<![CDATA[The increasing global demand for high-quality coffee requires more efficient and objective methods to evaluate bean quality. Traditional sensory and manual inspection techniques are time-consuming, subjective, and prone to inconsistency. This study aims to develop and validate an Artificial Intelligence (AI)-based predictive model for assessing coffee bean quality using digital image processing and sensor data. The research employs a quantitative experimental approach by integrating convolutional neural networks (CNNs) for visual analysis and machine learning regression models to process multispectral sensor data related to moisture, color, and aroma parameters. A dataset of 5,000 labeled coffee bean samples from three regional plantations was used for training and validation. The results demonstrate that the hybrid AI model achieved an accuracy rate of 96.8% in predicting bean grades compared to expert cupping scores, outperforming traditional visual grading methods by 18%. Furthermore, the integration of digital imaging and IoT-based sensors significantly reduced evaluation time and human error. The findings highlight AI’s potential to revolutionize coffee quality control by enabling automated, consistent, and scalable assessment systems that support sustainable agricultural practices.]]>
Copyrights © 2025
