Ontology mapping and merging through OntoDNA for learning object reusability

The issue of structural and semantic interoperability among learning objects and other resources on the Internet is increasingly pointing towards Semantic Web technologies in general and ontology in particular as a solution provider. Ontology defines an explicit formal specification of domains to learning objects. However, the effectiveness to interoperate learning objects among various learning object repositories are often reduced due to the use of different ontological schemes to annotate learning objects in each learning object repository. Hence, structural differences and semantic heterogeneity between ontologies need to be resolved in order to generate shared ontology to facilitate learning object reusability. This paper presents OntoDNA, an automated ontology mapping and merging tool. Significance of the study lies in an algorithmic framework for mapping the attributes of concepts/ learning objects and merging these concepts/ learning objects from different ontologies based on the mapped attributes; identification of a suitable threshold value for mapping and merging; an easily scalable unsupervised data mining algorithm for modeling existing concepts and predicting the cluster to which a new concept/ learning object should belong, easy indexing, retrieval and visualization of concepts and learning objects based on the merged ontology.