Solving the Oil Spill Problem Using a Combination of CBR and a Summarization of SOM Ensembles
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.
KeywordsCase-Based Reasoning oil spill Self Organizing Memory summarization Radial Basis Function
Unable to display preview. Download preview PDF.
- 2.Aamodt, A.: A Knowledge-Intensive, Integrated Approach to Problem Solving and Sustained Learning, Knowledge Engineering and Image Processing Group. University of Trondheim (1991)Google Scholar
- 4.Pölzlbauer, G.: Survey and Comparison of Quality Measures for Self-Organizing Maps. In: Rauber, J.P. (ed.) Fifth Workshop on Data Analysis (WDA 2004), pp. 67–82. Elfa Academic Press (2004)Google Scholar