Abstract
Today's activity and context recognition system have the drawback to use a static sensing infrastructure that has to be defined at the design time of the system. The predefined sensing infrastructure needed to work properly, as well as the fixed recognition purpose limits the flexibility of such a system as it can't react on changes in the sensing infrastructure nor it can address a change in its recognition purpose. In open ended dynamic, environments the sensing infrastructure can change during runtime of the system as new sensors can appear and disappear in a dynamic way. The term opportunistic sensing addresses this in selecting sensors that just happen to be available according to a stated recognition goal instead of using a predefined sensor infrastructure. Methodologies on how to state such a recognition goal to an opportunistic activity and context recognition system and how these goals can be translated into a machine readable and executable form to handle dynamic sensor setups have to be developed within the authors PhD-thesis.
| Original language | English |
|---|---|
| Title of host publication | Adjunct Proceedings of the 9th International Conference on Pervasive Computing (Pervasive2011) (Doctoral Consortium) |
| Number of pages | 3 |
| Publication status | Published - Jun 2011 |
Fields of science
- 102 Computer Sciences
- 102001 Artificial intelligence
- 102018 Artificial neural networks
JKU Focus areas
- Computation in Informatics and Mathematics
- Engineering and Natural Sciences (in general)