Individual Machine Learning Techniques Research Articles

Compressive Strength Estimation of Geopolymer Composites through Novel Computational Approaches.

The application of artificial intelligence approaches like machine learning (ML) to forecast material properties is an effective strategy to reduce multiple trials during experimentation. This study performed ML modeling on 481 mixes of geopolymer concrete with nine input variables, including curing time, curing temperature, specimen age, alkali/fly ash ratio, Na2SiO3/NaOH ratio, NaOH molarity, aggregate volume, superplasticizer, and water, with CS as the output variable. Four types of ML models were employed to anticipate the compressive strength of geopolymer concrete, and their performance was compared to find out the most accurate ML model. Two individual ML techniques, support vector machine and multi-layer perceptron neural network, and two ensembled ML methods, AdaBoost regressor and random forest, were employed to achieve the study’s aims. The performance of all models was confirmed using statistical analysis, k-fold evaluation, and correlation coefficient (R2). Moreover, the divergence of the estimated outcomes from those of the experimental results was noted to check the accuracy of the models. It was discovered that ensembled ML models estimated the compressive strength of the geopolymer concrete with higher precision than individual ML models, with random forest having the highest accuracy. Using these computational strategies will accelerate the application of construction materials by decreasing the experimental efforts.

Application of Soft Computing Techniques to Predict the Strength of Geopolymer Composites

Geopolymers may be the best alternative to ordinary Portland cement because they are manufactured using waste materials enriched in aluminosilicate. Research on geopolymer composites is accelerating. However, considerable work, expense, and time are needed to cast, cure, and test specimens. The application of computational methods to the stated objective is critical for speedy and cost-effective research. In this study, supervised machine learning approaches were employed to predict the compressive strength of geopolymer composites. One individual machine learning approach, decision tree, and two ensembled machine learning approaches, AdaBoost and random forest, were used. The coefficient correlation (R2), statistical tests, and k-fold analysis were used to determine the validity and comparison of all models. It was discovered that ensembled machine learning techniques outperformed individual machine learning techniques in forecasting the compressive strength of geopolymer composites. However, the outcomes of the individual machine learning model were also within the acceptable limit. R2 values of 0.90, 0.90, and 0.83 were obtained for AdaBoost, random forest, and decision models, respectively. The models’ decreased error values, such as mean absolute error, mean absolute percentage error, and root-mean-square errors, further confirmed the ensembled machine learning techniques’ increased precision. Machine learning approaches will aid the building industry by providing quick and cost-effective methods for evaluating material properties.

Determining the Geotechnical Slope Failure Factors via Ensemble and Individual Machine Learning Techniques: A Case Study in Mandi, India

Landslide disaster risk reduction necessitates the investigation of different geotechnical causal factors for slope failures. Machine learning (ML) techniques have been proposed to study causal factors across many application areas. However, the development of ensemble ML techniques for identifying the geotechnical causal factors for slope failures and their subsequent prediction has lacked in literature. The primary goal of this research is to develop and evaluate novel feature selection methods for identifying causal factors for slope failures and assess the potential of ensemble and individual ML techniques for slope failure prediction. Twenty-one geotechnical causal factors were obtained from 60 sites (both landslide and non-landslide) spread across a landslide-prone area in Mandi, India. Relevant causal factors were evaluated by developing a novel ensemble feature selection method that involved an average of different individual feature selection methods like correlation, information-gain, gain-ratio, OneR, and F-ratio. Furthermore, different ensemble ML techniques (Random Forest (RF), AdaBoost (AB), Bagging, Stacking, and Voting) and individual ML techniques (Bayesian network (BN), decision tree (DT), multilayer perceptron (MLP), and support vector machine (SVM)) were calibrated to 70% of the locations and tested on 30% of the sites. The ensemble feature selection method yielded six major contributing parameters to slope failures: relative compaction, porosity, saturated permeability, slope angle, angle of the internal friction, and in-situ moisture content. Furthermore, the ensemble RF and AB techniques performed the best compared to other ensemble and individual ML techniques on test data. The present study discusses the implications of different causal factors for slope failure prediction.

Bayesian optimization based machine learning approaches for prediction of plug-in electric vehicle state-of-charge

Abstract The growing popularity of plug-in electric vehicle (PEV) around the world makes complexity in power sector. The distribution system is subjected to overload due to the random penetration of PEVs in charging depending on their level of state-of-charge (SOC). The accurate calculation and prediction of SOC considering their travel distance makes significant impact on the level of SOC. Therefore, the accurate SOC prediction of PEVs is need of the hour in transportation sector. However, the prediction of SOC allows the PEVs owners to decide the charging/discharging mode or priority based charging. Recently, machine learning techniques are gaining popularity in prediction analysis of different parameters. This article proposes machine learning approaches in combination with Bayesian optimization (BO) for prediction analysis of PEVs SOC. The gradient boosting method (GBM) and random forest method (RFM) are used as machine learning approaches in this work. The energy consumption pattern, different battery capacities and total trip distance of PEVs are included in calculation for the estimation of accurate SOC. A satisfactory result of SOC prediction has been observed using both GBM-BO and RFM-BO. The comparative study of results reveals the performance and efficacy of GBM-BO against RFM-BO in the PEVs SOC prediction analysis. Moreover, the hybrid machine learning techniques with BO performs better than individual machine learning techniques in the prediction analysis of PEVs SOC.

Prediction of Skin Disease with Three Different Feature Selection Techniques Using Stacking Ensemble Method.

