Hybrid BO-XGBoost and BO-RF Models for the Strength Prediction of Self-Compacting Mortars with Parametric Analysis.

Self-compacting mortar (SCM) has superior workability and long-term durable performance compared to traditional mortar. The strength of SCM, including both its compressive and flexural strengths, is a crucial property that is determined by appropriate curing conditions and mix design parameters. In the context of materials science, predicting the strength of SCM is challenging because of multiple influencing factors. This study employed machine learning techniques to establish SCM strength prediction models. Based on ten different input parameters, the strength of SCM specimens were predicted using two different types of hybrid machine learning (HML) models, namely Extreme Gradient Boosting (XGBoost) and the Random Forest (RF) algorithm. HML models were trained and tested by experimental data from 320 test specimens. In addition, the Bayesian optimization method was utilized to fine tune the hyperparameters of the employed algorithms, and cross-validation was employed to partition the database into multiple folds for a more thorough exploration of the hyperparameter space while providing a more accurate assessment of the model's predictive power. The results show that both HML models can successfully predict the SCM strength values with high accuracy, and the Bo-XGB model demonstrated higher accuracy (R2 = 0.96 for training and R2 = 0.91 for testing phases) for predicting flexural strength with low error. In terms of compressive strength prediction, the employed BO-RF model performed very well, with R2 = 0.96 for train and R2 = 0.88 testing stages with minor errors. Moreover, the SHAP algorithm, permutation importance and leave-one-out importance score were used for sensitivity analysis to explain the prediction process and interpret the governing input variable parameters of the proposed HML models. Finally, the outcomes of this study might be applied to guide the future mix design of SCM specimens.

Immobilization possibility of tannery wastewater contaminants in the tiles fixing mortars for eco-friendly land disposal.

The Hazaribagh tannery area of Bangladesh is currently facing an enormous problem regarding the harmful impacts of wastewater produced from leather industries on the surrounding environment due to the presence of contaminants at a toxic level. As such, the current study aims to analyze the entrapment of tannery wastewater's pollutants inside the mortar specimens for sustainability. Two types of binding agents such as Portland Composite Cement (PCC) and Ready Mixed Dry Mortar (RMDM) were employed to prepare separate mortar pastes in which the collected tannery wastewater was used as mixing liquid. Also, five types of samples including brick walls made with only the PCC, where tiles walls and blocks constructed with both types of binding agents were built. Analytical results show that the surrogate contaminated water mixed mortar blocks possessed about 6-14% lower compressive strength than that of the blocks prepared with drinking water. Moreover, the examined heavy metals were observed below the limit of detection in the curing liquid of studied tiles walls during the whole test protocol of 360 days period. The explicit outcomes of this study might be a promising solution to minimize the effects of tannery wastewater contaminants on the environment by utilizing this wastewater as a mixing component in the tiles fixing mortar of walls and floors.

Effects of specimen size and mix ratio on the nickel migration behavior of landfill waste mixed mortar.

Landfill solid waste management system poses the potential source of silent wide-spread heavy metals like nickel poisoning in the entire ecosystem of nearby environment. Nickel containing demolish solid wastes are disposed at landfill zones to a great extent from where nickel migrate into the food chain through the surface water body as well as groundwater. Consequently, nickel exposure may cause different environmental problems. From this sense, it may be an attractive proposal to recycle the waste as a sustainable product. Herein is presented a long-term feasibility study on potential leaching behavioral pattern of nickel from different sizes and mixes based solidified landfill waste mixed mortar block. The calculated results revealed the larger sizes block entrapped more nickel content than the smaller in relation to the available for leaching. Moreover, the specimen bearing the higher amount of waste resulted the significant nickel immobilization within the crystalline structure. The study observed the fixation results 97.72%-99.35%, 97.08%-99.11%, 96.19%-98.58% and 95.86%-91.6% under the stabilizing agent to fine aggregate mixing combination 1:1, 1:1.5, 1:2 and 1:2.5 respectively where 30% of the total volume of fine aggregate was replaced by landfill waste. Although, mechanical strength test of all surrogate waste forms was also conducted that showed acceptable performance for land disposal, the current research pointing out that constructed green products were non-hazardous except the specimens having mixture ratio 1:2.5 because nickel ion release mechanism was observed under this ratio by surface decay or physical erosion of the monolithic matrices. Furthermore, semi-empirical based dominant leaching mechanism models were justified against the goodness of fit statistical parameters for interpreting the experimental observations of nickel transport profile where the adopted models possessed strong potential for predicting Ni content with high accuracy.

Prevalence and determinants of chronic malnutrition among preschool children: a cross-sectional study in Dhaka City, Bangladesh.

Chronic malnutrition is one of the major causes of morbidity and mortality among preschool children and the future productivity of nations. To understand the prevalence of chronic malnutrition and to identify the factors affecting height-for-age z-score (HAZ) among preschool children, a cross-sectional study was conducted among 380 randomly-selected children aged less than five years in Dhaka city, Bangladesh. Results of analysis of this study data revealed that the prevalence of stunting among preschool children in Dhaka city was 39.5%, with 25% severely stunted and 14% moderately stunted (p<0.001). Results of bivariate analysis revealed that socioeconomic and demographic factors were most significantly associated with the stunting of children. Children were found to be well-nourished if their parents had a tertiary-level education or higher and if the mother held a job and had good knowledge of nutrition. Well-nourishment of the children were also associated with the height of mothers (above 148 cm), good family educational background, normal birthweight, greater frequency of food intake (more than six times/day), and fewer fever episodes in the last six months. Results of multivariate linear regression models showed that height of mothers, birthweight of children, education of fathers, knowledge of mothers on nutrition, and frequency of feeding were the most significant factors that had an independent and direct influence on the stunting of children. To achieve the Millennium Development Goal target of 34% malnutrition prevalence by 2015, it is important to have specific government intervention to focus on the causes that directly influence the stunting of children.