Search

Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm. This paper focuses on the exploitation of a genetic algorithm following a wrapping iterative approach used to extract an optimal feature subset of a large database containing pollutant concentration measurements. The feature subset is fed to a machine learning algorithm in order to predict the daily maximum concentration of two air pollutants. The encoding problem of the complexity of representation of the features in the genomes is tackled. Results of the experimentation on a specific dataset of an air quality forecasting problem are presented, as well as some proposed alterations on the standard genetic algorithm that guided the process to a mature convergence and gave good solutions for this problem. A modified version of the initial algorithm is presented as well, implemented for the purpose of being compared on an equal basis with other feature selection methods. Two such methods of the filtering type, CFS and ReliefF, are being compared with. The comparative results suggest that the wrapping type technique described in this paper is significantly better in the specific problem at hand, but this conclusion is limited to the machine learning algorithm that the technique uses at its core in the feature selection phase. [ABSTRACT FROM AUTHOR]

Management of urban atmospheric pollution necessitates advanced modeling and information processing techniques. The design of the prototype system DNEMO, which is based on a distributed adaptive problem-solving approach is the focus of the research reported in this paper. Issues covered in the paper relate to the distributed nature of this environmental problem, handling noise and uncertainty in monitoring data, achieving graceful degradation of performance and system robustness, and adaptation of system performance to long-term evolution of the monitored phenomena. The research reported can be applicable to a broad class of environmental monitoring applications, since the problems addressed are common to many environmental problems. [ABSTRACT FROM AUTHOR]