Urban ambient air quality data mining and visualisation

• Main Authors: Lyu, Linjie, Kong, Jingyi, Peng, Yingyi
• Format: Conference or Workshop Item
• Published: IEEE 2022
• Online Access: http://psasir.upm.edu.my/id/eprint/37623/; https://ieeexplore.ieee.org/document/10102166

Air quality data analysis is based on real-time data collection, and how to use them for prediction after obtaining a large amount of data is an important problem to be solved in air quality prediction. The aim of this paper is to study urban ambient air quality data mining and visualisation. The concepts related to information visualisation, data mining and exponential smoothing methods are described. The architecture of the data mining system for urban ambient air quality in this paper is proposed. Taking city M as an example, an ambient air quality data warehouse is established and an exponential smoothing technique is used to design a prediction model. The exponential smoothing method was used to predict the medium and long-term ambient air quality in the ambient air quality data mining system. The experiments showed that the prediction model had good prediction accuracy.