AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices
This addresses power and memory limitations in wearable devices, offering a significant improvement for users and developers, though it is incremental as it builds on existing optimization techniques.
The paper tackles the problem of high power consumption in wearable devices for human activity recognition by introducing AdaSense, a co-optimized framework that dynamically switches sensor configurations based on user activity, resulting in a 69% reduction in power consumption with less than 1.5% decrease in accuracy.
Wearable devices have strict power and memory limitations. As a result, there is a need to optimize the power consumption on those devices without sacrificing the accuracy. This paper presents AdaSense: a sensing, feature extraction and classification co-optimized framework for Human Activity Recognition. The proposed techniques reduce the power consumption by dynamically switching among different sensor configurations as a function of the user activity. The framework selects configurations that represent the pareto-frontier of the accuracy and energy trade-off. AdaSense also uses low-overhead processing and classification methodologies. The introduced approach achieves 69% reduction in the power consumption of the sensor with less than 1.5% decrease in the activity recognition accuracy.