<![CDATA[Google Teachable Machine is a web-based application that allows users to create a machine learning model without the need for coding. The application utilizes Convolutional Neural Networks (CNN) in its process. In this study, Teachable Machine was utilized to create a machine learning model capable of identifying specific mineral rocks, particularly magnetite, calcite, and quartz. The research procedure was conducted through several stages: Sample Collection, Sample Classification (Dataset), Model Training, and Evaluation Process. Sample data in the form of mineral rock images were obtained and downloaded from Google. The data was then divided into three mineral classes: magnetite, calcite, and quartz, which were used as inputs in the Teachable Machine. Model training in Teachable Machine used input epochs of 100, batch size of 64, and learning rate of 0.0001. The results of the Teachable Machine modeling were then evaluated, showing that the obtained model could recognize magnetite, calcite, and quartz minerals with an average accuracy, precision, recall, specificity, and F1-score of 91.11% (86.67%), 87.30%, 86.67%, 93.33%, and 86.50% respectively. This research indicates that the utilization of Teachable Machine assists in quick, accurate, and easy identification, thereby contributing to speeding up the process of mineral rock analysis, decision-making, and exploration strategy development. Additionally, these results demonstrate the potential for broader development of this application in various fields of study.]]>
Copyrights © 2024
