High correlated variables creator machine: Prediction of the compressive strength of concrete

•High correlated creator variables (HCVCM) uses functions to create stronger inputs.•A case study with two inputs and one output was solved.•The effect of HCVCM on the accuracy of known models was evaluated.•HCVCM improves the accuracy of models significantly. In this paper, we introduce a novel hyb...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & structures Ročník 247; s. 106479
Hlavní autoři: Shishegaran, Aydin, Varaee, Hesam, Rabczuk, Timon, Shishegaran, Gholamreza
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Elsevier Ltd 15.04.2021
Elsevier BV
Témata:
Adaptive Neuro-Fuzzy Inference System (ANFIS)
Adaptive systems
Artificial neural networks
Compressive strength
Concrete
Correlation
Fuzzy logic
Gene expression
Gene Expression Programming (GEP)
Mean square errors
Model accuracy
Prediction models
Rebound Hammer (RH)
Rebound Number (RN)
Root-mean-square errors
Statistical analysis
Step-By-Step Regression (SBSR)
Ultrasonic Pulse Velocity (UPV)
Ultrasonic Pulse Velocity (UPV)
Step-By-Step Regression (SBSR)
Adaptive Neuro-Fuzzy Inference System (ANFIS)
Rebound Hammer (RH)
Gene Expression Programming (GEP)
Rebound Number (RN)
ISSN:0045-7949, 1879-2243
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•High correlated creator variables (HCVCM) uses functions to create stronger inputs.•A case study with two inputs and one output was solved.•The effect of HCVCM on the accuracy of known models was evaluated.•HCVCM improves the accuracy of models significantly. In this paper, we introduce a novel hybrid model for predicting the compressive strength of concrete using Ultrasonic Pulse Velocity (UPV) and Rebound Number (RN). First, we collect 516 datasets from 8 studies of UPV and Rebound Hammer (RH) tests. Then, we propose the High Correlated Variables Creator Machine (HCVCM) to create the new variables that have a better correlation with the output in order to improve the prediction models. Three single models, including a Step-By-Step Regression (SBSR), Gene Expression Programming (GEP), an Adaptive Neuro-Fuzzy Inference System (ANFIS) as well as three hybrid models, i.e. HCVCM-SBSR, HCVCM-GEP, and HCVCM-ANFIS are employed to predict the compressive strength of concrete. The statistical parameters and error terms such as the coefficient of determination, the Root Mean Square Error (RMSE), Normalized Mean Square Error (NMSE), fractional bias, the maximum positive and negative errors, and the Mean Absolute Percentage Error (MAPE) are computed to evaluate the models. The results show that HCVCM-ANFIS can predict the compressive strength of concrete better than all other models. HCVCM improves the accuracy of ANFIS by 5% in the coefficient of determination, 10% in the RMSE, 3% in the NMSE, 20% in MAPE, and 7% in the maximum negative error.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0045-7949
1879-2243
DOI:10.1016/j.compstruc.2021.106479