An Intelligent Bayesian Optimization with Stacked BiLSTM Model for Air Quality Index Prediction

Rapid urbanization and industrialization can quickly deteriorate surrounding quality of the air, particularly in evolving countries. Pollution in air carry out a major problem to public health and damage the atmosphere. Previous analysis is utilized Machine Learning (ML) and arithmetic modeling for classifying and forecasting pollution in air. But these techniques undergo the difficulty of air pollution databases giving an outcome in the absence of effectual classification and prediction of air pollutions. The research developed a Bayesian Optimization with Stacked Deep Learning-based Air Quality Index Prediction (BOSDL-AQIP) approach. The goal of the BOSDL-AQIP approach lies in the effectual identification and classification of Air Quality (AQ) into multiple class labels. To attain this, the presented BOSDL-AQIP technique employs min-max normalization for data scaling purposes. Next, the BOSDL-AQIP system utilizes Stacked Bidirectional Long Short-Term Memory (SBiLSTM) technique for prediction process. Moreover, BO technique was utilized for adjusting the hyperparameter values of the SBiLSTM technique and thereby improve the predictive outputs. The simulation outcome of the BOSDL-AQIP algorithm was tested on air quality dataset and the outputs implied the enhanced efficacy of the BOSDL-AQIP technique over other approaches.