<![CDATA[Student learning concentration is one of the key factors influencing academic achievement and the effectiveness of the learning process. However, monitoring students' concentration levels manually is often subjective and challenging, especially in classrooms with a large number of students. This study aims to implement a Convolutional Neural Network (CNN) model for facial expression detection to classify the learning concentration levels of Senior High School (SMA) students. The research employs a quantitative experimental approach using facial image datasets collected during classroom learning activities. The dataset undergoes several preprocessing stages, including face detection, cropping, image resizing, and pixel normalization before being used for model training. The CNN architecture is designed to automatically extract facial features and classify students' concentration levels into three categories: high, medium, and low concentration. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. The experimental results indicate that the CNN model is capable of recognizing facial expression patterns related to learning concentration effectively and achieving high classification performance. Furthermore, the developed system provides a more objective and efficient approach for monitoring student concentration compared to conventional observation methods. Therefore, the implementation of CNN-based facial expression recognition has significant potential to support intelligent educational systems and improve learning evaluation processes in school environments. ]]>
Copyrights © 2026
