<![CDATA[This study presents the development and implementation of an intelligent air quality monitoring system for waste treatment facilities utilizing Artificial Neural Networks (ANN) and eco-enzyme technology to address hazardous gas emissions including hydrogen sulfide (H₂S), ammonia (NH₃), and methane (CH₄) in landfill areas. The system integrates MQ-series gas sensors (MQ-136, MQ-137, and MQ-4) with an ESP32 microcontroller for real-time data acquisition, achieving exceptional performance with prediction accuracy exceeding 90% and a final Mean Squared Error of 0.006 after 2000 training epochs. Correlation analysis revealed strong negative relationships between gaseous pollutants and the Quality Index (r = -0.96 to -0.97, p < 0.001), confirming these gases as reliable predictors of air quality degradation. Cloud integration through Google Firebase and Blynk platforms enables remote monitoring and real-time data accessibility, while the implementation of eco-enzyme technology demonstrated significant effectiveness in reducing harmful gas emissions and mitigating unpleasant odors, with measurable improvements observed during the observation period. The system's ability to provide accurate predictions, automated control mechanisms, and comprehensive real-time monitoring positions it as a valuable tool for pollution mitigation efforts in landfill environments, contributing positively to public health outcomes and environmental sustainability.]]>
Copyrights © 2026
