Solving the Oil Spill Problem Using a Combination of CBR and a Summarization of SOM Ensembles
Fecha de publicación
Springer Science + Business Media
International Symposium on Distributed Computing and Artificial Intelligence 2008 (DCAI 2008) Advances in Soft Computing. Advances in Soft Computing. Volumen 50, pp. 658-662.
In this paper, a forecasting system is presented. It predicts the presence of oil slicks in a certain area of the open sea after an oil spill using Case-Based Reasoning methodology. CBR systems are designed to generate solutions to a certain problem by analysing historical data where previous solutions are stored. The system explained includes a novel network for data classification and retrieval. Such network works as a summarization algorithm for the results of an ensemble of Self-Organizing Maps. This algorithm, called Weighted Voting Superposition (WeVoS), is aimed to achieve the lowest topographic error in the map. The WeVoS-CBR system has been able to precisely predict the presence of oil slicks in the open sea areas of the north west of the Galician coast.
978-3-540-85862-1 (Print) / 978-3-540-85863-8 (Online)
1615-3871 (Print) / 1860-0794 (Online)
- BISITE. Congresos