A minimum-of-maximum relative error support vector machine for simultaneous reverse prediction of concrete components

Gou, Jianping; Fan, Zongwen; Wang, Cheng; Guo, Wang-Ping; Lai, Xingping; Chen, Meizhen

doi:10.1016/j.compstruc.2016.05.003

Cited by 32 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimization of accuracy and MSE can be improved by integrating an evolutionary algorithm to ensure its implementation on other data sets. In Reference 27 , despite high precision in classification, the method is time‐consuming and suitable for a small set of data. Most PSO algorithms, in combination with techniques such as SVM, can be effective, provided that they are not caught in local optimizations.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

“…This error could be reduced by optimization methods, while in the methods, they have received no attention. The lack of repetition and failure to solve the uncertainty problem in 27 also show that, since the SVM decision maker is regression, the PSO is applied to improve the results, but when the fitness function is a PSO function, it is a regression classifier. Since cross‐validation is performed as K‐fold and with repetition, for big data, the correct answer is not received in a short time.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

“…In a study, support vector machine (SVM) was used in the classification of concrete components with their proposed classifier being improved by the particle swarm optimization (PSO) method 27 . In another research, a neural network model was used to predict the strength of cementing materials.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A hybrid optimized learning‐based compressive performance of concrete prediction using GBMO‐ANFIS classifier and genetic algorithm reduction

Rahchamani

Movahedifar

Honarbakhsh

2019

Structural Concrete

View full text Add to dashboard Cite

High performance concrete (HPC) is a type of concrete that cannot be produced using conventional methods. The exact percentage of materials used in the production of this concrete is one of the challenges facing civil engineers so that if ingredients are not in proportion, the strength of concrete is undermined. In the present study, attempts have been made to find an intelligent model to predict the quality of HPC. As a result of regression analysis, the automatic recognition would be affected by inferential estimation. Hence, to increase classification accuracy, first extracted feature is rearranged based on expectation–maximization clustering algorithm and then feature vector size is reduced using genetic algorithm. The proposed classification is adaptive neuro‐fuzzy inference system, which is optimized by Gases Brownian Motion Optimization and able to predict outputs at an acceptable level in limited reiterations. The split ratio of data during learning and testing steps was 0.9 and 0.1, as measured by K‐fold cross‐validation method. Computation of criteria such as mean square error and mean absolute percentage error in the algorithm indicated the desirable performance of the proposed method.

show abstract

Section: Analysis Of Resultsmentioning

confidence: 99%

Section: Analysis Of Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid optimized learning‐based compressive performance of concrete prediction using GBMO‐ANFIS classifier and genetic algorithm reduction

Rahchamani

Movahedifar

Honarbakhsh

2019

Structural Concrete

View full text Add to dashboard Cite

show abstract

“…In this research, the relative error R e and Nash-Suttcliffe efficiency coefficient Ens are adopted to evaluate the fitting effects between the simulated results and the measured values [56,57]. Computation methods of the relative error R e and the efficiency coefficient Ens are, respectively, as shown in Formulas (11) and (12).…”

Section: Analysis Of Simulation Effectsmentioning

confidence: 99%

The Impact of Reservoirs on Runoff Under Climate Change: A Case of Nierji Reservoir in China

Men

Liu

Tian

et al. 2019

Water

View full text Add to dashboard Cite

Reservoirs play an important role in responding to natural disasters (such as flood and drought) by controlling the runoff. With the climate changing, the frequency and intensity of flood and drought are likely to increase. Thus, the impact of reservoirs on runoff under climate change needs to be studied to cope with future floods and drought. In this study, the Nierji Reservoir located on the Nenjiang River Basin was chosen to explore the impact. The Nenjiany River Basin is the vital water source in the water resources transfer project in Northeast China. Climate change in Nenjiang River Basin was analyzed using the 1980 to 2013 climate observations. The results show that the temperature of the basin significantly (p < 0.05) increased while the precipitation significantly (p < 0.05) decreased. Based on the result, nine kinds of different climate scenarios were set up. For different climate scenarios, the Hydroinformatic Modeling System (HIMS) model and the HIMS model with the reservoir calculation module were used to simulate runoff during the no reservoir operation period (1980–2000) and reservoir operation period (2007–2013), respectively. The impact of reservoirs on runoff under climate change is studied. Results show that the Nierji Reservoir can effectively relieve the impact of climate change on downstream runoff. When temperature increases or precipitation decreases, there are larger differences in runoff over the non-flood period, especially during periods of no reservoir operation. Reservoir operation under climate change can provide reliability in drought protection.

show abstract

“…The dataset comprised 720 experimental tests. The following seven algorithms were implemented for each material [49]: Multi-Linear Regression (MLR), K Nearest Neighbours (KNN), Regression Tree (RT), Random Forest (RF), Gradient Boosting (GB), Multi-Layer Perceptron (MLP) [50] and Support Vector Machine (SVM) [51,52]. 80% of the observations are randomly chosen to form the training dataset.…”

Section: Introductionmentioning

confidence: 99%

Prediction of mechanical properties of rail pads under in-service conditions through machine learning algorithms

Ferreño

Sainz-Aja

Carrascal

et al. 2021

Advances in Engineering Software

View full text Add to dashboard Cite

A minimum-of-maximum relative error support vector machine for simultaneous reverse prediction of concrete components

Cited by 32 publications

References 35 publications

A hybrid optimized learning‐based compressive performance of concrete prediction using GBMO‐ANFIS classifier and genetic algorithm reduction

A hybrid optimized learning‐based compressive performance of concrete prediction using GBMO‐ANFIS classifier and genetic algorithm reduction

The Impact of Reservoirs on Runoff Under Climate Change: A Case of Nierji Reservoir in China

Prediction of mechanical properties of rail pads under in-service conditions through machine learning algorithms

Contact Info

Product

Resources

About