AI‐ and IoT‐based hybrid model for air quality prediction in a smart city with network assistance

Air pollution is one of the biggest concerns in world but it has not been paid much attention developing countries. It necessary to design models and methods understand air countries reduce rate pollution. This paper proposes an Internet Things (IoT) Artificial Intelligence (AI)-based hybrid model predict Quality Index (AQI) with a practical case study public data sets. The sensor node deployed city collect quality data. Moreover, this connects cloud server for collecting at firebase real-time database through WiFi/5G network embedded raspberry controller. Carbon monoxide (CO) fine particular matter PM2.5 sensors are integrated within monitor AQI regions. A Kalman fis also applied remove unwanted noise from collected node. Models namely Neural Network (ANN), Support Vector Machine (SVM), k-nearest neighbour (k-NN), Convolutional Networks (CNN), Long Short Term Memory (LSTM), CNN-LSTM, ensemble model, proposed that is, CNN-LSTM-Bayesian optimization algorithm (BOA) have utilised AQI. performance evaluation done statistical parameters, such as mean absolute error (MAE), root square (RMSE), coefficient determination (R2), accuracy score on two different sets compared baseline models. CNN-LSTM-BOA better than terms above-mentioned parameters reported more 97 %.This can help provide sufficient time generate warning signals location.