Ari D.Alagoz B.B.2024-08-042024-08-0420219781665428705https://doi.org/10.1109/ICIT52682.2021.9491122https://hdl.handle.net/11616/92218Umniah and UWallet2021 International Conference on Information Technology, ICIT 2021 -- 14 July 2021 through 15 July 2021 -- 170653An important part of air pollution control is the pollution monitoring. Since industrial spectrometers are expensive equipment, the number of observation points to monitor air pollution over an urban area can be limited. The low-cost multi-sensors network can spread over areas and form a wide-area electronic nose to estimate pollutant concentration distributions. However, the collected multisensor data should be analyzed to correctly estimate pollutant concentrations. This study demonstrates implementation of genetic programming (GP) to obtain prediction models that can estimate CO and NO2 concentrations from multisensor electronic nose data. For this purpose, to function as an electronic nose, a regression model from a training data set is obtained by using a tree-based GP algorithm. In order to improve performance of the GP based prediction models, data normalization is performed and prediction performance enhancements are demonstrated via statistical performance analyses on a test data set. © 2021 IEEE.eninfo:eu-repo/semantics/closedAccessair qualityconcentration predictionelectronic noseGenetic programmingsensor data calibrationConference Object16817210.1109/ICIT52682.2021.94911222-s2.0-85112165495N/A