TAILIEUCHUNG - Evolving the neural network model for forecasting air pollution time series

Critical loads are typically expressed as deposition loading rates of one or more pollutants in amount per area per year (., kilo- grams per hectare per year (kg/ha/yr)). Critical loads are based on changes to specific biological or chemical indicators such as species composition of a given ecosystem (., grassland) or biotic community (., understory plants or tree-dwelling lichens) or acid neu- tralizing capacity (ANC) in soils, streams or lakes. Because different sensitive receptors (., forest soils, high elevation lakes, species of lichen) or species may have varying sensitivities to air pollutant loads, multiple critical loads can be used to describe a continuum of impacts. | Available online at ELSEVIER Engineering Applications of Artificial Intelligence 17 2004 159-167 7 f7c7l INTELLIGENCE w w w. el sevier. com locate engappai Evolving the neural network model for forecasting air pollution time series Harri Niskaa Teri Hiltunena Ari Karppinenb Juhani Ruuskanena Mikko Kolehmainena a Department of Environmental Sciences University of Kuopio . Box 1627 Kuopio FIN-70211 Finland b Finnish Meteorological Institute Sahiaajankatu 20 E Helsinki FIN-00880 Finland Abstract The modelling of real-world processes such as air quality is generally a difficult task due to both their chaotic and non-linear phenomenon and high dimensional sample space. Despite neural networks NN have been used successfully in this domain the selection of network architecture is still problematic and time consuming task when developing a model for practical situation. This paper presents a study where a parallel genetic algorithm GA is used for selecting the inputs and designing the high-level architecture of a multi-layer perceptron model for forecasting hourly concentrations of nitrogen dioxide at a busy urban traffic station in Helsinki. In addition the tuning of GA s parameters for the problem is considered in experimental way. The results showed that the GA is a capable tool for tackling the practical problems of neural network design. However it was observed that the evaluation of NN models is a computationally expensive process which set limits for the search techniques. 2004 Elsevier Ltd. All rights reserved. Keywords Feed-forward networks Time series forecasting Parallel genetic algorithms Urban air pollution 1. Introduction The forecasting of air quality is one of the topics of air quality research today due to urban air pollution and specifically pollution episodes . high pollutant concentrations causing adverse health effects and even premature deaths among sensitive groups such as asthmatics and elderly people Tiittanen et al. .

• Môi trường
• Streptococcal Toxin
• Streptolysin S
• Anesthesia
• Pain Management
• Techniques and Practice
• Multi Disciplinary
• Therapeutic Advances
• Stereotactic Radiosurgery
• Surgical Treatment
• precancerous lesions
• Streptolysin