Towards Context Awareness Using Symbol Clustering Map
Johan Himberg, John A. Flanagan, Jani Mäntyjärvi · 2003
Recognizing the context of use is important in making mobile devices simple to use. The device and the underlying mobile service can provide a personalized user interface that adapts to the usage situation. The device can infer parts of the context of the user from features extracted from on-board measurements of acceleration, noise level, luminosity, humidity, etc. In this paper we consider context recognition by fusing and clustering these context features using a recently introduced method, the Symbol Clustering Map. As such, it can be used for finding static patterns but a suitable transformation of the data allows identifying also temporal patterns.