Handling Displacement Effects in On-Body Sensor-Based Activity Recognition
- Cite this paper as:
- Baños O., Damas M., Pomares H., Rojas I. (2013) Handling Displacement Effects in On-Body Sensor-Based Activity Recognition. In: Nugent C., Coronato A., Bravo J. (eds) Ambient Assisted Living and Active Aging. IWAAL 2013. Lecture Notes in Computer Science, vol 8277. Springer, Cham
So far little attention has been paid to activity recognition systems limitations during out-of-lab daily usage. Sensor displacement is one of these major issues, particularly deleterious for inertial on-body sensing. The effect of the displacement normally translates into a drift on the signal space that further propagates to the feature level, thus modifying the expected behavior of the predefined recognition systems. On the use of several sensors and diverse motion-sensing modalities, in this paper we compare two fusion methods to evaluate the importance of decoupling the combination process at feature and classification levels under realistic sensor configurations. In particular a ’feature fusion’ and a ’multi-sensor hierarchical-classifier’ are considered. The results reveal that the aggregation of sensor-based decisions may overcome the difficulties introduced by the displacement and confirm the gyroscope as possibly the most displacement-robust sensor modality.
KeywordsSensor displacement Sensor network Sensor fusion Activity recognition Human Behavior Motion sensors
Unable to display preview. Download preview PDF.