Application of 3-algorithm ANN programming to predict the strength performance of hydrated-lime activated rice husk ash treated soil

Onyelowe, Kennedy C.; Iqbal, Mudassir; Jalal, Fazal E.; Onyia, Michael E.; Onuoha, Ifeanyichukwu C.

doi:10.1007/s41939-021-00093-7

Cited by 54 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Onyelowe et al, 2021 [16] applied evolutionary hybrid algorithms of ANN, Levenberg-Marquardt back-propagation (LMBP), Bayesian programming (BP), and conjugate gradient (CG) algorithms to predict the CBR value of ash-treated expansive soil, and the correlation was found to be R 2 = 0.9.…”

Section: Short Literature Review On Soft Computing Techniques For Estimation Of the California Bearing Ratiomentioning

confidence: 99%

“…In this research, the following three performance indicators were used to assess the prediction accuracy of the developed models: the root mean square error (RMSE) [93][94][95][96], mean absolute error (MAE) [19,97,98], and correlation coefficient (R 2 ) [16,97,98]:…”

Section: Prediction Accuracy Indicatorsmentioning

confidence: 99%

“…The correlation coefficient R 2 of the various models during the training stage was 0.937, 0.939, and 0.995 for the REPT, RSS-REPT, and RSS-ET models, respectively (Table 3). Correlation coefficient values in excess of 0.8 are generally considered to establish a close agreement between the measured and predicted values [16][17][18]93,[99][100][101][102][103]. However, the prediction accuracy of the testing dataset dropped significantly to R 2 = 0.709 and R 2 = 0.783 for the REPT and RSS-REPT models, respectively.…”

Section: Prediction Accuracymentioning

confidence: 99%

“…Artificial intelligence models can simulate highly non-linear associations between numerous input and output parameters and can therefore provide more accurate predictions than those obtained using simple and multiple regression analysis [13][14][15]. During the last decade numerous artificial intelligence models techniques, including artificial neural network (ANN) [16], adaptive neuro-fuzzy inference system (ANFIS) [17], gene and multi expression programming [18][19][20], ensemble framework techniques (for instance, bagging, rotation forest, and random subspace (RSS)) [21], decision tree (DT) [22], and support vector machine (SVM) [23], have been used in engineering and numerous other disciplines [13,24]. Hybrid ensemble strategies including bagging, RSS, and boosting with ensemble pruning are particularly suitable for extracting deep features from multivariate data [25].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

et al. 2021

Self Cite

View full text Add to dashboard Cite

The California Bearing Ratio (CBR) is an important index for evaluating the bearing capacity of pavement subgrade materials. In this research, random subspace optimization-based hybrid computing models were trained and developed for the prediction of the CBR of soil. Three models were developed, namely reduced error pruning trees (REPTs), random subsurface-based REPT (RSS-REPT), and RSS-based extra tree (RSS-ET). An experimental database was compiled from a total of 214 soil samples, which were classified according to AASHTO M 145, and included 26 samples of A-2-6 (clayey gravel and sand soil), 3 samples of A-4 (silty soil), 89 samples of A-6 (clayey soil), and 96 samples of A-7-6 (clayey soil). All CBR tests were performed in soaked conditions. The input parameters of the models included the particle size distribution, gravel content (G), coarse sand content (CS), fine sand content (FS), silt clay content (SC), organic content (O), liquid limit (LL), plastic limit (PL), plasticity index (PI), optimum moisture content (OMC), and maximum dry density (MDD). The accuracy of the developed models was assessed using numerous performance indexes, such as the coefficient of determination, relative error, MAE, and RMSE. The results show that the highest prediction accuracy was obtained using the RSS-based extra tree optimization technique.

show abstract

Section: Short Literature Review On Soft Computing Techniques For Estimation Of the California Bearing Ratiomentioning

confidence: 99%

Section: Prediction Accuracy Indicatorsmentioning

confidence: 99%

Section: Prediction Accuracymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Not only does the machine learning approach predicts outputs in a more precise form but also have the capability of inferring a decision boundary that separates the input data space into two distinctive regions of erosion and nonerosion segments, thereby, making soil loss prediction worthwhile [20]. As systems imitate the human brain, machine learning techniques have been applied in various areas of engineering and even beyond and are useful in making predictions, performing clustering, extracting association rules, or making decisions from a given dataset [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Prediction of Soil Loss from Observed Rainstorm Parameters in an Erosion Watershed Using Genetic Programming

Onyelowe

Ebid

Nwobia

2021

Applied and Environmental Soil Science

Self Cite

View full text Add to dashboard Cite

Various environmental problems such as soil degradation and landform evolutions are initiated by a natural process known as soil erosion. Aggregated soil surfaces are dispersed through the impact of raindrop and its associated parameters, which were considered in this present work as function of soil loss. In an attempt to monitor environmental degradation due to the impact of raindrop and its associated factors, this work has employed the learning abilities of genetic programming (GP) to predict soil loss deploying rainfall amount, kinetic energy, rainfall intensity, gully head advance, soil detachment, factored soil detachment, runoff, and runoff rate database collected over a three-year period as predictors. Three evolutionary trials were executed, and three models were presented considering different permutations of the predictors. The performance evaluation of the three models showed that trial 3 with the highest parametric permutation, i.e., that included the influence of all the studied parameters showed the least error of 0.1 and the maximum coefficient of determination (R2) of 0.97 and as such is the most efficient, robust, and applicable GP model to predict the soil loss value.

show abstract

Novel hybrid models of ANFIS and metaheuristic optimizations (SCE and ABC) for prediction of compressive strength of concrete using rebound hammer field test

Jalal²,

Iqbal³

et al. 2022

Front. Struct. Civ. Eng.

View full text Add to dashboard Cite

Application of 3-algorithm ANN programming to predict the strength performance of hydrated-lime activated rice husk ash treated soil

Cited by 54 publications

References 22 publications

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

Evolutionary Prediction of Soil Loss from Observed Rainstorm Parameters in an Erosion Watershed Using Genetic Programming

Novel hybrid models of ANFIS and metaheuristic optimizations (SCE and ABC) for prediction of compressive strength of concrete using rebound hammer field test

Contact Info

Product

Resources

About