Investigating pollen data with the aid of fuzzy methods

Authors:
Nikolaos Mitrakis;Kostas Karatzas;Siegfried Jaeger
Affiliations:
Department of Mechanical Engineering, Aristotle University, Thessaloniki, Greece;Department of Mechanical Engineering, Aristotle University, Thessaloniki, Greece;Medizinische Universität Wien, Universitätsklinik für Hals, Wien, Austria
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Year:
2010

Citing 2
Cited 0

Supervised fuzzy clustering for the identification of fuzzy classifiers

Pattern Recognition Letters
Forecasting airborne pollen concentration time series with neural and neuro-fuzzy models

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The analysis of pollen data coming from a large number of monitoring sites and related to various pollen types is a multivariate knowledge discovery problem. The relationships between the variables and the forecasting of their behaviour may successfully be performed with the aid of computational intelligence methods. The present paper deals with data coming from 25 monitoring sites in Austria, including time series of pollen counts for 10 pollen types. Fuzzy rules and fuzzy clustering were employed, as well as appropriate graphical representation, for the analysis of the behaviour of the pollen types. Results indicate the ability to extract knowledge and to forecast pollen count levels that directly affect the quality of life of allergic people.