Search

Power consumption is identified as one of the main complications in designing practical wearable systems, mainly due to their stringent resource limitations. When designing wearable technologies, several system-level design choices, which directly contribute to the energy consumption of these systems, must be considered. In this article, we propose a computationally lightweight system optimization framework that trades off power consumption and performance in connected wearable motion sensors. While existing approaches exclusively focus on one or a few hand-picked design variables, our framework holistically finds the optimal power-performance solution with respect to the specified application need. Our design tackles a multi-variant non-convex optimization problem that is theoretically hard to solve. To decrease the complexity, we propose a smoothing function that reduces this optimization to a convex problem. The reduced optimization is then solved in linear time using a devised derivative-free optimization approach, namely cyclic coordinate search. We evaluate our framework against several holistic optimization baselines using a real-world wearable activity recognition dataset. We minimize the energy consumption for various activity-recognition performance thresholds ranging from 40% to 80% and demonstrate up to 64% energy savings.

Designing remote health monitoring systems requires a multi-faceted perspective that takes into account requirements and contexts imposed by the medical application, technology, and end-user. We study such a design perspective in the context of remote and real-time edema monitoring. Edema (accumulation of fluid in certain soft-tissues) is regarded as one of the most important symptoms for systematic diseases such as heart failure. Monitoring edema allows patients and caregivers to understand the state of sickness and effectiveness of the treatments. This article proposes a novel low-power context-aware and real-time wearable platform capable of continuous assessment of ankle edema in remote settings. Our system keeps track of changes in subject’s ankle circumference as well as current body posture. An examination of our system with 15 subjects demonstrates the effectiveness and reliability of the proposed force-sensitive-resistor-based edema sensor (with an $R^2$ of 0.87 for our regression model and intraclass correlation of 0.97) as well as an over 96 percent accuracy in activity monitoring that provide the means to perform reliable data validation on ankle circumference measurements in a continuous manner. Furthermore, we devise a novel derivative-free power optimization approach to maximize the battery lifetime resulting in improvement in battery lifetime by a factor of 2.13.

Activity recognition, as an important component of behavioral monitoring and intervention, has attracted enormous attention, especially in Mobile Cloud Computing (MCC) and Remote Health Monitoring (RHM) paradigms. While recently resource constrained wearable devices have been gaining popularity, their battery life is limited and constrained by the frequent wireless transmission of data to more computationally powerful back-ends. This paper proposes an ultra-low power activity recognition system using a novel adaptive compressed sensing technique that aims to minimize transmission costs. Coarse-grained on-body sensor localization and unsupervised clustering modules are devised to autonomously reconfigure the compressed sensing module for further power saving. We perform a thorough heuristic optimization using Grammatical Evolution (GE) to ensure minimal computation overhead of the proposed methodology. Our evaluation on a real-world dataset and a low power wearable sensing node demonstrates that our approach can reduce the energy consumption of the wireless data transmission up to 81.2 and 61.5 percent, with up to 60.6 and 35.0 percent overall power savings in comparison with baseline and a naive state-of-the-art approaches, respectively. These solutions lead to an average activity recognition accuracy of 89.0 percent-only 4.8 percent less than the baseline accuracy-while having a negligible energy overhead of on-node computation.

Wearable motion sensors are widely used to estimate metabolic equivalent of task (MET) values associated with physical activities. However, one major obstacle in widespread adoption of current wearables is that any changes in configuration of the network requires new data collection and re-training of the underlying signal processing algorithms. For any wearable-based MET estimation framework to be considered a viable platform, it needs to be reconfigurable, reliable, and power-efficient. In this paper, we aim to address the issues of sensor misplacement, power efficiency, and new sensor addition and propose a reliable and reconfigurable MET estimation framework. We introduce a power-aware sensor localization approach that allows users to wear the sensors on different body locations without need for adhering to a specific installation protocol. Furthermore, we propose a novel transductive transfer learning approach, which gives end-users the ability to add new sensors to the network without need for collecting new training data. This is accomplished by transferring the knowledge of already trained sensors to the untrained sensors in real-time. Our experiments demonstrate that our sensor localization algorithm achieves an accuracy of $90.8$ % in detecting location of the wearable sensors. The integrated model of sensor localization and MET calculation achieves an $R^2$ of $0.8$ in estimating MET values using a regression-based model. Furthermore, our transfer learning algorithm improves the $R^2$ value of MET estimation up to $60\%$ .

Wearables are being widely utilized in health and wellness applications, primarily due to the recent advances in sensor and wireless communication, which enhance the promise of wearable systems in providing continuous and real-time monitoring and interventions. Wearables are generally composed of hardware/software components for collection, processing, and communication of physiological data. Practical implementation of wearable monitoring in real-life applications is currently limited due to notable obstacles. The wearability and form factor are dominated by the amount of energy needed for sensing, processing, and communication. In this article, we propose an ultra-low-power granular decision-making architecture, also called screening classifier, which can be viewed as a tiered wake-up circuitry, consuming three orders of magnitude-less power than the state-of-the-art low-power microcontrollers. This processing model operates based on computationally simple template matching modules, based on coarse- to fine-grained analysis of the signals with on-demand and gradually increasing the processing power consumption. Initial template matching rejects signals that are clearly not of interest from the signal processing chain, keeping the rest of processing blocks idle. If the signal is likely of interest, the sensitivity and the power of the template matching modules are gradually increased, and ultimately, the main processing unit is activated. We pose optimization techniques to efficiently split a full template into smaller bins, called mini-templates, and activate only a subset of bins during each classification decision. Our experimental results on real data show that this signal screening model reduces power consumption of the processing architecture by a factor of 70% while the sensitivity of detection remains at least 80%.

