Neural Networks with Complex-Valued Neurons for Recurrent and Feedforward Architectures

Abstract

data between private and public organization as well as the different levels of government. Ontologies have been shown in research to enhance the conceptual modeling of geographic data and allow a more effective and efficient way of integrating multiple sources of information. Different aspects such as fuzziness of the features, different levels of accuracy, precision and scale, heterogeneity of data models, generalization of concepts etc. may be resolved using ontologies. It still remains a challenge to use ontologies in order to automatically resolve the diverse geo-integration issues. One area that we are investigating is to integrate data related to shelters and hospitals with appropriate diverse geo-information sources so as to improve emergency management during floods, hurricanes and natural disasters.