<![CDATA[This study addresses the problem of manual classification of coffee bean ripeness, which is often inconsistent and inefficient, potentially affecting product quality and market value. To overcome this issue, the study proposes an automated classification approach using a deep learning model based on MobileNetV2. The objective of this study is to develop an accurate and efficient model for classifying coffee beans into four ripeness levels: Dark, Green, Light, and Medium, while ensuring its applicability in real-world conditions with limited resources. The dataset consists of 1,200 images collected from coffee plantations in Indonesia, processed through resizing, normalization, and data augmentation to improve generalization. The model was trained using transfer learning and evaluated using accuracy, precision, recall, and F1-score metrics. The results show that the model achieves an accuracy of 98.33% on the testing dataset, with a precision of 0.985, recall of 0.983, and F1-score of 0.983. When implemented in a web-based application, it achieves 97.8% accuracy with an average response time of 1.8 seconds and is capable of handling up to 100 concurrent users with stable performance. These findings indicate that the proposed model is effective and reliable for supporting automated coffee bean classification and enhancing efficiency in post-harvest processing.]]>
Copyrights © 2026
