This study hybridized the ensemble and weight optimization approaches with an artificial neural network (ANN) algorithm to forecast the dynamic modulus (E*) of asphalt concrete. For input selection, this study employed the random forest technique and tested various techniques, including evolutionary, backward, forward, and brute force, to be hybridized with random forest. The evolutionary-random forest technique was used as the best input-selection method. The ρ200, V_beff, binder G* (dynamic shear modulus), and binder φ (phase angle) were selected as the most important variables for developing the ANN models. The findings of this research indicated that the artificial neural network-particle swarm optimisation (ANNPSO) model performed better than the other models. Also, the weight optimization techniques were more efficient than the ensemble techniques to improve the predictive power of ANN to forecast the dynamic modulus of asphalt concrete.

This research addresses the paramount issue of enhancing safety and health conditions in underground mines through the selection of optimal sensor technologies. A novel hybrid MEREC-CoCoSo system is proposed, integrating the strengths of the MEREC (Method for Eliciting Relative Weights) and Combined Compromise Solution (CoCoSo) methods. The study involves a three-stage framework: criteria and sensor discernment, criteria weight determination using MEREC, and sensor prioritization through the MEREC-CoCoSo framework. Fifteen criteria and ten sensors were identified, and a comprehensive analysis, including MEREC-based weight determination, led to the prioritization of “Ease of Installation” as the most critical criterion. Proximity sensors were identified as the optimal choice, followed by biometric sensors, gas sensors, and temperature and humidity sensors. To validate the effectiveness of the proposed MEREC-CoCoSo model, a rigorous comparison was conducted with established methods, including VIKOR, TOPSIS, TODIM, ELECTRE, COPRAS, EDAS, and TRUST. The comparison encompassed relevant metrics such as accuracy, sensitivity, and specificity, providing a comprehensive understanding of the proposed model’s performance in relation to other established methodologies. The outcomes of this comparative analysis consistently demonstrated the superiority of the MEREC-CoCoSo model in accurately selecting the best sensor for ensuring safety and health in underground mining. Notably, the proposed model exhibited higher accuracy rates, increased sensitivity, and improved specificity compared to alternative methods. These results affirm the robustness and reliability of the MEREC-CoCoSo model, establishing it as a state-of-the-art decision-making framework for sensor selection in underground mine safety. The inclusion of these actual results enhances the clarity and credibility of our research, providing valuable insights into the superior performance of the proposed model compared to existing methodologies. The main objective of this research is to develop a robust decision-making framework for optimal sensor selection in underground mines, with a focus on enhancing safety and health conditions. The study seeks to identify and prioritize critical criteria for sensor selection in the context of underground mine safety. The research strives to contribute to the mining industry by offering a structured and effective approach to sensor selection, prioritizing safety and health in underground mining operations.

This work presents the development of new fatigue performance indices for asphalt binders based on viscoelastic continuum damage (VECD) theory and failure energy. Five plant-produced asphalt mixtures were subjected to three different conditioning levels (short-term ageing during production and loose mix ageing for 5 and 12 days at 95°C in the laboratory) and the corresponding binders were extracted and recovered. Direct Tension Cyclic Fatigue (DTCF) tests were performed on the mixtures to characterise the mixture fatigue properties using the simplified viscoelastic continuum damage (S-VECD) analysis approach. Frequency and temperature sweep tests and the Linear Amplitude Sweep (LAS) test using a Dynamic Shear Rheometer (DSR) were conducted on the recovered binders to evaluate the binder rheological and fatigue properties. Three new performance indices are explored from the LAS test: Strain Tolerance (ε_T), Strain Energy Tolerance (Ε_f), and Average Reduction in Integrity to Failure (I^R). These indices were used to track the evolution of binder fatigue properties with ageing. A unique aspect of these indices is that they capture the failure point of the binder during the LAS test and combine the stress and strain histories of the material. Compared with the traditional A and B parameters from the LAS test, the new indices show a consistent decrease in the fatigue properties of the binders with ageing. The newly proposed parameters show improved correlations with mixture fatigue performance index (D^R) from the DTCF test, indicating their potential for evaluation of asphalt mixture fatigue properties. In addition, the new indices developed from this study have been shown to effectively capture the ageing gradient within the pavement structure and can also be used together with the binder rheological indices (e.g. G-R parameter and ΔTc) to evaluate both environmental and fatigue cracking of asphalt pavements at the same time.