Classication of aerosol particles using inductive conformal prediction

Linn Karlsson, Henrik Boström, Paul Zieger
Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, PMLR 128:257-268, 2020.

Abstract

Aerosol particles are small airborne particles suspended in air affecting the climate and human health. Different types of particles come from different sources and impact the environment in different ways, which is why a reliable particle classification is of interest. In this study, inductive conformal prediction is applied to a dataset of laboratory-generated aerosol particles, consisting of ten particle subclasses that can be grouped into four parent classes for classification. The performance of the inductive conformal predictor (ICP) is evaluated on particle subclasses that were not included in training or calibration. The ICP appears to give accurate predictions in some cases, namely if the unknown particle is similar to the known ones in the parent class. The precision of the underlying model is not high enough to reject all unknown particles for any subclass at the chosen significance levels, but the ICP manages to reject them at a higher rate if they are sufficiently different from the training and calibration samples. Overall, the performance is not straightforward to evaluate and it seems to depend on the heterogeneity and size of the classes of particles. Further investigations using a simpler data and model set-up would be beneficial, and data and sampling standardisation should be considered more carefully if the model is to be applied to field measurements.

Cite this Paper

BibTeX
@InProceedings{pmlr-v128-karlsson20a, title = {Classication of aerosol particles using inductive conformal prediction}, author = {Karlsson, Linn and Bostr\"{o}m, Henrik and Zieger, Paul}, booktitle = {Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications}, pages = {257--268}, year = {2020}, editor = {Gammerman, Alexander and Vovk, Vladimir and Luo, Zhiyuan and Smirnov, Evgueni and Cherubin, Giovanni}, volume = {128}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v128/karlsson20a/karlsson20a.pdf}, url = {https://proceedings.mlr.press/v128/karlsson20a.html}, abstract = {Aerosol particles are small airborne particles suspended in air affecting the climate and human health. Different types of particles come from different sources and impact the environment in different ways, which is why a reliable particle classification is of interest. In this study, inductive conformal prediction is applied to a dataset of laboratory-generated aerosol particles, consisting of ten particle subclasses that can be grouped into four parent classes for classification. The performance of the inductive conformal predictor (ICP) is evaluated on particle subclasses that were not included in training or calibration. The ICP appears to give accurate predictions in some cases, namely if the unknown particle is similar to the known ones in the parent class. The precision of the underlying model is not high enough to reject all unknown particles for any subclass at the chosen significance levels, but the ICP manages to reject them at a higher rate if they are sufficiently different from the training and calibration samples. Overall, the performance is not straightforward to evaluate and it seems to depend on the heterogeneity and size of the classes of particles. Further investigations using a simpler data and model set-up would be beneficial, and data and sampling standardisation should be considered more carefully if the model is to be applied to field measurements.} }
Endnote
%0 Conference Paper %T Classication of aerosol particles using inductive conformal prediction %A Linn Karlsson %A Henrik Boström %A Paul Zieger %B Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2020 %E Alexander Gammerman %E Vladimir Vovk %E Zhiyuan Luo %E Evgueni Smirnov %E Giovanni Cherubin %F pmlr-v128-karlsson20a %I PMLR %P 257--268 %U https://proceedings.mlr.press/v128/karlsson20a.html %V 128 %X Aerosol particles are small airborne particles suspended in air affecting the climate and human health. Different types of particles come from different sources and impact the environment in different ways, which is why a reliable particle classification is of interest. In this study, inductive conformal prediction is applied to a dataset of laboratory-generated aerosol particles, consisting of ten particle subclasses that can be grouped into four parent classes for classification. The performance of the inductive conformal predictor (ICP) is evaluated on particle subclasses that were not included in training or calibration. The ICP appears to give accurate predictions in some cases, namely if the unknown particle is similar to the known ones in the parent class. The precision of the underlying model is not high enough to reject all unknown particles for any subclass at the chosen significance levels, but the ICP manages to reject them at a higher rate if they are sufficiently different from the training and calibration samples. Overall, the performance is not straightforward to evaluate and it seems to depend on the heterogeneity and size of the classes of particles. Further investigations using a simpler data and model set-up would be beneficial, and data and sampling standardisation should be considered more carefully if the model is to be applied to field measurements.
APA
Karlsson, L., Boström, H. & Zieger, P.. (2020). Classication of aerosol particles using inductive conformal prediction. Proceedings of the Ninth Symposium on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 128:257-268 Available from https://proceedings.mlr.press/v128/karlsson20a.html.

Related Material