Publication

Abstract : The continuous advancement of modern society and rapid urbanization has given rise to air pollution concerns, leading to increased respiratory problems among individuals. Therefore, it is necessary to design a system through which the pollutants can be prognosticated. Nevertheless, air quality forecasting is a strenuous process because air quality depends on several factors, such as weather, vehicles, etc. In order to tackle the difficult problems related to prediction and classification, machine learning (ML) and deep learning (DL) is employed. For these performances, a novel Red Deer Algorithm Optimized Gated Recurrent Neural Network (RDA-GRNN) algorithm was proposed for air quality prediction. The effectiveness of the proposed algorithm was evaluated by using the Air Quality Index (AQI) data of India between 2015 and 2020, dataset (city-day), and its performance was compared with existing algorithms. It was found that the predictive performance of the proposed algorithm in terms of R2 was 0.870 and 0.962, and MAPE was 0.136 and 0.241 for training and testing datasets compared to the existing state-of-the-art algorithms.