Integrated smart dust monitoring and prediction system for surface mine sites using IoT and machine learning techniques.

The mining industry confronts significant challenges in mitigating airborne particulate matter (PM) pollution, necessitating innovative approaches for effective monitoring and prediction. This research focuses on the design and development of an Internet of Things (IoT)-based real-time monitoring system tailored for PM pollutants in surface mines, specifically PM 1.0, PM 2.5, PM 4.0, and PM 10.0. The novelty of this work lies in the integration of IoT technology for real-time measurement and the application of machine learning (ML) techniques for accurate prediction based on recorded dust pollutants data. The study's findings indicate that PM 1.0 pollutants exhibited the highest concentration in the atmosphere of the ball clay surface mine sites, with the stockyard site registering the maximum levels of PM pollutants (28.45 µg/m3, 27.89 µg/m3, 26.17 µg/m3, and 27.24 µg/m3, respectively) due to the dry nature of clay materials. Additionally, the research establishes four ML models-Decision Tree (DT), Gradient Boosting Regression (GBR), Random Forest (RF), and Linear Regression (LR)-for predicting PM pollutant concentrations. Notably, Random Forest demonstrates superior performance with the lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) at 1.079 and 1.497, respectively. This comprehensive solution, combining IoT-based monitoring and ML-based prediction, contributes to sustainable mining practices, safeguarding worker well-being, and preserving the environment.

Structural equation modelling of work related musculoskeletal disorders among dumper operators.

The aim of this study is to investigate the impact of personal factors, habitual factors, and work-related factors on work-related musculoskeletal disorders (WRMSDs) among dumper operators. In total, 248 dumper operators working in an iron ore mine were considered for this study. A questionnaire was developed and administered to collect dumper operators' personal, habitual, and work-related data. The reliability of the questionnaire was cross-checked by Cronbach alpha and the test-retest method. The values of Cronbach alpha for all latent variables were above 0.7, and the correlation coefficient of the questionnaire items at Time 1 and Time 2 was above 0.82. After verifying the validity (i.e., convergent and divergent) of the questionnaire data, the relationship between the factors under consideration was examined by structural equation modeling (SEM). The SEM demonstrated a moderate fit, with [Formula: see text] value of 1.386, comparative fit index (CFI) of 0.86, goodness-of-fit index (GFI) of 0.72, adjusted goodness-of-fit index (AGFI) of 0.69, Tucker-Lewis Index (TLI) of 0.83, normed fit index (NFI) of 0.71 and root mean square error of approximation (RMSEA) of 0.051. The SEM analysis revealed a positive relationship between WRMSDs and personal factors (with path coefficient = 0.313 and p < 0.05) as well as work-related factors (with path coefficient = 0.296 and p < 0.05). However, the relationship between WRMSDs and habitual factors was not statistically significant (with path coefficient = 0.142 and p > 0.05). Overall, this study provides valuable insights into the factors that influence the prevalence of WRMSDs among dumper operators. The findings highlight the significance of personal and work-related factors by which one can make a positive decision to prevent and reduce the incidence of WRMSDs among dumper operators.

Quantitative Analysis of Solar Photovoltaic Panel Performance with Size-Varied Dust Pollutants Deposition Using Different Machine Learning Approaches.

In this paper, the impact of dust deposition on solar photovoltaic (PV) panels was examined, using experimental and machine learning (ML) approaches for different sizes of dust pollutants. The experimental investigation was performed using five different sizes of dust pollutants with a deposition density of 33.48 g/m2 on the panel surface. It has been noted that the zero-resistance current of the PV panel is reduced by up to 49.01% due to the presence of small-size particles and 15.68% for large-size (ranging from 600 µ to 850 µ). In addition, a significant reduction of nearly 40% in sunlight penetration into the PV panel surface was observed due to the deposition of a smaller size of dust pollutants compared to the larger size. Subsequently, different ML regression models, namely support vector machine (SVMR), multiple linear (MLR) and Gaussian (GR), were considered and compared to predict the output power of solar PV panels under the varied size of dust deposition. The outcomes of the ML approach showed that the SVMR algorithms provide optimal performance with MAE, MSE and R2 values of 0.1589, 0.0328 and 0.9919, respectively; while GR had the worst performance. The predicted output power values are in good agreement with the experimental values, showing that the proposed ML approaches are suitable for predicting the output power in any harsh and dusty environment.