Neuro-symbolic System for Forecasting Red Tides
A hybrid neuro-symbolic problem solving model is presented in which the aim is to forecast parameters of a complex and dynamic environment in an unsupervised way. In situations in which the rules that determine a system are unknown, the prediction of the parameter values that determine the characteristic behaviour of the system can be a problematic task. In such a situation, it has been found that a hybrid case-based reasoning (CBR) system can provide a more effective means of performing such predictions than other connectionist or symbolic techniques. The system employs a CBR model to wrap a growing cell structures network, a radial basis function network and a set of Sugeno fuzzy models to provide an accurate prediction. Each of these techniques is used in a different stage of the reasoning cycle of the CBR system to retrieve historical data, to adapt it to the present problem and to review the proposed solution. The results obtained from experiments, in which the system operated in a real environment, are presented.
Unable to display preview. Download preview PDF.
- 1.Tomczak, M., Godfrey, J. S.: Regional Oceanographic: An Introduction. Pergamon, New York, (1994)Google Scholar
- 2.Fernández, E.: Las Mareas Rojas en las Rías Gallegas. Technical Report, Department of Ecology and Animal Biology. University of Vigo, (1998)Google Scholar
- 6.Corchado, J. M., Aiken, J., Rees, N.: Artificial Intelligence Models for Oceanographic Forecasting. Plymouth Marine Laboratory, U.K., (2001)Google Scholar
- 7.Nakhaeizadeh, G.: Learning prediction of time series. A theoretical and empirical comparison of CBR with some other approaches. Proceedings of First European Workshop on Case-Based Reasoning, EWCBR-93, Kaiserslautern, Germany, (1993) 65–76Google Scholar
- 8.Lendaris, G. G., Fraser, A. M.: Visual Fitting and Extrapolation. Weigend, A. S., Fershenfield, N. A. (Eds.). Time Series Prediction, Forecasting the Future and Understanding the Past. Addison Wesley, (1994) 35Google Scholar
- 9.Lekkas, G. P., Arouris, N. M., Viras, L. L.: Case-Based Reasoning in Environmental Monitoring Applications. Artificial Intelligence, 8, (1994) 349–376Google Scholar
- 10.Faltings, B.: Probabilistic Indexing for Case-Based Prediction. Proceedings of Case-Based Reasoning Research and Development, Second International Conference, ICCBR-97, Providence, Rhode Island, USA, (1997), 611–622Google Scholar
- 12.Stottler, R. H.: Case-Based Reasoning for Cost and Sales Prediction. AI Expert, (1994), 25–33Google Scholar
- 13.Weber-Lee, R., Barcia, R. M., Khator, S. K.: Case-based reasoning for cash flow forecasting using fuzzy retrieval. Proceedings of the First International Conference on Case-Based Reasoning, ICCBR-95, Sesimbra, Portugal, (1995), 510–519Google Scholar
- 14.Corchado, J. M., Lees, B., Fyfe, C., Ress, N., Aiken, J.: Neuro-adaptation method for a case based reasoning system. Computing and Information Systems Journal, 5, num. 1, (1998), 15–20Google Scholar
- 15.Pal, S. K., Dilon, T. S., Yeung, D. S.: Soft Computing in Case Based Reasoning. Springer Verlag, London, (2000)Google Scholar
- 18.Jin, Y., Seelen, W. von., Sendho., B.: Extracting Interpretable Fuzzy Rules from RBF Neural Networks. Internal Report IRINI 00-02, Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany, (2000)Google Scholar