Classification of Landslide Types by Fuzzy If-then Rules Method

Abstract

Classification procedures of landslide types are presented in order to understand the landslide characters up to now. However, the results obtained from the discussion of type's classification can not be generally applied to the planning of landslide preventions because of the existing fuzziness of classification criteria.
This paper discusses a fuzzy-rule based classification system for landslide types. In the system, a genetic algorithm is introduced to select the effective if-then rules that are consisting the non-symmetric triangle fuzzy subspace of different size. It is shown that the classification of landslide types can be performed by a small number of fuzzy if-then rules through the numerical examples and the proposed method can be also used for the quantitative valuation of empirical information.