Abstract
The paper addresses the problem of real-time monitoring and intelligent forecasting for indoors ecological phenomena. The process yields a collection of ecological parameters viewed as distributed time series. Data acquired by means of a wireless network of sensors are modeled by using complex algorithms in view of prediction. An evolutionary searching strategy (Particle Swarm Optimization-PSO) is proposed in order to intelligently find the most accurate prediction model. This strategy is adapted to predictors like PARMA, PARMAX, KARMA and FORWAVER, which are implemented within the monitoring and forecasting system, in order to estimate the future evolution of some ecological parameters. The monitoring system was effectively integrated in an industrial application dealing with automatic irrigation of a small greenhouse. The forecasting simulation results with real data and a comparative assessment of best predictor performances obtained with PSO are presented in the end.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Stefanoiu, D., Culita, J.: Multivariable Prediction of Physical Data. PUB Scientific Bulletin, A Series 72(1), 95–102 (2010)
Stefanoiu, D., Culita, J., Ionescu, F.: FORWAVER – A Wavelet Based Predictor for Non Stationary Signals. In: Industrial Simulation Conference ISC, Lyon, France, pp. 377–381 (2008)
Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, Piscataway – N.J., U.S.A, pp. 1942–1948 (1995)
Dumitrascu, A.: Contributions to industrial computer networks in process control, PhD thesis, “Politehnica” University of Bucharest, 218 pages (2010)
Culita, J., Stefanoiu, D.: FORTIS – An integrated Simulator for Distributed Time Series Forecasting. In: Industrial Simulation Conference ISC, pp. 27–33, Budapest, Hungary, June 7-9 (2010)
Stefanoiu, D., Culita, J., Tudor, F.: Experimental Approaches in Process and Phenomena Identification. AGIR Press, Bucharest (to appear, 2012)
Söderström, T., Stoica, P.: System Identification. Prentice Hall, London (1989)
Culita, J., Stefanoiu, D., Dumitrascu, A.: EcoMonFor – A System for Greenhouses Monitoring and Forecasting. In: Industrial Simulation Conference, Venice, Italy, June 6-8, pp. 262–269 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Culiţă, J., Ştefănoiu, D., Dumitraşcu, A. (2013). Intelligent Forecasting of Indoors Ecological Processes. In: Dumitrache, L. (eds) Advances in Intelligent Control Systems and Computer Science. Advances in Intelligent Systems and Computing, vol 187. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32548-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-32548-9_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32547-2
Online ISBN: 978-3-642-32548-9
eBook Packages: EngineeringEngineering (R0)