Rayleigh model fitting to nonnegative discrete data

0531345 - ÚTIA 2021 RIV US eng C - Conference Paper (international conference)
Petrouš, Matej - Uglickich, Evženie
Rayleigh model fitting to nonnegative discrete data.
Proceedings of 2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES). Piscataway: IEEE, 2020, s. 67-72. ISBN 978-1-7281-1059-2. ISSN 1543-9259.
[IEEE International Conference on Intelligent Engineering Systems 2020 (INES 2020) /24./. Reykjavík (IS), 08.07.2020-10.07.2020]
R&D Projects: GA MŠMT(CZ) 8A17006
Institutional support: RVO:67985556
Keywords : Poisson distribution * multimodal data * Rayleigh distribution * recursive estimation * passenger demand
OECD category: Statistics and probability
http://library.utia.cas.cz/separaty/2020/ZS/uglickich-0531345.pdf

The paper deals with modeling ordinal discrete random variables with a high number of nonnegative realizations. The prediction of the Rayleigh distribution learned on clusters of the explanatory variables is proposed. The proposed solution consists of the clustering and estimation phases based on the knowledge both of the target and explanatory variables, and the prediction phase using only the information from the explanatory variables. The main contributions of the approach are: (i) using the discretized knowledge of clusters of the explanatory variables and (ii) describing nonnegative discrete data by the multimodal Rayleigh distribution. Experiments with a data set from a tram network are provided.
Permanent Link: http://hdl.handle.net/11104/0310088