Forecasting Daily Air Quality in Northern Thailand Using Machine Learning Techniques

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Srikamdee:2019:InCIT,

• author = "Supawadee Srikamdee and Janya Onpans",
• title = "Forecasting Daily Air Quality in Northern Thailand Using Machine Learning Techniques",
• booktitle = "2019 4th International Conference on Information Technology (InCIT)",
• year = "2019",
• pages = "259--263",
• abstract = "The air pollution problem becomes more intense in many countries including Thailand. It affects all sectors such as government, industries, and local communities. Accurate forecasts of air quality index would be useful for strategic planning, and pollution warning. Machine learning techniques have been applied to forecast the air quality index (AQI) in many areas. However, most of the existing researches proposed the forecasting model for a specific monitoring station [7-9]. This paper proposes the models to forecast the daily AQIs of the entire Northern Thailand. We collected data during the dry season (January - May) in the year 2018 - 2019, which are the most suffering years. We compared and analyzed the models obtained from three algorithms, i.e., linear regression, neural networks, and genetic programming. Based on the analysis, we recommend two linear equations derived from linear regression and genetic programming as the AQI forecasting models. The results show that our two recommended equations yield the average accuracy of 97.6percent and 78.7percent for forecasting clean and unhealthy air quality situations (i.e., AQI values of 0-50 and AQI values greater than 100), respectively.",
• keywords = "genetic algorithms, genetic programming",
• DOI = "doi:10.1109/INCIT.2019.8912072",
• month = oct,
• notes = "Also known as \cite{8912072}",

}

Genetic Programming entries for Supawadee Srikamdee Janya Onpans

Citations