Search

Modern processors often need to switch among different power states based on usage scenarios, energy availability, and thermal conditions. Dynamic voltage and frequency scaling (DVFS) is a commonly used power management strategy to trade off performance and energy. As transistor scaling is reaching its limit, the viable supply voltage range where DVFS can operate is shrinking, which limits its effectiveness. To extend the performance-energy trade-off capabilities in modern processors, this article proposes dynamic core scaling (DCS) that does not rely on voltage scaling. DCS dynamically adjusts the active superscalar datapath resources so that programs run at a given percentage of their maximum speed while minimizing energy consumption at the same time. Since DCS does not need voltage scaling, it can be combined with DVFS to achieve greater energy savings. To effectively manage performance-energy trade-offs using a combination of DCS and DVFS, this article proposes an oracle controller that demonstrates the optimal control strategy, and two practical controllers that are applicable in real implementations. Evaluations using an 8-way superscalar processor implemented in a 45-nm circuit show that DCS is more effective in performance-energy trade-offs than DVFS at the high performance end for a number of SPEC CPU2000 benchmarks. When used together with DVFS, DCS saves an additional 20 percent of a full-size core’s energy on average. At the minimum operating voltage, DVFS hits its limit, while DCS is still able to achieve an average of 46 percent further energy reduction.

Editor’s notes: A group of academicians from the University of Virginia has developed a graduate curriculum for cyber-physical systems education. The curriculum follows the National Academy of Engineering report on the need for such content consisting of multidisciplinary classes and professional development skills. — Mohammad Abdullah Al Faruque, University of California Irvine

Remote patient monitoring has emerged from the intersection of engineering and medicine. Advances in sensors, circuits and systems have made possible the implementation of small, wearable devices capable of collecting and streaming data for long periods of time to help physicians track diseases and detect conditions in a non-intrusive manner. Cardiac monitoring comprises many of these applications, with the need to capture transient cardiac events motivating the adoption of wearable monitors in standard clinical practice. However, user burden and battery life limit the duration of monitoring or require heavy duty cycling, thus preventing the adoption of these technologies for use cases that require long-term vigilant monitoring, in which the sensor system cannot miss a critical cardiac event. To overcome these challenges, this paper introduces a self-powered system for uninterrupted vigilant cardiac and activity monitoring that senses and streams electrocardiogram (ECG) and motion data continuously to a smartphone while consuming only $683~\mu \text{W}$ on average. To achieve self-powered operation under environmental and wearability constraints, the system incorporates an energy combining technique to support multi-modal energy harvesting from indoor solar and thermoelectric energy. A custom ECG shirt made of a knitted compression fabric with embedded dry electrodes addresses issues of user comfort, skin irritation and motion artifacts. Vigilant Atrial Fibrillation (AF) monitoring is used as an example case study, analyzing sampling frequency and bit-depth quantization and their correlation to vigilant, self-powered operation. The integrated system demonstrates an important step forward for remote patient monitoring beyond the clinic.

Dementia is a progressive brain disease that affects 5.8 million people in the USA. In 2018, more than 16 million Americans provided unpaid care for persons with dementia (PWD). Most of this care is provided by family members and friends yielding 18.5 billion hours of unpaid care worth $233.9 billion.Novel technological approaches to assist caregivers and improve health and function of PWD are being explored. Models to assess and predict behaviors may provide greater quality of life (QOL) for both PWD and their caregivers. The purpose of this paper is to review current available technologies for behavioral interventions in persons with Alzheimer’s disease or other related dementias who live in the home setting. High-quality systematic reviews have studied behavioral or psychological symptoms, some with non-pharmacological interventions (NPI). Some of these involve technology, but others address functional and safety issues. The most frequent behaviors identified in PWD were aggression, agitation, wandering, apathy, and disturbed sleep. There is some evidence of a beneficial effect of NPI on depression and ADL, but no impact on overall behavioral and psychological symptoms of dementia (BPSD), anxiety, or agitation. Technological interventions including combined phone and web impacted caregiver burden and depression. Multimodal sensors to detect agitation show moderate correlation and in-home video recording can improve caregiver’s competence and lessen depression. Acceptance and adherence in use of technologies are essential for PWD and their caregivers in the home setting. There is a need for more RCT’s and individualization of technologies and research must also involve both caregivers and PWD. Systematic reviews addressing behavioral symptoms identify music as the most effective NPI for improving overall BPSD.

