Forecasting airborne pollen concentration time series with neural and neuro-fuzzy models. Aznarte M., J. L., Benítez Sánchez, J. M., Lugilde, D. N., de Linares Fernández, C., de la Guardia, C. D., & Sánchez, F. A. Expert Systems with Applications, 32(4):1218–1225, May, 2007.
Forecasting airborne pollen concentration time series with neural and neuro-fuzzy models [link]Paper  doi  abstract   bibtex   
Forecasting airborne pollen concentrations is one of the most studied topics in aerobiology, due to its crucial application to allergology. The most used tools for this problem are single lineal regressions and autoregressive models (ARIMA). Notwithstanding, few works have used more sophisticated tools based in Artificial Intelligence, as are neural or neuro-fuzzy models. In this work, we applied some of these models to forecast olive pollen concentrations in the atmosphere of Granada (Spain). We first studied the overall performance of the selected models, then considering the data segmented into intervals (low, medium and high concentration), to test how they behave on each interval. Experimental results show an advantage of the neuro-fuzzy models against classical statistical methods, although there is still room for improvement.1This research has been partially supported by Ministerio de Ciencia y Tecnología under project TIC2003-04650. 1
@article{aznarte_m._forecasting_2007,
	title = {Forecasting airborne pollen concentration time series with neural and neuro-fuzzy models},
	volume = {32},
	copyright = {All rights reserved},
	issn = {0957-4174},
	url = {http://www.sciencedirect.com/science/article/pii/S0957417406000972},
	doi = {10.1016/j.eswa.2006.02.011},
	abstract = {Forecasting airborne pollen concentrations is one of the most studied topics in aerobiology, due to its crucial application to allergology. The most used tools for this problem are single lineal regressions and autoregressive models (ARIMA). Notwithstanding, few works have used more sophisticated tools based in Artificial Intelligence, as are neural or neuro-fuzzy models. In this work, we applied some of these models to forecast olive pollen concentrations in the atmosphere of Granada (Spain). We first studied the overall performance of the selected models, then considering the data segmented into intervals (low, medium and high concentration), to test how they behave on each interval. Experimental results show an advantage of the neuro-fuzzy models against classical statistical methods, although there is still room for improvement.1This research has been partially supported by Ministerio de Ciencia y Tecnología under project TIC2003-04650.
1},
	number = {4},
	urldate = {2015-10-29TZ},
	journal = {Expert Systems with Applications},
	author = {Aznarte M., José Luis and Benítez Sánchez, José Manuel and Lugilde, Diego Nieto and de Linares Fernández, Concepción and de la Guardia, Consuelo Díaz and Sánchez, Francisca Alba},
	month = may,
	year = {2007},
	keywords = {Aerobiology, Airborne pollen, Neuro-fuzzy, Time series, forecasting},
	pages = {1218--1225}
}

Downloads: 0