Keywords
machine learning methods, feature selection, air-pollution time series analysis and prediction
Start Date
1-7-2008 12:00 AM
Abstract
The study described in this paper, analyzed the urban air pollution principalcauses and identified the best subset of features (meteorological data and air pollutantsconcentrations) for each air pollutant in order to predict its medium-term concentration (inparticular for the PM10). An information theoretic approach to feature selection has beenapplied in order to determine the best subset of features by means of a proper backwardselection algorithm. The final aim of the research is the implementation of a prognostic toolable to reduce the risk for the air pollutants concentrations to be above the alarm thresholdsfixed by the law. The implementation of this tool will be carried out using machine learningmethods based on some of the most wide-spread statistical data driven techniques(Artificial Neural Networks, ANN, and Support Vector Machines, SVM).
An Application of Data Mining to PM10 Level Medium-Term Prediction
The study described in this paper, analyzed the urban air pollution principalcauses and identified the best subset of features (meteorological data and air pollutantsconcentrations) for each air pollutant in order to predict its medium-term concentration (inparticular for the PM10). An information theoretic approach to feature selection has beenapplied in order to determine the best subset of features by means of a proper backwardselection algorithm. The final aim of the research is the implementation of a prognostic toolable to reduce the risk for the air pollutants concentrations to be above the alarm thresholdsfixed by the law. The implementation of this tool will be carried out using machine learningmethods based on some of the most wide-spread statistical data driven techniques(Artificial Neural Networks, ANN, and Support Vector Machines, SVM).
