Prediction of International Roughness Index Based on Stacking Fusion Model

Adaptive habitat biogeography-based optimizer for optimizing deep CNN hyperparameters in image classification

Deep Convolutional Neural Networks (DCNNs) have shown remarkable success in image classification tasks, but optimizing their hyperparameters can be challenging due to their complex structure. This paper develops the Adaptive Habitat Biogeography-Based Optimizer (AHBBO) for tuning the hyperparameters of DCNNs in image classification tasks. In complicated optimization problems, the BBO suffers from premature convergence and insufficient exploration. In this regard, an adaptable habitat is presented as a solution to these problems; it would permit variable habitat sizes and regulated mutation. Better optimization performance and a greater chance of finding high-quality solutions across a wide range of problem domains are the results of this modification's increased exploration and population diversity. AHBBO is tested on 53 benchmark optimization functions and demonstrates its effectiveness in improving initial stochastic solutions and converging faster to the optimum. Furthermore, DCNN-AHBBO is compared to 23 well-known image classifiers on nine challenging image classification problems and shows superior performance in reducing the error rate by up to 5.14%. Our proposed algorithm outperforms 13 benchmark classifiers in 87 out of 95 evaluations, providing a high-performance and reliable solution for optimizing DNNs in image classification tasks. This research contributes to the field of deep learning by proposing a new optimization algorithm that can improve the efficiency of deep neural networks in image classification.

Coastal Flood risk assessment using ensemble multi-criteria decision-making with machine learning approaches

Coastal areas are at a higher risk of flooding, and novel changes in the climate are induced to raise the sea level. Flood acceleration and frequency have increased recently because of unplanned infrastructural conveniences and anthropogenic activities. Therefore, the assessment of flood susceptibility mapping is considered the most significant flood management model. In this paper, flood susceptibility identification is performed by applying the innovative Multi-criteria decision-making model (MCDM) called Analytical Hierarchy Process (AHP) by ensembles with Support vector machine (AHP-SVM) and Decision Tree (AHP-DT). This model combines two Representation concentration pathway (RCP) scenarios such as RCP 2.6 & RCP 8.5. The factors influencing the coastal flooding in Bandar Abbas, Iran, identified through Flood susceptibility mapping. Multi-criteria decision-making (MCDM) has been applied to evaluate the Coastal flood conditioning factors, and ensemble machine learning (ML) approaches are employed for Coastal risk factor (CRF) prediction and classification. The statistical variances are measured through Friedman and Wilcoxon signed rank tests and statistical metrics such as Accuracy, sensitivity, and specificity. Among the models, AHP-DT obtained an improved AUC value of ROC as 0.95. After applying the ML models, the northern and western park of Raidak Basin River recognises very low and low flood susceptibility because of their topographic characteristics. The eastern part of the middle section fell very high and high CFSM. Observed from this result analysis, the people living nearer to the coastline are distributed by the low to medium exposure in the region of the west and middle of the considered study area. The results of this study can help decision-makers take necessary risk reduction approaches in the high-risk flooding zones of the coastal system.

Cracking spoilage in jar cream cheese: Introducing, modeling and preventing

This study aimed to investigate the modeling of antimicrobial activity (AA) of nisin and sorbate on Clostridium sporogenes in jar cream cheese (JCC) using the linear regression (LR), multilayer perceptron (MLP) neural network, and reduced error pruning tree (REPTree) methods, in order to prevent the late blowing defect (LBD) in the cheese. Both preservatives used in JCC samples showed AA against C. sporogenes; so that sorbate at all the concentrations used in JCC samples inhibited cracking spoilage during storage period at 35 °C. However, nisin could not inhibit cracking spoilage at concentration of 30 ppm in the samples, and a higher concentration of it was needed. The three models used in this study, followed the similar pattern in both training and validation datasets for nisin and sorbat in JCC. The R2 and root mean square error (RMSE) values of training and validation datasets showed the superiority of the REPTree model compared to the MLP and LR models (conventional methods) in the modeling of AA of nisin and sorbate against C. sporogenes in JCC.