Dietary intake, eating behaviors, and context are important in chronic disease development, yet our ability to accurately assess these in research settings can be limited by biased traditional self-reporting tools. Objective measurement tools, specifically, wearable sensors, present the opportunity to minimize the major limitations of self-reported eating measures by generating supplementary sensor data that can improve the validity of self-report data in naturalistic settings. This scoping review summarizes the current use of wearable devices/sensors that automatically detect eating-related activity in naturalistic research settings. Five databases were searched in December 2019, and 618 records were retrieved from the literature search. This scoping review included N = 40 studies (from 33 articles) that reported on one or more wearable sensors used to automatically detect eating activity in the field. The majority of studies (N = 26, 65%) used multi-sensor systems (incorporating > 1 wearable sensors), and accelerometers were the most commonly utilized sensor (N = 25, 62.5%). All studies (N = 40, 100.0%) used either self-report or objective ground-truth methods to validate the inferred eating activity detected by the sensor(s). The most frequently reported evaluation metrics were Accuracy (N = 12) and F1-score (N = 10). This scoping review highlights the current state of wearable sensors’ ability to improve upon traditional eating assessment methods by passively detecting eating activity in naturalistic settings, over long periods of time, and with minimal user interaction. A key challenge in this field, wide variation in eating outcome measures and evaluation metrics, demonstrates the need for the development of a standardized form of comparability among sensors/multi-sensor systems and multidisciplinary collaboration.

BACKGROUND Distressing cancer pain remains a serious symptom management issue for patients and family caregivers, especially in the home setting. Technology can support home-based cancer symptom management but must consider the experience of both patients and family caregivers, as well as the broader environmental context. OBJECTIVE To test feasibility and acceptability of a smart health sensing system, Behavioral and Environmental Sensing and Intervention for Cancer (BESI-C), designed to monitor, and ultimately support management of, cancer pain in the home setting. METHODS Dyads of patients with cancer and their primary family caregivers were recruited from an outpatient palliative care clinic at an academic medical center in the Southeastern U.S. BESI-C was deployed in dyad homes for approximately two weeks each. Data were collected via: 1) environmental sensors that measure ambient noise, humidity, barometric pressure, light, and temperature; 2) Bluetooth beacons to help localize dyad position; and 3) smart watches worn by both patients and caregivers equipped with heartrate monitors, accelerometers, and a custom application to deliver ecological momentary assessments (EMAs). EMAs enabled dyads to record and characterize pain events from both their own and their partner’s perspective. Sensor data streams were integrated to describe and explore the context for cancer pain events. Feasibility was assessed technically (by scoring each deployment regarding fidelity of data capture across system components) and procedurally (e.g., deployment process, participant recruitment). Acceptability was assessed by post-deployment surveys and structured interviews with participants. RESULTS 5 deployments (n=10 participants; 5 dyads of patients and primary family caregivers) were completed, and a total of 283 unique pain events were recorded. Using our ‘BESI-C Performance Scoring Instrument’, the overall feasibility technical score for deployments was 86.4/100. Procedural feasibility challenges included: rural location of dyads; smart watch battery life and EMA reliability; and length of time required for deployment installation. Post-deployment acceptability Likert surveys (1, strongly disagree; 5, strongly agree), found dyads disagreed that BESI-C was a burden (1.7/5) or compromised their privacy (1.9/5) and agreed the system collected helpful information to better manage cancer pain (4.6/5). Participants also expressed interest in seeing their own individual data (4.4/5) and strongly agreed it is important that data collected by BESI-C are shared with their respective partner (4.8/5) and healthcare provider (4.8/5). Qualitative feedback from participants suggests BESI-C positively improved communication regarding pain management. Importantly, we demonstrated proof of concept that seriously ill patients and their caregivers will mark pain events in real time using a smart watch. CONCLUSIONS It is feasible to deploy BESI-C, and dyads find the system acceptable. Leveraging human-centered design and the collection of heterogenous environmental, physiological, and behavioral data, BESI-C offers an innovative approach to monitor cancer pain, mitigate escalation of pain and distress, and improve symptom management self-efficacy. Future work will: (shorter-term) 1) test BESI-C in a larger, more diverse sample; 2) continue to streamline system architecture; 3) deploy a no-contact, self-installation system in response to the COVID-19 pandemic and to enhance scalability; 4) explore how to best share data visualizations of collected data with key stakeholders; and 5) (longer-term) inform design of and deliver just-in-time personalized pain management interventions to patients and caregivers. CLINICALTRIAL n/a INTERNATIONAL REGISTERED REPORT RR2-10.2196/16178

Central airway obstruction (CAO) is a respiratory disorder characterized by the blockage of the trachea and/or the main bronchi that can be life-threatening. Airway stenting is a palliative procedure for CAO commonly used given its efficacy. However, mucus impaction, secretion retention, and granulation tissue growth are known complications that can counteract the stent's benefits. To prevent these situations, patients are routinely brought into the hospital to check stent patency, incurring a burden for the patient and the health care system, unnecessarily when no problems are found. In this paper, we introduce a capacitive sensor embedded in a stent that can detect solid and colloidal obstructions in the stent, as such obstructions alter the capacitor's dielectric relative permittivity. In the case of colloidal obstructions (e.g., mucus), volumes as low as 0.1 ml can be detected. Given the small form factor of the sensor, it could be adapted to a variety of stent types without changing the standard bronchoscopy insertion method. The proposed system is a step forward in the development of smart airway stents that overcome the limitations of current stenting technology.Clinical Relevance- This establishes the foundation for smart stent technology to monitor stent patency as an alternative to rutinary bronchoscopies.

