Development of Sensors and IoT Systems for Environmental Monitoring in Congolese Mines

Environmental monitoring in Congolese mines is crucial for ensuring worker safety and minimising ecological impact. A hybrid approach combining machine learning algorithms with traditional sensor technologies was employed to design and test these monitoring systems. The prototype sensors demonstrated a precision rate of at least 95% in air quality measurement, which is significantly higher than the industry standard for such applications. The integration of IoT into mine operations has shown promising results, reducing operational risks by providing real-time environmental data. Further research should focus on expanding sensor coverage and integrating predictive maintenance systems to enhance system reliability. Environmental Monitoring, Sensors, IoT Systems, Congolese Mines, Machine Learning The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.