In the Semantic Web of Everything, observation data collected from sensors and devices disseminated in smart environments must be annotated in order to produce a Knowledge Base (KB) or Knowledge Graph (KG) which can be used subsequently for inference. Available approaches allow defining complex data models for mapping tabular data to KBs/KGs: while granting high flexibility, they can be difficult to use. This paper introduces a framework for automatic KB generation in Web Ontology Language (OWL) 2 from observation data sets. It aims at simplicity both in usage and in expressiveness of generated KBs, in order to enable reasoning with SWoE inference engines in pervasive and embedded devices. An illustrative example from a precision farming case study clarifies the approach and early performance results support its computational sustainability.
A Framework for Automatic Knowledge Base Generation from Observation Data Sets
Giuseppe Loseto;
2023-01-01
Abstract
In the Semantic Web of Everything, observation data collected from sensors and devices disseminated in smart environments must be annotated in order to produce a Knowledge Base (KB) or Knowledge Graph (KG) which can be used subsequently for inference. Available approaches allow defining complex data models for mapping tabular data to KBs/KGs: while granting high flexibility, they can be difficult to use. This paper introduces a framework for automatic KB generation in Web Ontology Language (OWL) 2 from observation data sets. It aims at simplicity both in usage and in expressiveness of generated KBs, in order to enable reasoning with SWoE inference engines in pervasive and embedded devices. An illustrative example from a precision farming case study clarifies the approach and early performance results support its computational sustainability.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
