TY - EJOU AU - Hamza, Manar Ahmed AU - Shaiba, Hadil AU - Marzouk, Radwa AU - Alhindi, Ahmad AU - Asiri, Mashael M. AU - Yaseen, Ishfaq AU - Motwakel, Abdelwahed AU - Rizwanullah, Mohammed TI - Big Data Analytics with Artificial Intelligence Enabled Environmental Air Pollution Monitoring Framework T2 - Computers, Materials \& Continua PY - 2022 VL - 73 IS - 2 SN - 1546-2226 AB - Environmental sustainability is the rate of renewable resource harvesting, pollution control, and non-renewable resource exhaustion. Air pollution is a significant issue confronted by the environment particularly by highly populated countries like India. Due to increased population, the number of vehicles also continues to increase. Each vehicle has its individual emission rate; however, the issue arises when the emission rate crosses the standard value and the quality of the air gets degraded. Owing to the technological advances in machine learning (ML), it is possible to develop prediction approaches to monitor and control pollution using real time data. With the development of the Internet of Things (IoT) and Big Data Analytics (BDA), there is a huge paradigm shift in how environmental data are employed for sustainable cities and societies, especially by applying intelligent algorithms. In this view, this study develops an optimal AI based air quality prediction and classification (OAI-AQPC) model in big data environment. For handling big data from environmental monitoring, Hadoop MapReduce tool is employed. In addition, a predictive model is built using the hybridization of ARIMA and neural network (NN) called ARIMA-NN to predict the pollution level. For improving the performance of the ARIMA-NN algorithm, the parameter tuning process takes place using oppositional swallow swarm optimization (OSSO) algorithm. Finally, Adaptive neuro-fuzzy inference system (ANFIS) classifier is used to classify the air quality into pollutant and non-pollutant. A detailed experimental analysis is performed for highlighting the better prediction performance of the proposed ARIMA-NN method. The obtained outcomes pointed out the enhanced outcomes of the proposed OAI-AQPC technique over the recent state of art techniques. KW - Sustainability; environmental air quality; predictive model; pollution monitoring; statistical models; artificial intelligence DO - 10.32604/cmc.2022.029604