Daphney-Stavroula Zois

Energy-Efficient, Heterogeneous Sensor Selection for Physical Activity Detection in Wireless Body Area Networks

In this paper, the problem of efficient operation of an energy-constrained, heterogeneous Wireless Body Area Network (WBAN) to optimize an activity detection application is addressed. WBANs constitute a new class of wireless sensor networks that enable diverse applications in healthcare, entertainment, sports, military and emergency situations. A typical WBAN consists of a few, heterogeneous sensors wirelessly coupled to an energy-constrained fusion center which, according to observations of a real-world prototype WBAN, imposes critical restrictions on system lifetime. To address this issue, a novel stochastic control framework is introduced, which considers both sensor heterogeneity and application requirements, for achieving the two-fold goal: energy savings with satisfactory detection performance. An optimal dynamic programming algorithm for the sensor selection problem is also derived. Important properties of the cost functionals are derived and used to design three approximation algorithms, which offer near optimal performance with significant complexity reduction. Simulations on real-world data show energy gains as high as 68% in comparison to an equal allocation scheme with probability of detection error on the order of 10-4.

KNOWME: a case study in wireless body area sensor network design

Wireless body area sensing networks have the potential to revolutionize health care in the near term. The coupling of biosensors with a wireless infrastructure enables the real-time monitoring of an individuals health and related behaviors continuously, as well as the provision of realtime feedback with nimble, adaptive, and personalized interventions. The KNOWME platform is reviewed, and lessons learned from system integration, optimization, and in-field deployment are provided. KNOWME is an endto- end body area sensing system that integrates off-the-shelf sensors with a Nokia N95 mobile phone to continuously monitor and analyze the biometric signals of a subject. KNOWME development by an interdisciplinary team and in-laboratory, as well as in-field deployment studies, employing pediatric obesity as a case study condition to monitor and evaluate physical activity, have revealed four major challenges: (1) achieving robustness to highly varying operating environments due to subject-induced variability such as mobility or sensor placement, (2) balancing the tension between acquiring high fidelity data and minimizing network energy consumption, (3) enabling accurate physical activity detection using a modest number of sensors, and (4) designing WBANs to determine physiological quantities of interest such as energy expenditure. The KNOWME platform described in this article directly addresses these challenges.

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

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 WBANs 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.

Non-linear smoothers for discrete-time, finite-state Markov chains

The problem of enhancing the quality of system state estimates is considered for a special class of dynamical systems. Specifically, a system characterized by a discrete-time, finite-state Markov chain state and observed via conditionally Gaussian measurements is assumed. The associated mean vectors and covariance matrices are tightly intertwined with the system state and a control input selected by a controller. Exploiting an innovations approach, finite-dimensional, non-linear approximate MMSE smoothing estimators are derived for the Markov chain system state. The resulting smoothers are driven by a control policy determined by a stochastic dynamic programming algorithm, which minimizes the MSE filtering error, and was proposed in our earlier work. An application of the smoothers derived in this paper is presented for the problem of physical activity detection in wireless body sensing networks, which illustrates the performance enhancement due to smoothing.

Sequential decision-making in healthcare IoT: Real-time health monitoring, treatments and interventions

Internet of Things (IoT) technology and infrastructure have the potential to revolutionize healthcare delivery. Networked body sensing devices coupled with sensors in our living environment enable the real-time and continuous collection of information related to an individuals physical and mental health and related behaviors. Captured in a continual basis and aggregated, such information needs to be effectively exploited to permit real-time, continuous and personalized monitoring, treatments and interventions. However, medical decisions are often sequential and uncertain in nature. Sequential decision-making models such as Markov decision processes (MDPs) and partially observable MDPs (POMDPs) constitute powerful tools for modeling and solving such stochastic and dynamic problems. In this paper, an overview of such models that are expected to support proactive, preventive and personalized healthcare delivery are surveyed along with the associated solution techniques. A set of representative health applications that take advantage of such tools is also described. Finally, various challenges and opportunities that arise during the realization of smart and connected healthcare IoT are highlighted.

Active object detection on graphs via locally informative trees

Active object detection refers to the problem of determining the existence and location of objects in an image by actively selecting which regions of the image to explore. Herein, an object detection algorithm is proposed that models image regions as vertices and overlap relationships as edges in a directed weighted graph. Information is propagated from labeled vertices through graph edges that operate as noisy channels via message passing over locally informative trees that are extracted from the original graph using an information-theoretic criterion. Influential vertices are determined by an appropriate centrality index. Our algorithm can be applied on top of any state-of-the-art region proposal method as it treats it as a black box. The effectiveness of the proposed algorithm is illustrated on different scenarios, where in some cases only 0.45% of the total regions is evaluated.

A POMDP approach for active collision detection via networked sensors

In recent years, urban mobility demand has become highly variable over time challenging the sustainability of transportation networks of major cities. At the same time, various types of incidents such as accidents, construction zone closures and weather hazards exacerbate the already congested transportation network. Timely detection of such events can offer an unprecedented opportunity to mitigate the consequences. In this paper, a partially observable Markov decision process (POMDP) framework is proposed for continuous active collision detection in a road segment equipped with spatially distributed speed sensors of variable accuracy. To this end, measurement selection strategies are designed that can quickly estimate the existence of a collision by appropriately selecting which sensors to query and when. A Kalman-like filter is used for estimation purposes. The efficacy of the proposed framework is shown on real data collected on the 405 freeway in the Los Angeles County.

A Weiss-Weinstein lower bound based sensing strategy for active state tracking.

The problem of sensing strategy design for active state tracking is considered. The system state is modeled by a discrete-time, finite-state Markov chain, which is observed through Gaussian measurement vectors that are dynamically selected by a controller. To overcome the computational complexity associated with the optimal sensing strategy derived in our prior work, a sensing strategy based on the sequential Weiss-Weinstein lower bound (WWLB) is proposed. To this end, closed-form WWLB formulae for our system model are obtained, while accommodating for multi-valued discrete parameters and control inputs. Numerical results validating the success of the proposed strategy on real data from a physical activity tracking application are provided.

Controlled sensing: A myopic fisher information sensor selection algorithm

This paper considers the problem of state tracking with observation control for a particular class of dynamical systems. The system state evolution is described by a discrete-time, finite-state Markov chain, while the measurement process is characterized by a controlled multi-variate Gaussian observation model. The computational complexity of the optimal control strategy proposed in our prior work proves to be prohibitive. A suboptimal, lower complexity algorithm based on the Fisher information measure is proposed. Toward this end, the preceding measure is generalized to account for multi-valued discrete parameters and control inputs. A closed-form formula for our system model is also derived. Numerical simulations are provided for a physical activity tracking application showing the near-optimal performance of the proposed algorithm.

A unified framework for energy efficient physical activity tracking

A unified framework of joint state tracking and control design is proposed for energy-efficient physical activity tracking in heterogeneous Wireless Body Area Networks (WBANs). The objective is to devise sensor selection strategies for the WBANs fusion center to optimize the trade-off between tracking performance and energy consumption. Our recently proposed Kalman-like estimator is employed for state tracking. The associated mean-squared error and an appropriate energy consumption metric are used in a partially observable Markov decision process formulation to derive the optimal selection strategy. A low-complexity suboptimal strategy is also proposed. Numerical results are provided using real WBAN experimental data.