Numerical study on the feasibility of dynamic evolving neural-fuzzy inference system for approximation of compressive strength of dry-cast concrete |
| |
Affiliation: | 1. Department of Concrete Technology; Road, Housing & Urban Development Research Center (BHRC), Tehran 13145-1696, Iran;2. Department of Civil and Environmental Engineering and Construction, University of Nevada Las Vegas, Las Vegas, NV, USA;1. School of Computer Engineering, Nanyang Technological University, Singapore;2. CIST, Korea University, Seoul, South Korea;1. Department of Telecommunications and Systems Engineering, The Autonomous University of Barcelona, Carrer Emprius 2, Sabadell, Barcelona 08202, Spain;2. Department of Electrical and Computer Engineering, The University of Arizona, 1230 E. Speedway Boulevard, Tucson, AZ 85721, USA;3. Department of Surgery, College of Medicine, The University of Arizona, 1501 N. Campbell Avenue, Tucson, AZ 85724, USA |
| |
Abstract: | This paper assesses effectiveness of dynamic evolving neural-fuzzy inference system (DENFIS) models in predicting the compressive strength of dry-cast concretes, and compares their prediction performances with those of regression, neural network (NN) and ANFIS models. The results of this study emphasized capabilities of online first-order and offline high-order Takagi–Sugeno (TSK) type DENFIS models for prediction purposes, whereas offline first-order TSK-type DENFIS models did not produce reliable results. Comparison between the produced results of an elite high-order DENFIS model with those predicted by the selected NN, regression and ANFIS models showed effectiveness of DENFIS model than the regression model, while its performance was similar to or slightly better than the other artificial prediction tools. |
| |
Keywords: | Predictive model DENFIS ANFIS Neural network Regression Compressive strength Dry-cast (No-slump) concrete |
本文献已被 ScienceDirect 等数据库收录! |
|