This paper presents a distributed information extraction and visualisation service, called the mapping service, for maximising information return from large-scale wireless sensor networks. Such a service would greatly simplify the production of higher-level, information-rich, representations suitable for informing other network services and the delivery of field information visualisations. The mapping service utilises a blend of inductive and deductive models to map sense data accurately using externally available knowledge. It utilises the special characteristics of the application domain to render visualisations in a map format that are a precise reflection of the concrete reality. This service is suitable for visualising an arbitrary number of sense modalities. It is capable of visualising from multiple independent types of the sense data to overcome the limitations of generating visualisations from a single type of sense modality. Furthermore, the mapping service responds dynamically to changes in the environmental conditions, which may affect the visualisation performance by continuously updating the application domain model in a distributed manner. Finally, a distributed self-adaptation function is proposed with the goal of saving more power and generating more accurate data visualisation. We conduct comprehensive experimentation to evaluate the performance of our mapping service and show that it achieves low communication overhead, produces maps of high fidelity, and further minimises the mapping predictive error dynamically through integrating the application domain model in the mapping service.
展开▼
