Optimal Time-Resource Allocation for Energy-Efficient Physical Activity Detection

Abstract

The optimal allocation of samples for physical activity detection in a wireless body area network for health-monitoring is considered. The number of biometric samples collected at the mobile device fusion center, from both device-internal and external Bluetooth heterogeneous sensors, is optimized to minimize the transmission power for a fixed number of samples, and to meet a performance requirement defined using the probability of misclassification between multiple hypotheses. A filter-based feature selection method determines an optimal feature set for classification, and a correlated Gaussian model is considered. Using experimental data from overweight adolescent subjects, it is found that allocating a greater proportion of samples to sensors which better discriminate between certain activity levels can result in either a lower probability of error or energy-savings ranging from 18% to 22%, in comparison to equal allocation of samples. The current activity of the subjects and the performance requirements do not significantly affect the optimal allocation, but employing personalized models results in improved energy-efficiency. As the number of samples is an integer, an exhaustive search to determine the optimal allocation is typical, but computationally expensive. To this end, an alternate, continuous-valued vector optimization is derived which yields approximately optimal allocations and can be implemented on the mobile fusion center due to its significantly lower complexity.

Kalman-like state tracking and control in POMDPS with applications to body sensing networks

“…We use real data collected through an implemented WBAN, the KNOWME network [18]. For clarity of exposition, we focus on the three-sensor case, two ACCs and one ECG, with four physical activity states (Sit, Stand, Run, Walk), and underscore that our methods are directly applicable to multiple sensors and physical states.…”

“…At each time step, the WBAN sensors generate a set of biometric signals; feature extraction and selection techniques [17,18] are employed to produce a set of samples that correspond to extracted features' values, e.g. ACC mean, ECG period.…”

A POMDP framework for heterogeneous sensor selection in wireless body area networks

“…Motivated by our previous work [8], we address the problem of designing a heterogeneous sensor selection algorithm for a Wireless Body Area Network (WBAN) with an energyconstrained fusion center to optimize a physical activity detection application. We consider a time-varying system in contrast to [8].…”

“…We consider a time-varying system in contrast to [8]. Our goal is two-fold: maximize the lifetime of such a unique sensor network while achieving accurate This research has been funded in part by the following grants and organizations: ONR N00014-09-1-0700, NSF CNS-0832186, NSF CCF-0917343, the National Center on Minority Health and Health Disparities (NCMHD) (supplement to P60 MD002254), Nokia and Qualcomm.…”

“…activity detection. Given our prototype system [8], continuously collecting samples from all the WBAN sensors leads to undesirably high energy consumption at the fusion center (cellphone). Being fully charged, the fusion center's battery is depleted in a couple of hours with such a sampling scheme, while the WBAN dedicated sensors can run for a couple of weeks.…”