Article: Deep learning technologies for the assessment of air pollution level systems in smart cities Journal: International Journal of System of Systems Engineering (IJSSE) 2023 Vol.13 No.4 pp.419 - 435 Abstract: In order to prevent pollution and make sure that air pollution control systems are working as intended, forecasting can provide reliable data on pollution prediction. When analysing the ecosystem in smart cities, it is imperative to update the framework in order to improve daily life. When other factors, such as humidity, temperature, the direction and speed of the wind, as well as precipitation and snowfall, are taken into account, it is much more challenging to comprehend how concentrations of air pollution change over time. In these conditions, it is more difficult to comprehend fluctuations in air pollution concentrations. This paper presents a number of different deep-learning models that, by drawing on a wide variety of characteristics, can assist in the forecasting of environmental air pollution. This paper examines the limitations of the methodologies that are currently being used and provides recommendations for future researchers who are interested in advancing prediction-based research in the field of air pollution. Inderscience Publishers - linking academia, business and industry through research

Title: Deep learning technologies for the assessment of air pollution level systems in smart cities

Authors: S. Silvia Priscila; A. Jayanthiladevi

Addresses: Institute of Computer Science and Information Science, Srinivas University, Karnataka, 574146, India; Department of Computer Science, Bharath Institute of Higher Education and Research (BIHER), Tamil Nadu, 600126, India ' Institute of Computer Science and Information Science, Srinivas University, Karnataka, 574146, India

Abstract: In order to prevent pollution and make sure that air pollution control systems are working as intended, forecasting can provide reliable data on pollution prediction. When analysing the ecosystem in smart cities, it is imperative to update the framework in order to improve daily life. When other factors, such as humidity, temperature, the direction and speed of the wind, as well as precipitation and snowfall, are taken into account, it is much more challenging to comprehend how concentrations of air pollution change over time. In these conditions, it is more difficult to comprehend fluctuations in air pollution concentrations. This paper presents a number of different deep-learning models that, by drawing on a wide variety of characteristics, can assist in the forecasting of environmental air pollution. This paper examines the limitations of the methodologies that are currently being used and provides recommendations for future researchers who are interested in advancing prediction-based research in the field of air pollution.

Keywords: pollution; prediction; deep learning; ecosystems; PM2.5; SO2; CO; NO2; LSTM; long short-term memory unit; environment; community; pollutant; air quality; patients; government; PM 10; ANFIS; CO2; geostatistics.

DOI: 10.1504/IJSSE.2023.134433

International Journal of System of Systems Engineering, 2023 Vol.13 No.4, pp.419 - 435

Received: 13 Oct 2022
Accepted: 30 Nov 2022
Published online: 23 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Deep learning technologies for the assessment of air pollution level systems in smart cities

Keep up-to-date