Lightweight signal processing for wearable body sensor networks

Use of mobile sensor-based platforms for human action recognitionis an ever-growing area of research. Recent advances in this field allowpatients to wear several small sensors with embedded processors and radios.Collectively, these sensors form a body sensor network (BSN). AlthoughBSNs have the potential to enable many useful applications [1], limitedprocessing power, storage and energy make efficient use of these systemscrucial. Moreover, user comfort is a major issue, which can cause patients tobecome frustrated and stop wearing the sensor nodes. The interactionbetween the human body and these wearable nodes here is defined as wearability.