Smartphone prompts and notifications are popular because they provide users with timely and important information. However, they can also be an annoyance if they pop up at inopportune times and interrupt important tasks. In this paper, we introduce Thyme, an intelligent notification front end that uses activity recognition and machine learning to identify the best times to prompt smartphone users. We evaluate the performance of an activity-aware prompting approach based on 47 participants with fixed time and Thyme-based prompts. Our results show that responsiveness improves from 12.8% to 93.2% using this intelligent approach to the timing of smartphone-based prompts.

Activity recognition systems are widely used in monitoring physical and physiological conditions as well as observing the short/long term behavioral patterns for the purpose of improving the health and wellbeing of the users. The major obstacle in widespread use of these systems is the need for collecting labeled data to train the activity recognition model. While a personalized model outperforms a user-independent model, collecting labels from every single user is burdensome and in some cases impractical. In this paper, we propose an uninformed cross-subject transfer learning algorithm that leverages the cross-user similarities by constructing a network-based feature-level representation of the data in source and target users and perform a best effort community detection to extract the core observations in target data. Our algorithm uses a heuristic classifier-based mapping to assign activity labels to the core observations. Finally, the output of labeling is conditionally fused with the prediction of the source-model to develop a boosted and personalized activity recognition algorithm. Our analysis on real-world data demonstrates the superiority of our approach. Our algorithm achieves over 87% accuracy on average which is 7% higher than the state-of-the art approach.

One of major challenges in chronic disease self-management is the lack of medication adherence. Despite the proliferation of mobile technologies, the potential of using pervasive computing solutions for improved medication management has remained almost unexplored. In this paper, we present a smart-phone based system capable of delivering adaptive activity-aware medication reminders by learning the user’s activity of daily living and detecting the most appropriate and effective timing for medication reminders centered around the initial user-specified schedule.

Ankle edema an important symptom for monitoring patients with chronic systematic diseases. It is an important indicator of onset or exacerbation of a variety of diseases that disturb cardiovascular, renal, or hepatic system such as heart, liver, and kidney failure, diabetes, etc. The current approaches toward edema assessment are conducted during clinical visits. In-clinic assessments, in addition to being burdensome and expensive, are sometimes not reliable and neglect important contextual factors such as patient's physical activity level and body posture. A novel wearable sensor, namely SmartSock, equipped with accelerometer and flexible stretch sensor embedded in clothing is presented. SmartSock is powered by advanced machine learning, signal processing, and correlation techniques to provide real-time, reliable, and context-rich information in remote settings. Our experiments on human subjects indicate high confidence in activity and posture recognition (with an accuracy of > 96%) as well as reliable edema quantification with intra-class correlation and Pearson correlation of 0.97.

Intervention strategies can help individuals with cognitive impairment to increase adherence to instructions, independence, and activity engagement and reduce errors on everyday instrumental activities of daily living (IADLs) and caregiver burden. However, to be effective, intervention prompts should be given at a time that does not interrupt other important user activities and is more convenient. In this paper, we propose an intelligent personalized intervention system for smartphones. In our approach, we use context and activity awareness to time prompts when they will most likely be viewed and used. Our result based on real data collected using smartphone motion sensors demonstrate that the proposed approach can detect the time-frame of a user response with an average accuracy of 65% and reduce the inefficiency by 39%, on average, compared to different static time interventions which shows the possibilities and advantages of the proposed system to increase user satisfaction and response rate.

Wearable monitoring devices for ubiquitous health care are becoming a reality that has to deal with limited battery autonomy. Several researchers focus their efforts in reducing the energy consumption of these motes: from efficient micro-architectures, to on-node data processing techniques. In this paper we focus in the optimization of the energy consumption of monitoring devices for the prediction of symptomatic events in chronic diseases in real time. To do this, we have developed an optimization methodology that incorporates information of several sources of energy consumption: the running code for prediction, and the sensors for data acquisition. As a result of our methodology, we are able to improve the energy consumption of the computing process up to 90% with a minimal impact on accuracy. The proposed optimization methodology can be applied to any prediction modeling scheme to introduce the concept of energy efficiency. In this work we test the framework using Grammatical Evolutionary algorithms in the prediction of chronic migraines.

