The rapid growth of transportation sector and related emissions are attracting the attention of policymakers to ensure environmental sustainability. Therefore, the deriving factors of transport emissions are extremely important to comprehend. The role of electric vehicles is imperative amid rising transport emissions. Electric vehicles pave the way towards a low-carbon economy and sustainable environment. Successful deployment of electric vehicles relies heavily on energy consumption models that can predict energy consumption efficiently and reliably. Improving electric vehicles’ energy consumption efficiency will significantly help to alleviate driver anxiety and provide an essential framework for operation, planning, and management of the charging infrastructure. To tackle the challenge of electric vehicles’ energy consumption prediction, this study aims to employ advanced machine learning models, extreme gradient boosting, and light gradient boosting machine to compare with traditional machine learning models, multiple linear regression, and artificial neural network. Electric vehicles energy consumption data in the analysis were collected in Aichi Prefecture, Japan. To evaluate the performance of the prediction models, three evaluation metrics were used; coefficient of determination ( R²), root mean square error, and mean absolute error. The prediction outcome exhibits that the extreme gradient boosting and light gradient boosting machine provided better and robust results compared to multiple linear regression and artificial neural network. The models based on extreme gradient boosting and light gradient boosting machine yielded higher values of R², lower mean absolute error, and root mean square error values have proven to be more accurate. However, the results demonstrated that the light gradient boosting machine is outperformed the extreme gradient boosting model. A detailed feature important analysis was carried out to demonstrate the impact and relative influence of different input variables on electric vehicles energy consumption prediction. The results imply that an advanced machine learning model can enhance the prediction performance of electric vehicles energy consumption.

The current outbreak of monkeypox (mpox) has become a major public health concern because of the quick spread of this disease across multiple countries. Early detection and diagnosis of mpox is crucial for effective treatment and management. Considering this, the purpose of this research was to detect and validate the best performing model for detecting mpox using deep learning approaches and classification models. To achieve this goal, we evaluated the performance of five common pretrained deep learning models (VGG19, VGG16, ResNet50, MobileNetV2, and EfficientNetB3) and compared their accuracy levels when detecting mpox. The performance of the models was assessed with metrics (i.e., the accuracy, recall, precision, and F1-score). Our experimental results demonstrate that the MobileNetV2 model had the best classification performance with an accuracy level of 98.16%, a recall of 0.96, a precision of 0.99, and an F1-score of 0.98. Additionally, validation of the model with different datasets showed that the highest accuracy of 0.94% was achieved using the MobileNetV2 model. Our findings indicate that the MobileNetV2 method outperforms previous models described in the literature in mpox image classification. These results are promising, as they show that machine learning techniques could be used for the early detection of mpox. Our algorithm was able to achieve a high level of accuracy in classifying mpox in both the training and test sets, making it a potentially valuable tool for quick and accurate diagnosis in clinical settings.

As a fundamental feature of green building cost forecasting, external support is crucial. However, minimal research efforts have been directed to developing practical models for determining the impact of external public and private support on green construction projects’ costs. To fill the gap, the current research aims to develop a mathematical model to explore the balance of supply and demand under deflationary conditions for external green construction support and the accompanying spending adjustment processes. The most current datasets from 3578 green projects across Northern America were collected, pre-processed, analyzed, post-processed, and evaluated via cutting-edge machine learning (ML) techniques to retrieve the deep parameters affecting the green construction cost prediction process. According to the findings, public and private investments in green construction are projected to decrease the cost of green buildings. Furthermore, the impact of public and private investment on green construction cost reduction during deflationary periods is more significant than its influence during inflation. As a result, decision-makers may utilize the suggested model to monitor and evaluate the yearly optimal external investment in green building construction.

