Machine Learning with WEKA for Predicting Concrete Compressive Strength: An Educational Approach for Civil Engineering Students
Year: 2024
Type: conference-paper
Abstract: The research paper explores the application of machine learning algorithms using the WEKA platform to predict the compressive strength of concrete, a critical aspect of civil engineering. This study focuses on educating undergraduate students with no prior programming experience, offering a practical introduction to AI tools. Utilizing established datasets and advanced machine learning techniques, the research evaluates the performance of various ensemble-based models, including Random Committee, Bagging, and Rotation Forest, alongside instance-based models like KStar and IBk. The findings reveal that ensemble methods outperform instance-based techniques, providing higher prediction accuracy, lower error rates, and improved reliability. By integrating machine learning into civil engineering education, the study aims to enhance students' understanding of key concepts like compressive strength while preparing them for real-world engineering challenges. This interdisciplinary approach also underscores the potential of AI in optimizing construction materials and advancing sustainable infrastructure.
Authors: M Arifuzzaman, M Muhitur Rahman, M K Islam, M Assali, U Gazder, Wadea Sindi, Manal Aburizaiza
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: gold
Funder: University of Waikato
OpenAlex ID: W4408287833