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

Abstract

Wireless body area networks (WBANs) are emerging as a powerful tool for health management, emergency response, military personnel wellness as well as sports and entertainment. In contrast to traditional sensor networks for, say, environmental sensing, WBANs are often characterized by a modest number of heterogeneous sensors wirelessly coupled to a fusion center such as a mobile phone. Based on an actual implementation of a prototype WBAN, energy efficiency at the fusion center has proven to be one of the critical roadblocks to long-term deployment of WBANs. To this end, a novel formulation based on stochastic control tools is devised to model the sensor selection process. Sensors are heterogeneous both in their discrimination capabilities as well as their energy cost, further challenging sensor selection. The goal is to maximize the WBAN's lifetime while optimizing the performance of a physical state detection application. To this end, an optimal dynamic programming algorithm is derived. However, due to the prohibitive complexity of the optimal method, a low-cost approximation scheme, T3S, is designed. The low complexity design is based on several key properties of the cost functional. The proposed T3S scheme is evaluated on real-world data collected from an implemented WBAN and observed to offer near optimal performance with significantly lower complexity.

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

“…c ⃝IEEE the total energy consumption. Similarly, by striking a trade-off between the detection performance and energy consumption, Zois et al [287] designed a POMDP aided sensor node selection scheme for WBANs by maximizing the system's lifetime as well as optimizing the physical state detection accuracy. The main goal of the sensor node selection was to devise a schedule under which the sensors alternated between the active state and the dormant state relying on the specific network activity.…”

Context-Aware Sensing via Dynamic Programming for Edge-Assisted Wearable Systems

“…In 2012-2014, Zois et al [22][23][24] proposed MDP-based approaches to detect the activity of a monitored subject by means of imperfect observations acquired by noisy wearable sensors. The framework proposed in those works, which is based on partially observable Markov decision rocesses, enable exploration of the trade-off between energy consumption, sampling rate, and estimation accuracy.…”

Joint sink deployment and association for multi‐sink wireless camera networks

“…Then, each camera c can stream its surveillance video at a transmission rate r c back to any sink that operates over the same channel, where r c 2 R and R is the set of all available transmission bit rates; for example, R D f6, 9,12,18,24,36,48, 54g Mb/s in 802.11a. To mathematically formulate the multi-sink deployment problem, we quantize the surveillance terrain as a finite set of possible deployment locations L. For example, a terrain can be quantized as a set of locations with an integer coordinate .x, y/, where x 2 Z and y 2 Z; that is, each possible location is a 1 m 1 m grid.…”

“…Many past works have been devoted to configure the cameras effectively, including how many cameras are required to monitor an area of interest [7][8][9], what resolution or video rates are sufficient for video analysis [3], where the cameras should be deployed [6,[10][11][12], and even what direction should the cameras face [7]. However, less attention has been drawn to sink deployment.…”