On the Multiple Linear Regression and Artificial Neural Networks for Strength Prediction of Soil-Based Controlled Low-Strength Material
This paper presents two approaches, multiple linear regression (MLR) and artificial neural network (ANN), to develop predictive models for unconfined compressive strength of soil-based controlled low-strength material (CLSM). Our obtained laboratory data conducting on the soil-based CLSM were employed for analysis. Two strength prediction models were proposed: (1) strength is assumed to be a function of mix proportion and curing period; and (2) it is estimated from measured ultrasonic pulse velocity combined with effect of mixture parameters and curing ages. In each model, three predicted formulas were developed; one from MLR and two from ANN. It was showed that all the proposed equations have a well-predicted capacity.
Keishi Matsuda, P.S. Pa and Wiseroad Yun
L. J. Huang et al., "On the Multiple Linear Regression and Artificial Neural Networks for Strength Prediction of Soil-Based Controlled Low-Strength Material", Applied Mechanics and Materials, Vol. 597, pp. 349-352, 2014