With the proliferation of wearable devices in the Internet-of-Things applications, designing highly power-efficient solutions for continuous operation of these technologies in life-critical settings emerges. We propose a novel ultra-low power framework for adaptive compressed sensing in activity recognition. The proposed design uses a coarse-grained activity recognition module to adaptively tune the compressed sensing module for minimized sensing/transmission costs. We pose an optimization problem to minimize activity-specific sensing rates and introduce a polynomial time approximation algorithm using a novel heuristic dynamic optimization tree. Our evaluations on real-world data shows that the proposed autonomous framework is capable of generating feedback with −80% confidence and improves power reduction performance of the state-of-the-art approach by a factor of two.

Author(s): Evangelista, Lorraine S; Ghasemzadeh, Hassan; Lee, Jung-Ah; Fallahzadeh, Ramin; Sarrafzadeh, Majid; Moser, Debra K | Abstract: BackgroundIt is unclear whether subgroups of patients may benefit from remote monitoring systems (RMS) and what user characteristics and contextual factors determine effective use of RMS in patients with heart failure (HF).ObjectiveThe study was conducted to determine whether certain user characteristics (i.e. personal and clinical variables) predict use of RMS using advanced machine learning software algorithms in patients with HF.MethodsThis pilot study was a single-arm experimental study with a pre- (baseline) and post- (3 months) design; data from the baseline measures were used for the current data analyses. Sixteen patients provided consent; only 7 patients (mean age 65.8 ± 6.1, range 58-83) accessed the RMS and transmitted daily data (e.g. weight, blood pressure) as instructed during the 12 week study duration.ResultsBaseline demographic and clinical characteristics of users and non-users were comparable for a majority of factors. However, users were more likely to have no HF specialty based care or an automatic internal cardioverter defibrillator. The precision accuracy of decision tree, multilayer perceptron (MLP) and k-Nearest Neighbor (k-NN) classifiers for predicting access to RMS was 87.5%, 90.3%, and 94.5% respectively.ConclusionOur preliminary data show that a small set of baseline attributes is sufficient to predict subgroups of patients who had a higher likelihood of using RMS. While our findings shed light on potential end-users more likely to benefit from RMS-based interventions, additional research in a larger sample is warranted to explicate the impact of user characteristics on actual use of these technologies.

Power consumption is a major obstacle in designing stringent resource constraint wearables. Several system-level design considerations contribute to energy consumption of these systems which must be taken into account while designing the system. We propose a power-performance optimization framework, namely CyHOP (Cyclic and Holistic Optimization framework), for connected wearable motion sensors. While existing work focus solely on one design parameter, our approach globally trades-off the performance of activity recognition and power consumption. CyHOP is capable of optimally adjusting the system to fulfill specific application needs. Using a smoothing technique, the initial multi-variate non-convex optimization problem is reduced to a convex problem and solved using our devised derivative-free optimization approach, namely, cyclic coordinate search. Our model performs a linear search by cycling through the system variables on each iteration until it converges to the global optimum. Using real-world data collected with wearable motion sensors during activity monitoring, we validate our approached with various performance thresholds ranging from 40% to 80%.

One of the most important challenges in chronic disease self-management is medication non-adherence, which has irrevocable outcomes. Although many technologies have been developed for medication adherence monitoring, the reliability and cost-effectiveness of these approaches are not well understood to date. This paper presents a medication adherence monitoring system by user-activity tracking based on wrist-band wearable sensors. We develop machine learning algorithms that track wrist motions in real-time and identify medication intake activities. We propose a novel data analysis pipeline to reliably detect medication adherence by examining single-wrist motions. Our system achieves an accuracy of 78.3% in adherence detection without need for medication pillboxes and with only one sensor worn on either of the wrists. The accuracy of our algorithm is only 7.9% lower than a system with two sensors that track motions of both wrists.

Background: As commercially available activity trackers are being utilized in clinical trials, the research community remains uncertain about reliability of the trackers, particularly in studies that involve walking aids and low-intensity activities. While these trackers have been tested for reliability during walking and running activities, there has been limited research on validating them during low-intensity activities and walking with assistive tools. Objective: The aim of this study was to (1) determine the accuracy of 3 Fitbit devices (ie, Zip, One, and Flex) at different wearing positions (ie, pants pocket, chest, and wrist) during walking at 3 different speeds, 2.5, 5, and 8 km/h, performed by healthy adults on a treadmill; (2) determine the accuracy of the mentioned trackers worn at different sites during activities of daily living; and (3) examine whether intensity of physical activity (PA) impacts the choice of optimal wearing site of the tracker. Methods: We recruited 15 healthy young adults to perform 6 PAs while wearing 3 Fitbit devices (ie, Zip, One, and Flex) on their chest, pants pocket, and wrist. The activities include walking at 2.5, 5, and 8 km/h, pushing a shopping cart, walking with aid of a walker, and eating while sitting. We compared the number of steps counted by each tracker with gold standard numbers. We performed multiple statistical analyses to compute descriptive statistics (ie, ANOVA test), intraclass correlation coefficient (ICC), mean absolute error rate, and correlation by comparing the tracker-recorded data with that of the gold standard. Results: All the 3 trackers demonstrated good-to-excellent (ICC>0.75) correlation with the gold standard step counts during treadmill experiments. The correlation was poor (ICC