Back to Search
Start Over
Comparison of hybrid machine learning model for the analysis of black carbon in air around the major coal mines of India.
- Source :
- Neural Computing & Applications; Feb2023, Vol. 35 Issue 4, p3449-3468, 20p
- Publication Year :
- 2023
-
Abstract
- Air is the basis for the existence of life on Earth; but in the present age of modernization the degrading quality of air year by year, due to the growth of Industrialization, urbanization, automobiles, coal-fired thermal power plants, and various other factories is the matter of real concern. To predict the future growth of air pollutants numerous prediction models have been developed by researchers. Time-series ARIMA model although quite useful for forecasting but fails to handle non-stationary problems. Among all the existing forecasting models, wavelets along with the Machine learning models have proved to be very successful and have been widely used in various fields like mathematical modeling, signal recognition, image recognition, classification, function approximation, data processing, filtering, clustering, compression, robotics, and decision making. It is also used in the field of mathematical forecasting for developing efficient prediction models. This paper aims to develop a wavelet-ANFIS conjugation model and a wavelet-ARIMA coupled model along with the time-series ARIMA model for the prediction of black carbon concentration over the Raniganj, Jharia, and Bokaro coal mines of India, by considering a long term data obtained by NASA (http://nasa.gov/) and compare the results obtained by these models for determining the best prediction model. The validity of the results is tested with the help of error measures like RMSE, MSE, MAPE, MAE, and relative error. Results over the three sample sites conclude that the Wavelet-ANFIS conjugation approach outperforms the wavelet-ARIMA coupled approach and the simple time-series ARIMA model. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 35
- Issue :
- 4
- Database :
- Complementary Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 161516476
- Full Text :
- https://doi.org/10.1007/s00521-022-07909-8