SOM Neural Network - a Piece of Intelligence in Disaster Management

Abstract

A collaborative emergency call-taking information system in the Czech Republic processes calls from the European 112 emergency number. Large amounts of various incident records are stored in its databases. The data can be used for mining spatial and temporal anomalies. When such an anomalous situation is detected so that the system could suffer from local or temporal performance decrease, either a person, or an automatic management module could take measures to reconfigure the system traffic and balance its load. In this paper we describe a method for knowledge discovery and visualization with respect to the emergency call taking information system database characteristics. The method is based on the Kohonen Self Organizing Map (SOM) algorithm. Transformations of categorical attributes into numeric values are proposed to prepare training set for successful SOM generation.