| dc.description.abstract | Air pollution has emerged as a significant concern in the twenty-first century, posing
threats to both the environment and public health. Recent studies have delved extensively
into air pollution and air quality monitoring, yet the field continues to grapple with
unresolved challenges. This study presents a Fog-computing architecture tailored for
indoor air quality monitoring, focusing on multiple pollution parameters.Our Internet
of Things (IoT) system is designed to collect and monitor various pollutants, including
PM2.5, CO2, CO, temperature, and humidity. This is achieved through the integration
of STM32f429I-DISC1, NodeMCU, and various low-cost sensors. The collected data is
then transmitted to ThingsBoard, serving as our fog-computing platform, utilizing the
Raspberry Pi for monitoring tasks on the administrative side. The integration of fog
computing allows for efficient and decentralized data processing, enhancing the system’s
responsiveness. Furthermore, the implementation of deep learning models adds a layer of
sophistication, enabling the creation of a real-time online interface for monitoring. This
interface not only visualizes the current air quality but also provides forecasts, offering
valuable insights for clients. By leveraging this comprehensive approach, our system aims
to address the existing challenges in air quality monitoring and contribute to a healthier
and more informed living environment. | en_US |
