of 100%, and an F1-score of 99.1%, as validated by a confusion matrix that highlights the model’s classification reliability. This automated system significantly enhances the efficiency and accuracy of corn quality assessment, offering a scalable solution to replace outdated manual techniques. By providing a reliable tool for quality differentiation, this study supports Indonesia’s agricultural and livestock industries, with potential for broader application in optimizing crop management and ensuring food security under varying environmental conditions.]]>
