A modular IOT sensing platform using hybrid learning ability for air quality prediction

Abstract

The world's underdeveloped countries, who have been affected the worst, are experiencing an increase in climatic issues. Today more than ever, the requirement for precise measurements and predictions of pollutants with low-cost installation is essential. Low-cost air quality sensors are susceptible to inaccurate readings, frequent outages, and erratic operating circumstances. To provide an efficient and adaptable calibration method in such a setting, a cautious approach is required. There are several commercially available monitoring options; a typical system uses particle sensor and gas to keep track of the air quality. These sensor values are compared to established criteria, and alerts are then generated when those thresholds are exceeded. An IoT node with many sensors for a few pollutants, including NH3, NO2, CO, and PM 2.5 as well as air humidity & the ambient temperature, is designed for this purpose. The Internet of Things node is installed inside a research facility to gather indoor air data for research purposes and proof of concept. The suggested system may use GSM/WiFi technology to transmit real-time air quality reports to a web site and web/mobile app, and it can also produce alarms when it notices abnormalities in the air quality. The platform is appropriate for Big Information analysis applications including weather forecasts, and traffic predictions since it can capture sensor readings as fast as one sample per second. Normalized to the average CO, O3, and NO2 sensor readings and association of sensor information are optimal in range. The goal of the study is to advance the field of distributed, low-cost sensing devices for environment intelligence applications.

Keywords

• Calibration
• Measurements
• PM 2.5
• Frequent downtime
• GSM/WiFi
• Urbanization