AIR POLLUTION PREDICTION USING MACHINE LEARNING

AUTHOR(S)

Sneha A R, Premkumar M, Sanjuvikashini A P, Soniga N, Swathika T

DOI: https://doi.org/10.46647/ijetms.2023.v07i02.091

ABSTRACT
The fact that environment tracking is focused largely on the fundamental rights of people, lifestyles, and health makes it so important. As a result, this device tracks the quality of the air using excellent sensor nodes within that check for CO2, NOx, UV light, temperature, and humidity. The gad get is able to categorize automatically if a certain geographic area is going above the established gas emission restrictions thanks to the statistics assessment using device mastering algorithms. In order to choose the most contaminated sectors, the DB SCAN with LR, SVM, and NB set of rules delivered a noteworthy category overall performance. Monitoring air quality is a crucial concern in many commercial and physical areas of the world. In areas with serious difficulties with air pollution, Air Quality Operational Centers (AQOCs) are established specifically for this purpose. The AQOCs are operational units responsible for managing tracking networks, analyzing the gathered data, and eventually disseminating online assessments of air pollutants and their short- and long-term evolution. Up until recently, modelling of air pollution events has been focused mostly on dispersion models, which approximate the complex physicochemical processes at play. Although the intricacy and complexity of these models have increased over time, their application in real-time atmospheric pollution tracking appears to no longer be acceptable in terms of performance, input data requirements, and compliance with the problem's time limitations.

Page No: 830 - 835

References:

1. Environmental research, vol. 158, 2017, pp. 105–117. Air quality evaluation and air pollutant concentration prediction: a unique air quality monitoring and early warning system Yang, Z., and Wang, J.
2. Vol. 8, No. 2, page 99, ISPRS International Journal of Geoformation, 2019. An application to Tehran's capital city of an unique technology for improving air pollution prediction based on machine learning methodologies. Along with M. R. Delavar, A. Gholami, and G. R. Shiran, the authors are Y. Rashidi, G. R. Nakhaeizadeh, K. Fedra, and S. HatefiAfshar.
3. IoT-based Air Pollution Monitoring and Forecasting System, 2015 International Conference on Computer and Computational Sciences, C. Xiao Jun, L. Xian Peng, and X. Peng (ICCCS). 2015, IEEE, pp. 257–260
4. T. L. Youd, C. M. Hansen, and S. F. Bartlett claim that changes have been made to multi linear regression equations for forecasting lateral spread displacement in Journal of Geotechnical and Geo environmental Engineering, vol. 128, no. 12, 2002, pp. 1007-1017.
5. In 1992, a study titled "Multilayer Perceptron, Fuzzy Sets, Classification" was published by S. K. Pal and S. Mitra.

How to Cite This Article:
Sneha A R, Premkumar M, Sanjuvikashini A P, Soniga N, Swathika T . AIR POLLUTION PREDICTION USING MACHINE LEARNING . ijetms;7(2):830-835. DOI: 10.46647/ijetms.2023.v07i02.091