Retraction Note to: Potential of soft computing approach for evaluating the factors affecting the capacity of steel–concrete composite beam

Toghroli, Ali; Suhatril, Meldi; Ibrahim, Zainah; Safa, Maryam; Shariati, Mahdi; Shamshirband, Shahaboddin

doi:10.1007/s10845-019-01528-2

Cited by 6 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is a bionics-based problem solution scheme which mimics the functionality of human brain [1][2][3][4][5][6][7][8][9][10][11][12][13]. It is usually constituted by a series of mathematic operations and transformations which are implemented by computer programs coupled with modern electronic computers.…”

Section: Introductionmentioning

confidence: 99%

Hybrid machine learning hydrological model for flood forecast purpose

Kan¹,

Liang²,

Yu³

et al. 2020

Open Geosciences

View full text Add to dashboard Cite

Machine learning-based data-driven models have achieved great success since their invention. Nowadays, the artificial neural network (ANN)-based machine learning methods have made great progress than ever before, such as the deep learning and reinforcement learning, etc. In this study, we coupled the ANN with the K-nearest neighbor method to propose a novel hybrid machine learning (HML) hydrological model for flood forecast purpose. The advantage of the proposed model over traditional neural network models is that it can predict discharge continuously without accuracy loss owed to its specially designed model structure. In order to overcome the local minimum issue of the traditional neural network training, a genetic algorithm and Levenberg–Marquardt-based multi-objective training method was also proposed. Real-world applications of the HML hydrological model indicated its satisfactory performance and reliable stability, which enlightened the possibility of further applications of the HML hydrological model in flood forecast problems.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid machine learning hydrological model for flood forecast purpose

Kan¹,

Liang²,

Yu³

et al. 2020

Open Geosciences

View full text Add to dashboard Cite

show abstract

“…In recent years, artificial intelligence (AI) has been widely developed in various applications 34,35 for prediction, 36‐39 simulation, 34,40 or detection 41 . Researchers have deployed this technique to address the shortcomings of old‐fashioned numerical methods 42‐48 .…”

Section: Methodsmentioning

confidence: 99%

Analysis of groundwater pollution in a petroleum refinery energy contributed in rock mechanics throughANFIS‐AHP

Tan

AL-Huqail

Chen³

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary Urban groundwater pollution caused by the oil industry and gas stations is a significant global environmental problem. Due to the increased demand for petroleum and petrochemical production in recent years, it is crucial to monitor and investigate the quality and contamination level of groundwater for groundwater extraction, usage, and protection. On the basis of the rock mechanic state and the features of petroleum hydrocarbon pollution in groundwater, the control parameters of petroleum hydrocarbon pollution in groundwater are investigated. Ten water samples were gathered from the vicinity of two refinery sites and experimented via a soft computing model of the adaptive neuro‐fuzzy inference system, later evaluated by the hierarchical ladder method of the analytic hierarchy process. According to the data, high and very severe pollution sites account for 31.45% of shallow phreatic water and only 20% of deep confined water, indicating that shallow groundwater is more severely contaminated than deep groundwater. Total dissolved solids, total hardness, Cl−, SO42−, and so on, which are influenced by both the natural environment and human activities, are the primary factors impacting the quality of groundwater in those regions. The primary pollutants in groundwater are nitrite and nitrate nitrogen, both of which are caused by human activities.

show abstract

“…This is because the results are more dependable than those acquired using traditional procedures 65–69 . AI systems have displayed promise in handling real‐world issues, particularly non‐linear ones 70–75 . Through the implementation and testing of emerging computer models that can approximate the mechanical characteristics of concrete mixtures, material science has seen substantial growth 76–82 .…”

Section: Introductionmentioning

confidence: 99%

“…[65][66][67][68][69] AI systems have displayed promise in handling real-world issues, particularly non-linear ones. [70][71][72][73][74][75] Through the implementation and testing of emerging computer models that can approximate the mechanical characteristics of concrete mixtures, material science has seen substantial growth. [76][77][78][79][80][81][82] AI-based models are able to reduce the usage of harmful testing in the concrete sector, where a least amount of three specimens should be examined at each designated age to determine compressive strength (Figure 3).…”

Section: Introductionmentioning

confidence: 99%

The metaheuristic optimization of the mechanical properties of sustainable energies using artificial neural networks and genetic algorithm: A case study by eggshell fine waste

Wang

AL‐Huqail

Salimimoghadam

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary Eggshell concrete is a novel green material that aids the recycling of eggshell powder (ESP) waste while decreasing the environmental damage due to higher manufacture to develop sustainable energies. Nevertheless, current investigations on eggshell concrete are limited, and the results might vary according to admixture design variations. Despite the fact that the design of experiments is utilized to simplify and optimize the research of sustainable energies, the studies employing eggshell concrete are still uncommon. The powdered egg shells were employed as fine concrete aggregate as a tool of sustainable energies. The flexural and compressive strength of concrete with (5%, 10%, and 15%) and without egg shell are examined, and the findings are predicted by artificial neural network (ANN) and genetic algorithm (GA) as a hybridized model of ANN‐GA. The contour plot research revealed that eggshell powder boosted the energy stability in an appropriate replacement proportion of 5% to 10%. Conversely, for mix designs with a larger water ratio, the partial substitution with eggshell powder is preferable. The findings demonstrate that with 5% ESP replacement, the strengths were greater than in control concrete, indicating that 5% ESP is an ideal content for maximal strength. Furthermore, in terms of transport qualities, the performance of ESP concretes was equivalent to control concrete up to 15% ESP substitution. The statistical regression indices as determination coefficient (R2) and root‐mean‐square error demonstrated that the ANN‐GA model is an effective tool for formulating and predicting the flexural and compressive strength of eggshell concrete to develop sustainable energies.

show abstract

Retraction Note to: Potential of soft computing approach for evaluating the factors affecting the capacity of steel–concrete composite beam

Cited by 6 publications

References 5 publications

Hybrid machine learning hydrological model for flood forecast purpose

Hybrid machine learning hydrological model for flood forecast purpose

Analysis of groundwater pollution in a petroleum refinery energy contributed in rock mechanics throughANFIS‐AHP

The metaheuristic optimization of the mechanical properties of sustainable energies using artificial neural networks and genetic algorithm: A case study by eggshell fine waste

Contact Info

Product

Resources

About