An on-node intelligence based energy efficient ECG monitoring system

This paper proposes a two-tier body sensor network architecture for electrocardiogram (ECG) monitoring which consists of a base station layer and a sensor nodes layer with an intelligent ECG analysis function achieved by employing a simple but effective classification method. In this scenario, a sensor node only transmits sensed data to a base station when the sensed data shows abnormality. Such an approach is energy-efficient, while ensuring that abnormal ECG cycles are never missed. For the low power implementation of the abnormality detection on a local power-hungry sensor node, we propose a light-weight computation of the Euclidean distance between a sensed ECG signal and a reference ECG signal. Using experimental results obtained on PowerTOSSIM, we demonstrate that our approach can reduce power consumption of the sensor nodes by 39-57% and, accordingly, prolong the lifetime of the whole monitoring system.