Prediction and Analysis of Pollutant using Supervised Machine Learning
Akiladevi R1, Nandhini Devi B2, Nivesh Karthick V, Nivetha P3

1Akiladevi R*, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India.
2Nandhini Devi B, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India.
3Nivesh Karthick V, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India.
4Nivetha P, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India. 

Manuscript received on June 12, 2020. | Revised Manuscript received on June 22, 2020. | Manuscript published on July 30, 2020. | PP: 50-54 | Volume-9 Issue-2, July 2020. | Retrieval Number: A2837059120/2020©BEIESP | DOI: 10.35940/ijrte.A2837.079220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Air is the most essential natural resource for the survival of humans, animals, and plants on the planet. Air is polluted due to the burning of fuels, exhaust gases from factories and industries, and mining operations. Now, air pollution becomes the most dangerous pollution that humanity ever faced. This causes many health effects on humans like respiratory, lung, and skin diseases, which also causes effects on plants, and animals to survive. Hence, air quality prediction and evaluation as becoming an important research area. In this paper, a machine learning-based prediction model is constructed for air quality forecasting. This model will help us to find the major pollutant present in the location along with the causes and sources of that particular pollutant. Air Quality Index value for India is used to predict air quality. The data is collected from various places throughout India so that the collected data is preprocessed to recover from null values, missing values, and duplicate values. The dataset is trained and tested with various machine learning algorithms like Logistic Regression, Naïve Bayes Classification, Random Forest, Support Vector Machine, K Nearest Neighbor, and Decision Tree algorithm in order to find the performance measurement of the above-mentioned algorithms. From this, the prediction model is constructed using the Decision Tree algorithm to predict the air quality, because it provides the best and highest accuracy of 100%. The machine learning-based air quality prediction model helps India meteorological department in predicting the future of air quality, and its status and depends on that they can take action.
Keywords: Prediction, Decision Tree algorithm, Air Quality Index, Air Pollution.