Data mining application in an introductory engineering physics lab: a diagnostic activity

Abstract

This study explores the application of data mining techniques in Physics laboratories for Engineering, aiming to enhance the educational process and students' understanding of physical phenomena. The primary objective is to analyze how the use of Orange Data Mining software can facilitate the analysis of large volumes of experimental data, enabling students to identify patterns and extract relevant insights for their investigations. The adopted methodology involved conducting Physics experiments in non-conservative systems, where students collected data on friction across different materials and utilized techniques such as linear regression and clustering (K-means) to analyze the results. Following the application of these techniques, a pre- and post-class knowledge assessment was conducted using a Likert-type questionnaire. The results indicated a significant improvement in participants' understanding of concepts related to force, energy, and data analysis. Additionally, the experience with Orange provided students with greater familiarity with data science tools, better preparing them for the challenges of the engineering job market. This study highlights the importance of integrating data mining techniques into engineering education, offering an innovative approach to learning complex physical concepts.