A novel systematic and evolved approach based on XGBoost-firefly algorithm to predict Young’s modulus and unconfined compressive strength of rock

Cao, Jing; Gao, Juncheng; Rad, Hima Nikafshan; Mohammed, Ahmed; Hasanipanah, Mahdi; Zhou, Jian

doi:10.1007/s00366-020-01241-2

Cited by 74 publications

(23 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the best value for R 2 is one. Regarding the SI parameter, it can be said that a model has a poor performance when SI > 0.3, a fair performance when 0.2 < SI < 0.3, a good performance when 0.1 < SI < 0.2, and an excellent performance when SI < 0.1 [ 43 , 101 ]. Moreover, in Eq ( 9 ) the OBJ parameter was also used to assess the efficiency of the proposed models as an integrated performance parameter.…”

Section: Model Performance Assessment Criteriamentioning

confidence: 99%

Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes

Ahmed

Mohammed

et al. 2021

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Geopolymer concrete is an inorganic concrete that uses industrial or agro by-product ashes as the main binder instead of ordinary Portland cement; this leads to the geopolymer concrete being an eco-efficient and environmentally friendly construction material. A variety of ashes used as the binder in geopolymer concrete such as fly ash, ground granulated blast furnace slag, rice husk ash, metakaolin ash, and Palm oil fuel ash, fly ash was commonly consumed to prepare geopolymer concrete composites. The most important mechanical property for all types of concrete composites, including geopolymer concrete, is the compressive strength. However, in the structural design and construction field, the compressive strength of the concrete at 28 days is essential. Therefore, achieving an authoritative model for predicting the compressive strength of geopolymer concrete is necessary regarding saving time, energy, and cost-effectiveness. It gives guidance regarding scheduling the construction process and removal of formworks. In this study, Linear (LR), Non-Linear (NLR), and Multi-logistic (MLR) regression models were used to develop the predictive models for estimating the compressive strength of fly ash-based geopolymer concrete (FA-GPC). In this regard, a comprehensive dataset consists of 510 samples were collected in several academic research studies and analyzed to develop the models. In the modeling process, for the first time, twelve effective variable parameters on the compressive strength of the FA-GPC, including SiO2/Al2O3 (Si/Al) of fly ash binder, alkaline liquid to binder ratio (l/b), fly ash (FA) content, fine aggregate (F) content, coarse aggregate (C) content, sodium hydroxide (SH)content, sodium silicate (SS) content, (SS/SH), molarity (M), curing temperature (T), curing duration inside ovens (CD) and specimen ages (A) were considered as the modeling input parameters. Various statistical assessments such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Scatter Index (SI), OBJ value, and the Coefficient of determination (R2) were used to evaluate the efficiency of the developed models. The results indicated that the NLR model performed better for predicting the compressive strength of FA-GPC mixtures compared to the other models. Moreover, the sensitivity analysis demonstrated that the curing temperature, alkaline liquid to binder ratio, and sodium silicate content are the most affecting parameter for estimating the compressive strength of the FA-GPC.

show abstract

Section: Model Performance Assessment Criteriamentioning

confidence: 99%

Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes

Ahmed

Mohammed

et al. 2021

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning models have achieved impressive success in many fields, such as healthcare [12], engineering projects [13], cyber security [14], CV [15,16], NLP [17][18][19], etc. However, these models seem to have inevitable vulnerability and adversarial examples [1,2,20,21], as firstly studied in CV, to fool neural network models while being imperceptible for humans.…”

Section: Related Workmentioning

confidence: 99%

CRank: Reusable Word Importance Ranking for Text Adversarial Attack

Chen

Liu

2021

Applied Sciences

View full text Add to dashboard Cite

Deep learning models have been widely used in natural language processing tasks, yet researchers have recently proposed several methods to fool the state-of-the-art neural network models. Among these methods, word importance ranking is an essential part that generates text adversarial examples, but suffers from low efficiency for practical attacks. To address this issue, we aim to improve the efficiency of word importance ranking, making steps towards realistic text adversarial attacks. In this paper, we propose CRank, a black box method utilized by our innovated masking and ranking strategy. CRank improves efficiency by 75% at the ’cost’ of only a 1% drop of the success rate when compared to the classic method. Moreover, we explore a new greedy search strategy and Unicode perturbation methods.

show abstract

“…The main purpose of the grouting process is to cover the sand particles with a high flowable grout material. The component's compressive and bonding strengths will be greatly improved as a result [5]. Water reducer polymers are widely used in the cement grout (CG), cementitious materials (CM), and concrete industries to reduce the content of water and improve the physical and structural properties of cement [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Modeling Flexural and Compressive Strengths Behaviour of Cement-Grouted Sands Modified with Water Reducer Polymer

et al. 2022

Self Cite

View full text Add to dashboard Cite

By using the American Society for Testing and Materials and British Standards standards, the impact of various grading of sand (Five types of sand) on the compressive strength (CS) of the cement grout (CG) treated with water reducer polymer is investigated. The properties of CG treated with polymer up to 0.16 % of cement weight were investigated and quantified in both fresh and hardened states. The water to cement ratio (w/c) was reduced by 21.9 to 54.1%, and the CG flow time was retained between 18 and 23 seconds. The highest compression strength was achieved at seven and 28 days for the cement-grouted sand using the coarser-graded sand than finer-graded sand at low w/c ranged between 0.50 and 0.53. The highest compression strength was obtained at high w/c for the cement grout mixed with the fine-grained sands compared to coarse-grained sands. Adding water reducer polymer enhances the compressive strength (spc) and cylindrical compressive strength (scc) by 113 to 577% and 53 to 459%, depending on mix proportion and curing period. An amorphous gel fills the porous places between the cement particles were formed when the CG was treated with water reducer polymer, which reduces voids, increases porosity, and increases the cement's dry density; as a result, the CS of the CG increases significantly. To evaluate the CS of CG with different grain sizes, w/c, percentage of polymer, and curing age, linear and nonlinear techniques were used. according to the bs standard, the CS of the CG produced was 71% higher than that of the identical mix produced according to the ASTM standard. Compared to the other sands, the cement grout produced with finer sand grading had the maximum flexural strength at all testing ages.

show abstract

A novel systematic and evolved approach based on XGBoost-firefly algorithm to predict Young’s modulus and unconfined compressive strength of rock

Cited by 74 publications

References 84 publications

Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes

Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes

CRank: Reusable Word Importance Ranking for Text Adversarial Attack

Modeling Flexural and Compressive Strengths Behaviour of Cement-Grouted Sands Modified with Water Reducer Polymer

Contact Info

Product

Resources

About