Three-stage fuzzy rule-based model for earthquake non-engineered building house damage hazard determination

Indonesia is a country with a high earthquake intensity which brings significant impact on a lot of infrastructure damage, including building houses in every incident of a natural earthquake. The assessment model on earthquake damage with a fuzzy system has previously developed. It was aimed to assess the building damage rate after earthquake events, and it has a particular weakness on both the criteria used and the rate of model accuracy. The study was conducted to develop fuzzy inference model to determine the building damage hazard, especially for non-engineered building houses on a particular earthquake event (mitigation). The model was is a threestage fuzzy rule-based model using a thousand data of building houses damaged as result of the impact of earthquake in Bener Meriah district, Aceh Province, Indonesia in the 2013 event, the peak ground acceleration (PGA) data, slope data extracted from 30 meters digital elevation model (DEM) and distance from major fault that was extracted from geological structure map. The main contribution of the research that has been done is to develop the function and fuzzy membership for each determinant variable of building house damage hazard and three stage fuzzy inference process to determine the building house damage hazard as an impact of an earthquake event. Using four hundred data of building houses damage as an impact of the earthquake at the same location, a three-stage fuzzy rule-based model that has been implemented in the study was proven to be able to determine the level of damaged building houses especially for nonengineered building houses better than the previous models with model performance by 93%.