Nowadays, Wireless Body Sensor Networks (WBSN) are emerging as a low cost solution for healthcare application to find new solutions, regarding patient monitoring
which is becoming the elusive requirement. Quicker emergency
detection is the main purpose to create a quicker reaction
and treatment if required, such as an abnormal variation of
the respiration rate, which satisfies the goal of extending life
expectancy. This process can help all the chronic patients who
are most of the time living alone or in nursing homes. However,
the limited lifetime bio-medical sensors bring on the energy
consumption challenge as one of the leading challenges in WBSN.
Moreover, detecting locally an emergency is also one of the main
challenges in WBSN. In this paper, we propose an adaptive
sampling approach, based on fisher test theory, that estimates
and adapts the sensing frequency based on previous readings and
the patient criticality. The main goal is to optimize the energy
consumption. Furthermore, we show how emergency alerts can
be supported locally on each node of the network. To validate
the effectiveness of our approach we conducted several series of
simulations and built a simple energy saving comparison.