TY  - CONF
T1  - Context Cells: Towards Lifelong Learning in Activity Recognition Systems
A1  - Calatroni, Alberto
A1  - Villalonga, Claudia
A1  - Roggen, Daniel
A1  - Tröster, Gerhard
TI  - Proceedings of the 4th European Conference on Smart Sensing and Context (EuroSSC)
T3  - LNCS
Y1  - 2009
PB  - Springer
KW  - Activity Recognition
KW  - Automatic Labelling
KW  - Autonomous Evolution
KW  - Context Cell
KW  - context recognition
KW  - incremental learning
KW  - OPPORTUNITY
KW  - Wearable Computing
N2  - A robust activity and context-recognition system must be capable of operating over a long period of time, exploiting new sources of information as they become available and evolving in an autonomous manner, coping with user variability and changes in the number and type of available sensors. In particular, wearable and ambient nodes should be trained lifelong, as new context instances naturally arise, and the labeling of the instances should be carried out ideally with no user intervention. In this paper we show by means of an experiment and simulations that we can indeed achieve lifelong learning and automatic labeling by using Context Cells, an architecture capable of sensing, learning, classifying data and exchanging information.
ER  -