A Review of data fusion models and architectures: towards engineering guidelines
Neural Computing and Applications
UAHCI '09 Proceedings of the 5th International Conference on Universal Access in Human-Computer Interaction. Addressing Diversity. Part I: Held as Part of HCI International 2009
| Hi-index | 0.00 |
Improved sensing technologies and cheap sensor devices facilitate the creation of Ambient Assisted Living (AAL) environments. Whereas the increasing manifoldness of sensing possibilities helps to gain detailed and precise information about the environment, the task of dynamically mapping data from different sensor sources to a processable data model becomes more and more complex. Especially in AAL environments which build upon different sensors and sensor networks, the integration of distinct data sources becomes an issue. Most systems cope with this issue by requiring hand written adapters which encapsulate the device communication as well as the data mapping logic. Within this paper we tackle the problem of mapping perceived sensor data to a formal (ontology-based) model with a semi-automated approach. We split up the mapping in two separate parts: (i) a protocol specific adapter which encapsulates the communication with the sensor device and (ii) a mapping description. The mapping description is specific for each sensor type and defines how the sensed data is mapped to the data model. In addition the mapping description can be used to enrich the data model with additional information, like time and space.