Iot based indoor air quality monitoring and prediction system using machine learning

Air and good air quality are important for humans to carry out their everyday activities. Bad indoor air quality (IAQ) will cause to human such as irritation of the skin, nose, and mouth, headaches, dizziness, and weakness. Current concern found by author on indoor air quality in UMS’s FCI such as problem in monitoring indoor air quality condition that would eventually affect the respiratory system of a student or academic staff, no proper notify system for indoor air quality condition to alert student or academic staff and inadequate statistics on indoor air pollution index to make prediction and keep track the air pollution index level. The objective of this project is to design an IoT Based Indoor Air Quality Monitoring and Prediction System for admin in UMS’s FCI using Node MCU ESP8266 deals with indoor air quality using MQ135 sensor. It then tested by detecting air quality value in Parts per Million (PPM) based on air pollution index (API). For the air quality sensors is focusing on alert message which trigger the message with certain API levels and the reading of API is collected to do prediction and reports on the stages of the API causes. In this project, Exponential Smoothing is chosen as the research element, and it will be used for prediction purpose. Author used rapid prototyping methodology where it is a model consists of phases that able to build, test and reworked as necessary until an acceptable prototype is accomplished in the project. The goal of the proposed system is to develop a web-based indoor air quality monitoring and prediction system with IoT devices that can monitor and do prediction on indoor air pollution index (API) using Machine Learning. Finally, the proposed system will display the monitoring air pollution index (API) data from sensor and used it for prediction data chart for UMS academic staff