Agent-oriented and ontology-driven digital libraries: the IndianaMAS experience

This paper describes IndianaMAS, a multiagent system able to automatically classify and manage images, sketches, and multilingual documents in a cultural heritage domain. The latter has been formalized by means of an ontology, which enables the semantic integration of heterogeneous data from different sources, drives the agent communication with the internal and external environment, and provides an abstract and human-readable interface between the system and the user. IndianaMAS is able to expose to the world the classified data via a digital library. Modularity and reusability are the key engineering principles followed in the system design and implementation. We present the details of the IndianaMAS system and discuss how its architecture can be generalized to create – with the minimal effort – systems addressing similar classification, storage, and management problems, but operating in different domains and driven by different ontologies. The concrete problems we faced and their solutions are described to share our lesson learned and, at the same time, to show the applicability and reusability of our modular approach based on ontologies, agents, and digital libraries.