A Machine Learning Model for Air Quality Prediction for Smart Cities

Usha, M.; Elangovan, K.; Dobhal, Himanshu; Valliappa, Chocko; Shrestha, Sindhu; Kedam, Giriprasad

doi:10.1109/wispnet45539.2019.9032734

Cited by 65 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From the outcomes, the authors presumed that the K-Nearest Neighbor algorithm predicts the air quality index better. In [13], the accuracy obtained in this experiment was 91.62%. A machine learning approach for forecasting air quality indexes for intelligent cities is proposed in this research effort.…”

Section: Discussionmentioning

confidence: 63%

Predicting Air Pollution Level in Particular Area Using KNN by Comparing Accuracy with SVM

Reddy

Parvathy

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

To predict the air pollution level in a particular region area using a K-Nearest Neighbor algorithm compared with the Support Vector Machine algorithm, The Novel K-Nearest Neighbor Algorithm and the Support Vector Machine Algorithm are two groupings. The algorithms were implemented and evaluated on a dataset of 32516 records. Various air pollution was identified through a programming experiment with N = 5 iterations for each method. G power is set at 80%. The confidence interval is 95%, and the threshold value is 0.05%. The G-power test is around 80% accurate. The K-Nearest Neighbor algorithm (97.44%) has better accuracy when compared with the Support Vector Machine (70.32%). The K-Nearest Neighbor algorithm has the highest accuracy compared to the Support Vector Machine algorithm. In the prediction of air pollution, K-Nearest Neighbor has better performance when compared to the Support Vector Machine Algorithm.

show abstract

Section: Discussionmentioning

confidence: 63%

Predicting Air Pollution Level in Particular Area Using KNN by Comparing Accuracy with SVM

Reddy

Parvathy

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

show abstract

“…This paper investigated strategies for consolidating classifiers along with specific recently publicly released boosting calculations to anticipate the not-so-distant future's air quality expectation. In [16], the accuracy obtained in this experiment is 91.62%. In this study, a machine learning approach for forecasting air quality indexes for smart cities is proposed.…”

Section: Discussionmentioning

confidence: 67%

Prediction of Air Pollution Level in Particular Region Area Using Logistic Regression and Naive Bayes

Reddy

Parvathy

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

To predict the air pollution level in a particular region area using an Innovative Logistic Regression algorithm compared with the Naive Bayes algorithm. The Logistic Regression Algorithm and the Naive Bayes Algorithm are two sets of algorithms. The algorithms were implemented and evaluated on a dataset of 32516 records. Various air pollution was identified through a programming experiment with N=5 iterations for each method. The threshold value is 0.05%, and the Confidence Interval is 95%. The G-power test used is about 80%. The innovative Logistic Regression algorithm (98.26%) has better accuracy when compared with Naive Bayes(97.32%). Logistic Regression has the highest accuracy in comparison to the Naive Bayes algorithm. Significance value for accuracy is 0.056(p>0.05), Precision 0.02(p<0.05) and recall 0.01(p<0.05) based on 2-tail analysis. Logistic Regression outperforms the Naive Bayes Algorithm in the prediction of air pollution.

show abstract

“…Madan et al [71] mentioned that a variety of machine learning methods, including linear regression, decision tree, random forest, neural network, and support vector machine, have been used to predict quality of air. The air quality prediction model developed by Mahalingam et al [72] using the neural network algorithm and support vector machine proved effective. Pasupuleti et al [73] found that the random forest method is more accurate in comparison to regression and decision tree for predicting pollutants (r CO = 0.79, r O 3 = 0.79, r NO 2 = 0.70, r PM 2.5 = 0.86, and r PM 10 = 0.79).…”

Section: Figurementioning

confidence: 99%

Machine Learning for Determining Interactions between Air Pollutants and Environmental Parameters in Three Cities of Iran

et al. 2022

View full text Add to dashboard Cite

Air pollution, as one of the most significant environmental challenges, has adversely affected the global economy, human health, and ecosystems. Consequently, comprehensive research is being conducted to provide solutions to air quality management. Recently, it has been demonstrated that environmental parameters, including temperature, relative humidity, wind speed, air pressure, and vegetation, interact with air pollutants, such as particulate matter (PM), NO2, SO2, O3, and CO, contributing to frameworks for forecasting air quality. The objective of the present study is to explore these interactions in three Iranian metropolises of Tehran, Tabriz, and Shiraz from 2015 to 2019 and develop a machine learning-based model to predict daily air pollution. Three distinct assessment criteria were used to assess the proposed XGBoost model, including R squared (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Preliminary results showed that although air pollutants were significantly associated with meteorological factors and vegetation, the formulated model had low accuracy in predicting (R2PM2.5 = 0.36, R2PM10 = 0.27, R2NO2 = 0.46, R2SO2 = 0.41, R2O3 = 0.52, and R2CO = 0.38). Accordingly, future studies should consider more variables, including emission data from manufactories and traffic, as well as sunlight and wind direction. It is also suggested that strategies be applied to minimize the lack of observational data by considering second-and third-order interactions between parameters, increasing the number of simultaneous air pollution and meteorological monitoring stations, as well as hybrid machine learning models based on proximal and satellite data.

show abstract

A Machine Learning Model for Air Quality Prediction for Smart Cities

Cited by 65 publications

References 11 publications

Predicting Air Pollution Level in Particular Area Using KNN by Comparing Accuracy with SVM

Predicting Air Pollution Level in Particular Area Using KNN by Comparing Accuracy with SVM

Prediction of Air Pollution Level in Particular Region Area Using Logistic Regression and Naive Bayes

Machine Learning for Determining Interactions between Air Pollutants and Environmental Parameters in Three Cities of Iran

Contact Info

Product

Resources

About