Energy-efficient multihypothesis activity-detection for health-monitoring applications

Multi-hypothesis activity-detection using a wireless body area network is considered. A fusion center receives samples of biometric signals from heterogeneous sensors. Due to the different discrimination capabilities of each sensor, an optimized allocation of samples per sensor results in lower energy consumption. Optimal sample allocation is determined by minimizing the probability of misclassification given the current activity state of the user. For a particular scenario, optimal allocation can achieve the same accuracy (97%) as equal allocation across sensors with an energy savings of 26%. As the number of samples is an integer, further energy reduction is achieved by developing an approximation to the probability of misclassification which allows for a continuous-valued vector optimization. This alternate optimization yields approximately optimal allocations with significantly lower complexity, facilitating real-time implementation.