Context-aware mobile computing requires wearable sensors to acquire information about the user. Continuous sensing rapidly depletes the wearable system's energy, which is a critically constrained resource. In this paper, we analyze the trade-off between power consumption and prediction accuracy of context classifiers working on dual-axis accelerometer data collected from the eWatch sensing and notification platform. We improve power consumption tech- niques by providing competitive classification performance even in the low frequency region of 1-10 Hz and for the highly erratic wrist based sensing location. Furthermore, we propose and analyze a collection of selective sampling strategies in order to reduce the number of required sensor readings and the computation cycles even further. Our results indicate that optimized sampling schemes can increase the deployment lifetime of a wearable computing platform by a factor of four without a significant loss in prediction accuracy.

@inproceedings{krause05trading,
	author = {Andreas Krause and Matthias Ihmig and Edward Rankin and Derek Leong and Smriti Gupta and Daniel Siewiorek and Asim Smailagic and Michael Deisher and Uttam Sengupta},
	booktitle = {Proc. 9th International Symposium on Wearable Computers (ISWC)},
	month = {October},
	title = {Trading off Prediction Accuracy and Power Consumption for Context-Aware Wearable Computing},
	year = {2005}}