Performance Comparison of Machine Learning Models for Concrete Compressive Strength Prediction

• Published in: Materials Vol. 17; no. 9; p. 2075
• Main Authors: Sah, Amit Kumar, Hong, Yao-Ming
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.05.2024
• Subjects: Algorithms; artificial neural network (ANN); Artificial neural networks; Cement; coefficient of correlation; Compressive strength; Concrete; concrete compressive strength; Concrete construction; Concrete properties; Construction industry; Machine learning; Neural networks; Neurons; Performance evaluation; Problem solving; Raw materials; Regression analysis; regression tree; root mean square error; Software; Support vector machines; Variables; concrete compressive strength; artificial neural network (ANN); coefficient of correlation; regression tree; root mean square error
• ISSN: 1996-1944; 1996-1944
• DOI: 10.3390/ma17092075

This study explores the prediction of concrete compressive strength using machine learning models, aiming to overcome the time-consuming and complex nature of conventional methods. Four models-an artificial neural network (ANN), a multiple linear regression, a support vector machine, and a regression tree-are employed and compared for performance, using evaluation metrics such as mean absolute deviation, root mean square error, coefficient of correlation, and mean absolute percentage error. After preprocessing 1030 samples, the dataset is split into two subsets: 70% for training and 30% for testing. The ANN model, further divided into training, validation (15%), and testing (15%), outperforms others in accuracy and efficiency. This outcome streamlines compressive strength determination in the construction industry, saving time and simplifying the process.