Heavy metals contamination, receptor model-based sources identification, sources-specific ecological and health risks in road dust of a highly developed city

The present study quantified Ni, Cu, Cr, Pb, Cd, As, Zn, and Fe levels in road dust collected from a variety of sites in Tangail, Bangladesh. The goal of this study was to use a matrix factorization model to identify the specific origin of these components and to evaluate the ecological and health hazards associated with each potential origin. The inductively coupled plasma mass spectrometry was used to determine the concentrations of Cu, Ni, Cr, Pb, As, Zn, Cd, and Fe. The average concentrations of these elements were found to be 30.77 ± 8.80, 25.17 ± 6.78, 39.49 ± 12.53, 28.74 ± 7.84, 1.90 ± 0.79, 158.30 ± 28.25, 2.42 ± 0.69, and 18,185.53 ± 4215.61 mg/kg, respectively. Compared to the top continental crust, the mean values of Cu, Pb, Zn, and Cd were 1.09, 1.69, 2.36, and 26.88 times higher, respectively. According to the Nemerow integrated pollution index (NIPI), pollution load index (PLI), Nemerow integrated risk index (NIRI), and potential ecological risk (PER), 84%, 42%, 30%, and 16% of sampling areas, respectively, which possessed severe contamination. PMF model revealed that Cu (43%), Fe (69.3%), and Cd (69.2%) were mainly released from mixed sources, natural sources, and traffic emission, respectively. Traffic emission posed high and moderate risks for modified NIRI and potential ecological risks. The calculated PMF model-based health hazards indicated that the cancer risk value for traffic emission, natural, and mixed sources had been greater than (1.0E-04), indicating probable cancer risks and that traffic emission posed 38% risk to adult males where 37% for both adult females and children.

Nondestructive Detection and Early Warning of Pavement Surface Icing Based on Meteorological Information

Monitoring and warning of ice on pavement surfaces are effective means to improve traffic safety in winter. In this study, a high-precision piezoelectric sensor was developed to monitor pavement surface conditions. The effects of the pavement surface temperature, water depth, and wind speed on pavement icing time were investigated. Then, on the basis of these effects, an early warning model of pavement icing was proposed using an artificial neural network. The results showed that the sensor could detect ice or water on the pavement surface. The measurement accuracy and reliability of the sensor were verified under long-term vehicle load, temperature load, and harsh natural environment using test data. Moreover, pavement temperature, water depth, and wind speed had a significant nonlinear effect on the pavement icing time. The effect of the pavement surface temperature on icing conditions was maximal, followed by the effect of the water depth. The effect of the wind speed was moderate. The model with a learning rate of 0.7 and five hidden units had the best prediction effect on pavement icing. The prediction accuracy of the early warning model exceeded 90%, permitting nondestructive and rapid detection of pavement icing based on meteorological information.

Predicting compressive strength of eco-friendly plastic sand paver blocks using gene expression and artificial intelligence programming

Plastic sand paver blocks provide a sustainable alternative by using plastic waste and reducing the need for cement. This innovative approach leads to a more sustainable construction sector by promoting environmental preservation. No model or Equation has been devised that can predict the compressive strength of these blocks. This study utilized gene expression programming (GEP) and multi-expression programming (MEP) to develop empirical models to forecast the compressive strength of plastic sand paver blocks (PSPB) comprised of plastic, sand, and fibre in an effort to advance the field. The database contains 135 results for compressive strength with seven input parameters. The R² values of 0.87 for GEP and 0.91 for MEP for compressive strength reveal a relatively significant relationship between predicted and actual values. MEP outperformed GEP by displaying a higher R² and lower values for statistical evaluations. In addition, a sensitivity analysis was conducted, which revealed that the sand grain size and percentage of fibres play an essential part in compressive strength. It was estimated that they contributed almost 50% of the total. The outcomes of this research have the potential to promote the reuse of PSPB in the building of green environments, hence boosting environmental protection and economic advantage.

Optimized LightGBM Power Fingerprint Identification Based on Entropy Features

The huge amount of power fingerprint data often has the problem of unbalanced categories and is difficult to upload by the limited data transmission rate for IoT communications. An optimized LightGBM power fingerprint extraction and identification method based on entropy features is proposed. First, the voltage and current signals were extracted on the basis of the time-domain features and V-I trajectory features, and a 56-dimensional original feature set containing six entropy features was constructed. Then, the Boruta algorithm with a light gradient boosting machine (LightGBM) as the base learner was used for feature selection of the original feature set, and a 23-dimensional optimal feature subset containing five entropy features was determined. Finally, the Optuna algorithm was used to optimize the hyperparameters of the LightGBM classifier. The classification performance of the power fingerprint identification model on imbalanced datasets was further improved by improving the loss function of the LightGBM model. The experimental results prove that the method can effectively reduce the computational complexity of feature extraction and reduce the amount of power fingerprint data transmission. It meets the recognition accuracy and efficiency requirements of a massive power fingerprint identification system.