This work describes an experimental and machine learning approach for the prediction of selenite removal on chemically modified zeolite for water treatment. Breakthrough curves were constructed using iron-coated zeolite adsorbent and the adsorption behavior was evaluated as a function of an initial contaminant concentration as well as the ionic strength. An elevated selenium concentration in water threatens human health and aquatic life. The migration of this metalloid from the contaminated sites and the problems associated with its high releases into the water has become a major environmental concern. The mobility of this emerging metalloid in the contaminated water prompted the development of an efficient, cost-effective adsorbent for its removal. Selenite $\left[\mathrm{Se}\left(\mathrm{IV}\right)\right]$ removal from aqueous solutions was studied in laboratory-scale continuous and packed-bed adsorption columns using iron-coated natural zeolite adsorbents. The proposed adsorbent combines iron oxide and natural zeolite’s ability to bind contaminants. Breakthrough curves were initially obtained under variable experimental conditions, including the change in the initial concentration of $\mathrm{Se}\left(\mathrm{IV}\right)$, and the ionic strength of solutions. Investigating the effect of these parameters will enhance selenite mobility retardation in contaminated water. Continuous adsorption experiment findings will evaluate the efficiency of this economical and naturally-based adsorbent for selenite removal and fate in water. Multilinear and non-linear regressions approaches were utilized, yet low coefficients of determination values were respectively obtained. Then, a comparative analysis of five boosted regression tree algorithms for a selenite breakthrough curve prediction was performed. AdaBoost, Gradient boosting, $XGBoost$, $LightGBM$, and $CatBoost$ models were analyzed using the experimental data of the packed-bed columns. The performance of these models for the breakthrough curve prediction under different operation conditions, such as initial selenite concentration and ionic strength, was discussed. The applicability of these models was evaluated using performance metrics (i.e., Mean Absolute Error ($MAE$), Root Mean Square Error ($RMSE$), Mean Absolute Percentage Error ($MAPE$), and coefficient of determination ($R^2$). The $CatBoost$ model provided the best fit for a breakthrough prediction with a coefficient of determination $R^2$ equal to 99.57. The k-fold cross-validation technique and the statistical metrics verify this model’s accurateness. A feature importance assessment indicated that $\mathrm{Se}\left(\mathrm{IV}\right)$ initial concentration was the most influential experimental variable, while the ionic strength had the least effect. This finding was consistent with the column transport results, which observed $\mathrm{Se}\left(\mathrm{IV}\right)$ sorption dependency on its inlet concentration; simultaneously, the ionic strength effect was negligible. This work proposes implementing machine learning-based approaches for predicting water remediation-associated processes. The significance of this work was to provide an alternative method for investigating selenite adsorption behavior and predicting the breakthrough curves using a machine-based approach. This work also highlighted the importance of management practices of adsorption processes involved in water remediation.

Highway construction projects are important for financial and social development in the United States. Such types of construction are usually accompanied by construction delay, causing liquidated damages ($LDs$) as a contractual provision are vital in construction agreements. Accurate quantification of $LDs$ is essential for contract parties to avoid legal disputes and unfair provisions due to the lack of appropriate documentation. This paper effort sought to develop an ensemble machine learning technique ($EMLT$) that combines algorithms of the Extreme Gradient Boosting ($XGBoost)$, Categorical Boosting ($CatBoost$), k-Nearest Neighbor ($kNN$), Light Gradient Boosting Machine ($LightGBM$), Artificial Neural Network ($ANN$), and Decision Tree ($DT$) for the prediction of $LDs$ in highway construction projects. Key attributes are identified and examined to predict the interrelated correlations among the influential features to develop accurate forecast models to assess the impact of each delay factor. Various machine-learning-based models were developed, where the different modeling outputs were analyzed and compared. Four performance matrices such as Root Mean Square Error ($RMSE$), Mean Absolute Error ($MAE$), Mean Absolute Percentage Error ($MAPE$), and Coefficient of Determination ($R^2$) were used to assess and evaluate the accuracy of the implemented machine learning ($ML$) algorithms. The prediction outputs implied that the developed EMLT model has shown better performance compared to other ML-based models, where it has the highest accuracy of 0.997, compared to the DT, kNN, CatBoost, XGBoost, LightGBM, and ANN with an accuracy of 0.989, 0.988, 0.986, 0.975, 0.873, and 0.689, respectively. Thus, the findings of this research designate that the EMLT model can be used as an effective administrative decision adding tool for forecasting the $LDs$. As a result, this paper emphasizes ML’s potential to aid in the advancement of computerization as a comprehensible subject of investigation within highway building projects.

The influence of concrete mix properties on the shear strength of slender structured concrete beams without stirrups (SRCB-WS) is a widespread point of contention. Over the past six decades, the shear strength of SRCB-WS has been studied extensively in both experimental and theoretical contexts. The most recent version of the ACI 318-19 building code requirements updated the shear strength equation for SRCB-WS by factoring in the macroeconomic factors and the contribution of the longitudinal steel structural ratio. However, the updated equation still does not consider the effect of the shear span ratio ($a/d$) and the yield stress of longitudinal steel rebars ($F_y$). Therefore, this study investigates the importance of the most significant potential variables on the shear strength of SRCB-WS to help develop a gene expression-based model to estimate the shear strength of SRCB-WS. A database of 784 specimens was used from the literature for training and testing the proposed gene expression algorithm for forecasting the shear strength of SRCB-WS. The collected datasets are comprehensive, wherein all considered concrete properties were considered over the previous 68 years. The performance of the suggested algorithm versus the ACI 318-19 equation was statistically evaluated using various measures, such as root mean square error, mean absolute error, mean absolute percentage error, and the coefficient of determination. The evaluation results revealed the superior performance of the proposed model over the current ACI 318-19 equation. In addition, the proposed model is more comprehensive and considers additional variables, including the effect of the shear span ratio and the yield stress of longitudinal steel rebars. The developed model reflects the power of employing gene expression algorithms to design reinforced concrete elements with high accuracy.