Implementation study of wearable sensors for human activity recognition systems
Hamed Rezaie, Mona Ghassemian · Institution of Engineering and Technology eBooks · 2019
This chapter addresses a number of activity recognition methods for a wearable sensor system. Three methods for data transmission, namely `stream-based', `feature-based' and `threshold-based' scenarios are applied to study the accuracy against energy efficiency of transmission and processing power that affects the mote's battery lifetime. The impact of variation of sampling frequency and data transmission rate on energy consumption of motes is also analysed for each method. This study leads the authors to propose a cross-layer optimisation of an activity recognition system for provisioning acceptable levels of accuracy and energy efficiency.