Improving air pollution detection accuracy and Status monitoring based on supervised learning systems and Internet of Things

In recent decades air pollution and its associated health risks are in growing numbers. Detecting air pollution in the environment and alarming the people may accomplish various advantages among health monitoring, telemedicine, and industrial sectors. A novel method of detecting air pollution using supervised learning models and an alert system using IoT is proposed. The main aim of the research is manifold: a) Air pollution data is preprocessed using the feature scaling method, b) The feature selection and feature extraction process done followed by performing a Recurrent Neural Network and c) The predicted data is stored in the cloud server, and it provides the end-users with an alert when the threshold pollution index exceeds. The proposed RNN reports enhanced performance when tested against traditional machine learning models such as Convolutional Neural Networks (CNN), Deep Neural Networks(DNN) and Artificial Neural Networks(ANN) for parameters such as accuracy, specificity, and sensitivity.