While relying on energy harvesting to power Internet of Things (IoT) devices eliminates the maintenance burden of battery replacement, energy generation fluctuation constitutes a major source of uncertainty to design reliable self-powered IoT devices. To characterize spatial-temporal variability of energy harvesting, data acquisition campaigns are needed across the range of potential harvesting sources. In this work we present a dataset to characterize thermal energy sources in residential settings by measuring thermoelectric generator (TEG) operating conditions over 16 deployment locations for periods ranging from 19 to 53 days. We present our easy-to-use thermal energy measurement platform built from off-the-shelf component modules and a custom TEG interface circuit. We demonstrate how the collected measurements can inform the design of energy harvesting IoT devices by deriving the TEG's maximum power output and estimating the available energy at each harvesting location.

Early identification of motion disparities in Anterior Cruciate Ligament reconstructed (ACL-R) athletes may better post-operative decision making when returning athletes to sport. Existing return to play assessments consist of assessments of muscle strength, functional tasks, patient-reported outcomes, and 3D coordinate tracking. However, these methods primarily depend on the medical provider's intuition to release them to participate in an unrestricted activity after ACL-R that may cause reinjury or long-term impacts. This study proposes a wearable sensor-based system that helps track athlete rehabilitation progress and return to sport decision making. For this, we capture gait data from 89 ACL-R athletes during their walking and jogging trials. The raw gyroscope data collected from this system is used to extract causal features based on Nolte's phase slope index. Features extracted from this study are used to develop computational models that classify ACL-R athletes based on their reconstructed knee during two visits (3-6 months9 months) post ACL-R surgery. The classifier's performance degradation in detecting ACL-R athletes injured knee during multiple visits supports athletic trainers and physicians' decision-making process to confirm an athlete's safe return to sport.Clinical Relevance- This study develops computational models based on causal analysis of gait data to support athletic trainers and medical practitioners' decision to return athletes to sport post ACL-R surgery.

Wearable and implantable technology for respiratory monitoring has created the potential for continuous collection of respiratory parameters for healthcare and other applications. However, battery life, form factor, and user burden impose practical constraints that affect user acceptance and therefore clinical utility. This work introduces a wireless self-powered sensing system for airway monitoring that uses an array of piezoelectric cantilevers that functions as both the respiratory flow sensor and the energy harvester that powers the system. The cantilevers are excited by airflow in the airway, and the harvested energy from the cantilevers is stored in a capacitor. Once a threshold energy is available in the capacitor, a load switch closes and enables a low frequency oscillator that functions as a data-less transmitter. The signal coming from the sensing system is received by an external software-defined radio (SDR), and the rate at which this signal is received is mapped to the respiratory conditions in the airway. A benchtop testing system that incorporates a lung simulator, a data acquisition system, and a hot wire anemometer was created to validate the sensor. Results show that the signal reception rate is affected by the breathing rate and volume, demonstrating the potential for a self-powered, miniaturized, passive implantable device for continuous respiratory health monitoring.

Dementia caregiver burden associated with patient agitation is one of the most common reasons for the institutionalization of a person with dementia. We developed an integrative sensing, analytics, modeling, and intervention system that detects early signs of agitation and notifies the caregiver to intervene before escalation.

Family relationships influence eating behavior and health outcomes (e.g., obesity). Because eating is often habitual (i.e., automatically driven by external cues), unconscious behavioral mimicry may be a key interpersonal influence mechanism for eating within families. This pilot study extends existing literature on eating mimicry by examining whether multiple family members mimicked each other's bites during natural meals. Thirty-three participants from 10 families were videotaped while eating an unstructured family meal in a kitchen lab setting. Videotapes were coded for participants' bite occurrences and times. We tested whether the likelihood of a participant taking a bite increased when s/he was externally cued by a family eating partner who had recently taken a bite (i.e., bite mimicry). A paired-sample t-test indicated that participants had a significantly faster eating rate within the 5 s following a bite by their eating partner, compared to their bite rate at other times (t = 7.32, p < .0001). Nonparametric permutation testing identified five of 78 dyads in which there was significant evidence of eating mimicry; and 19 of 78 dyads that had p values < .1. This pilot study provides preliminary evidence that suggests eating mimicry may occur among a subset of family members, and that there may be types of family ties more prone to this type of interpersonal influence during meals.

