<![CDATA[Traditional learning media tends to have limitations in providing interactive experiences that can stimulate better understanding. This is supported by changes in learning styles among students, influenced by extensive exposure to computers and the internet, leading students to prefer learning with the aid of visualizations. This research designs, develops, and tests a machine learning-based visualization tool integrated with the Streamlit framework to enhance students' understanding of the mechanical properties of materials. This visualization tool consists of four main features: data analysis, correlation analysis, 3D visualization, and prediction models using machine learning. The data used for training the machine learning model includes tensile test data of low-alloy steel, comprising mechanical properties, chemical elements, and heat treatment temperatures. The research results indicate that the visualization tool can illustrate the cause-and-effect relationships of parameters influencing the changes in the mechanical properties of low-alloy steel. Each feature in this visualization tool can be utilized to support the analysis of mechanical properties and improve students' understanding of material mechanical properties. Additionally, the visualization tool is evaluated by experts, with information accuracy scoring 4 in the good category, visualization quality at 4.25 in the good category, suitability for learning at 4 in the good category, and ease of use at 4.5 in the good category. Nevertheless, further research and development are needed to test and expand the use of this visualization tool in various learning contexts and other material fields.]]>
Copyrights © 2024