Skin disease is the most common problem between people. Due to pollution and deployment of ozone layer, harmful UV rays of sun burn the skin and develop various types of skin diseases. Nowadays, machine learning and deep learning algorithms are generally used for diagnosis for various kinds of diseases. In this study, we have applied three feature extraction techniques univariate feature selection, feature importance, and correlation matrix with heat map to find the optimum data subset of erythemato-squamous disease. Four classification techniques Gaussian Naïve Bayesian (NB), decision tree (DT), support vector machine (SVM), and random forest are used for measuring the performance of model. Stacking ensemble technique is then applied to enhance the prediction performance of the model. The proposed method used for measuring the performance of the model. It is finding that the optimal subset of the erythemato-squamous disease is performed well in the case of correlation and heat map feature selection techniques. The mean value, slandered deviation, root mean square error, kappa statistical error, and area under receiver operating characteristics and accuracy are calculated for demonstrating the effectiveness of the proposed model. The feature selection techniques applied with staking ensemble technique gives the better result as compared to individual machine learning techniques. The obtained results show that the performance of proposed model is higher than previous results obtained by researchers.

Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach

In this paper, an intelligent approach based on the machine learning technique is proposed for predicting the compressive strength of concrete. This approach employs the adaptive boosting algorithm to construct a strong learner by integrating several weak learners, which can find the mapping between the input data and output data. The weak learner whose predicting error is small will have a larger weight in the entire system, thus the overall accuracy of the strong learner will be enhanced. A total of 1030 sets of concrete compressive strength tests is collected to train and test the learners, in which the concrete mixture components (e.g., coarse/fine aggregates, cement, water, additive, etc.) and the curing time are set as the input data while the compressive strength value is set as the output data. The proposed approach is validated through a 10-fold cross validation method, and reaches an average accuracy of over 95% in sense of determination coefficient. In addition, a new dataset of 103 samples for concrete compressive strength is also adopted to demonstrate the generalization power of the proposed mode. The proposed approach is also compared to some other individual machine learning techniques that are already applied in this field, e.g., artificial neural network (ANN) and support vector machine (SVM), and shows superior advantages over these methods. Finally, the influence of some key factors in the adaptive boosting approach is also investigated, e.g., the amount of training data, the choice of weak learner, and the influence of the sensitivity and number of the input parameters. It is shown that using 80% of the total data for training can obtain acceptable prediction results and decision tree is the best choice for the weak learner in the boosting framework. Also, the importances of different input variables are obtained based on the sensitivity analysis results.

Enhanced Predictive Models for Construction Costs: A Case Study of Turkish Mass Housing Sector

The analysis of a construction project, regarding cost, is one of the most vital problem in planning. Due to its nature, the construction sector is an area of strong competition and estimation works are of vital importance. In recent years the Turkish Republic has started a serious urban regeneration movement in parallel to its economic development. This study is based on the drawings and quantities of 63 detached multi-story reinforced concrete housing unit projects of the Housing Development Administration (TOKI) and the Turkey Residential Building Cooperative Union (TURKKONUT). TOKI is a public company and its projects are that have been applied to 282 separate projects and are being applied to a further 266. On the other side TURKKONUT is a union of 1347 private building cooperative and have been completed 200,000 residential building. The main objective of this study is to improve the estimation accuracy of individual machine learning techniques, namely multi-layer perceptron and classification and regression trees and compares the performance of two machine learning meta-algorithms (i.e., bagging and random subspace) on a real world construction cost estimation problem. The study shows that the estimation accuracy of ensemble models are better than the models that constructed by their base learners and ensemble models may improve individual machine learning models.

Cheminformatics Modeling of Amine Solutions for Assessing their CO2 Absorption Properties.

As stricter regulations on CO2 emissions are adopted worldwide, identifying efficient chemical processes to capture and recycle CO2 is of critical importance for industry. The most common process known as amine scrubbing suffers from the lack of available amine solutions capable of capturing CO2 efficiently. Tertiary amines characterized by low heats of reaction are considered good candidates but their absorption properties can significantly differ from one analogue to another despite high structural similarity. Herein, after collecting and curating experimental data from the literature, we have built a modeling set of 41 amine structures with their absorption properties. Then we analyzed their chemical composition using molecular descriptors and non-supervised clustering. Furthermore, we developed a series of quantitative structure-property relationships (QSPR) to assess amines' CO2 absorption properties from their structural characteristics. These models afforded reasonable prediction performances (e. g., Q2LOO =0.63 for CO2 absorption amount) even though they are solely based on 2D chemical descriptors and individual machine learning techniques (random forest and neural network). Overall, we believe the chemical analysis and the series of QSPR models presented in this proof-of-concept study represent new knowledge and innovative tools that could be very useful for screening and prioritizing hypothetical amines to be synthesized and tested experimentally for their CO2 absorption properties.

A hybrid case adaptation approach for case-based reasoning

Case-Based Reasoning is a methodology for problem solving based on past experiences. This methodology tries to solve a new problem by retrieving and adapting previously known solutions of similar problems. However, retrieved solutions, in general, require adaptations in order to be applied to new contexts. One of the major challenges in Case-Based Reasoning is the development of an efficient methodology for case adaptation. The most widely used form of adaptation employs hand coded adaptation rules, which demands a significant knowledge acquisition and engineering effort. An alternative to overcome the difficulties associated with the acquisition of knowledge for case adaptation has been the use of hybrid approaches and automatic learning algorithms for the acquisition of the knowledge used for the adaptation. We investigate the use of hybrid approaches for case adaptation employing Machine Learning algorithms. The approaches investigated how to automatically learn adaptation knowledge from a case base and apply it to adapt retrieved solutions. In order to verify the potential of the proposed approaches, they are experimentally compared with individual Machine Learning techniques. The results obtained indicate the potential of these approaches as an efficient approach for acquiring case adaptation knowledge. They show that the combination of Instance-Based Learning and Inductive Learning paradigms and the use of a data set of adaptation patterns yield adaptations of the retrieved solutions with high predictive accuracy.