Achim J. Lilienthal, Sahar Asadi and Matteo Reggente
Estimating Predictive Variance for Statistical Gas Distribution Modelling
American Institute of Physics, Proceedings of the 13th International Symposium on Olfaction and Electronic Nose (ISOEN), 2009, pp. 65-68
Abstract: Recent publications in statistical gas distribution modelling have proposed algorithms that model mean and variance of a distribution. This paper argues that estimating the predictive concentration variance entails not only a gradual improvement but is rather a significant step to advance the field. This is, first, since the models much better fit the particular structure of gas distributions, which exhibit strong fluctuations with considerable spatial variations as a result of the intermittent character of gas dispersal. Second, because estimating the predictive variance allows to evaluate the model quality in terms of the data likelihood. This offers a solution to the problem of ground truth evaluation, which has always been a critical issue for gas distribution modelling. It also enables solid comparisons of different modelling approaches, and provides the means to learn meta parameters of the model, to determine when the model should be updated or re-initialised, or to suggest new measurement locations based on the current model. We also point out directions of related ongoing or potential future research work.
Keywords: Gas distribution modelling; gas sensing; mobile robot olfaction; density estimation; model evaluation.
Download:
Paper: [PDF (0.3MB)]
Presentation: [PDF (12.7MB)]
Bibtex:
@INPROCEEDINGS{Lilienthal_etal:ISOEN:2009,
  author = {Lilienthal, Achim J. and Asadi, Sahar and Reggente, Matteo},
  title = {Estimating Predictive Variance for Statistical Gas Distribution Modelling},
  booktitle = {AIP Conference Proceedings Volume 1137: Olfaction and Electronic Nose - Proceedings of the 13th International Symposium on Olfaction and Electronic Nose (ISOEN)},
  year = {2009},
  pages = {65--68}
}