A framework for the automated generation of power-efficient classifiers for embedded sensor nodes

Ari Y. Benbasat, Joseph A. Paradiso
2007 Proceedings of the 5th international conference on Embedded networked sensor systems - SenSys '07  
This paper presents a framework for power-efficient detection in embedded sensor systems. State detection is structured as a decision tree classifier that dynamically orders the activation and adjusts the sampling rate of the sensors (termed groggy wakeup), such that only the data necessary to determine the system state is collected at any given time. This classifier can be tuned to trade-off accuracy and power in a structured, parameterized fashion. An embedded instantiation of these
more » ... s, including real-time sensor control, is described. An application based on a wearable gait monitor provides quantitative support for this framework. The decision tree classifiers achieved roughly identical detection accuracies to those obtained using support vector machines while drawing three times less power. Both simulation and real-time operation of the classifiers demonstrate that our multi-tiered classifier determines states as accurately as a single-trigger (binary) wakeup system while drawing as little as half as much power and with only a negligible increase in latency.
doi:10.1145/1322263.1322285 dblp:conf/sensys/BenbasatP07 fatcat:twvya3omwzamfhfqcgmjtnsqku