RDF-based Model Research Articles

Modelling with AAS and RDF in Industry 4.0

Industry 4.0 has proposed the Asset Administration Shell (AAS) model for digital twins. This model should help to solve interoperability issues, a topic that is also addressed by the Semantic Web and its Resource Description Framework (RDF). AAS and RDF-based models have their own strengths. AAS models are easier to integrate with operational technologies in a production environment, whereas RDF-based models offer more semantic expressiveness and advanced querying. In the Horizon MAS4AI project we found that both modelling paradigms can complement each other to develop agentbased digital twins for modular production environments. In this work we propose two different approaches to bridge both modelling paradigms. First we define a set of mapping rules to generate an AAS model from a given RDF-based model, supporting model development. Secondly, we propose to use RDF-based models to generate a digital shadow of AASs to improve semantic discoverability. Preliminary results demonstrate that heterogeneity of metamodels does not exclude achieving semantic interoperability, as well as that greater functionality can be obtained compared to using both models in isolation. The solutions will be further developed in collaboration with pilot lines in the MAS4AI project.

Improving the representation of image descriptions for semantic image retrieval with RDF

The past few years have witnessed a surge of interest in many topics at the intersection of natural language processing and computer vision. In particular, using objects together with their attributes and relations to represent images or interpret languages has been proved useful across a wide variety of applications. The goal of this work is to provide an improved RDF-based model to represent images for enhancing textual based image retrieval. We use natural language processing tools to obtain a set of objects, attributes and relations; and then model them into graphical structures with RDF-based model. We also conduct some preliminary experiments to show how to handle textual based image retrieval for complex queries or multilingual queries. The experimental results show that our approach improves the representation of image descriptions, which is suitable for enhancing image retrieval with high-level semantics.