In-home monitoring applications often need strong and reliable contextual information to be of value. Indoor location tracking can play an important role in providing this context. However, most current indoor tracking solutions require extensive, application-specific knowledge and pre-deployment preparation, often including detailed information about floorplans and RF signal strength calibration, which is not practical in many deployments. This paper introduces an edge-based location monitoring technique that uses doorway sensors to detect doorway crossing events with walking directions. The approach is designed to provides room-level tracking. Users movement from a wearable device is used in conjunction with the edge-monitored approach to track multiple people. This method also enables the tracked location and doorway crossing events to be transformed into states and state transitions, respectively. This provides an opportunity to implement stochastic models to the edge-based location tracking to correct tracking errors and improve its accuracy, as demonstrated in simulation. This location tracking method has been implemented and deployed in a health monitoring study on dementia-related agitation.

BACKGROUND Caregiver burden associated with dementia-related agitation is one of the most common reasons for a community-dwelling person living with dementia to transition to a care facility. The Behavioral and Environmental Sensing and Intervention (BESI) for the Dementia Caregiver Empowerment system uses sensing technology, smartwatches, tablets, and data analytics to detect and predict agitation in persons living with dementia and to provide just-in-time notifications and dyad-specific intervention recommendations to caregivers. The BESI system has shown that there is a valid relationship between dementia-related agitation and environmental factors and that caregivers prefer a home-based monitoring system. OBJECTIVE The aim of this study is to obtain input from caregivers of persons living with dementia on the value, usability, and acceptability of the BESI system in the home setting and obtain their insights and recommendations for the next stage of system development. METHODS A descriptive qualitative design with thematic analysis was used to analyze 10 semistructured interviews with caregivers. The interviews comprised 16 questions, with an 80% (128/160) response rate. RESULTS Postdeployment caregiver feedback about the BESI system and the overall experience were generally positive. Caregivers acknowledged the acceptability of the system by noting the ease of use and saw the system as a fit for them. Functionality issues such as timeliness in agitation notification and simplicity in the selection of agitation descriptors on the tablet interface were identified, and caregivers indicated a desire for more word options to describe agitation behaviors. Agitation intervention suggestions were well received by the caregivers, and the resulting decrease in the number and severity of agitation events helped confirm that the BESI system has good value and acceptability. Thematic analysis suggested several subjective experiences and yielded the themes of usefulness and helpfulness. CONCLUSIONS This study determined preferences for assessing caregiver strain and burden, explored caregiver acceptance of the technology system (in-home sensors, actigraph or smart watch technology, and tablet devices), discerned caregiver insights on the burden and stress of caring for persons living with dementia experiencing agitation in dementia, and solicited caregiver input and recommendations for system changes. The themes of usefulness and helpfulness support the use of caregiver knowledge and experience to inform further development of the technology.

Background Caregiver burden associated with dementia-related agitation is one of the most common reasons for a community-dwelling person living with dementia to transition to a care facility. The Behavioral and Environmental Sensing and Intervention (BESI) for the Dementia Caregiver Empowerment system uses sensing technology, smartwatches, tablets, and data analytics to detect and predict agitation in persons living with dementia and to provide just-in-time notifications and dyad-specific intervention recommendations to caregivers. The BESI system has shown that there is a valid relationship between dementia-related agitation and environmental factors and that caregivers prefer a home-based monitoring system. Objective The aim of this study is to obtain input from caregivers of persons living with dementia on the value, usability, and acceptability of the BESI system in the home setting and obtain their insights and recommendations for the next stage of system development. Methods A descriptive qualitative design with thematic analysis was used to analyze 10 semistructured interviews with caregivers. The interviews comprised 16 questions, with an 80% (128/160) response rate. Results Postdeployment caregiver feedback about the BESI system and the overall experience were generally positive. Caregivers acknowledged the acceptability of the system by noting the ease of use and saw the system as a fit for them. Functionality issues such as timeliness in agitation notification and simplicity in the selection of agitation descriptors on the tablet interface were identified, and caregivers indicated a desire for more word options to describe agitation behaviors. Agitation intervention suggestions were well received by the caregivers, and the resulting decrease in the number and severity of agitation events helped confirm that the BESI system has good value and acceptability. Thematic analysis suggested several subjective experiences and yielded the themes of usefulness and helpfulness. Conclusions This study determined preferences for assessing caregiver strain and burden, explored caregiver acceptance of the technology system (in-home sensors, actigraph or smart watch technology, and tablet devices), discerned caregiver insights on the burden and stress of caring for persons living with dementia experiencing agitation in dementia, and solicited caregiver input and recommendations for system changes. The themes of usefulness and helpfulness support the use of caregiver knowledge and experience to inform further development of the technology.

Background The field of dietary assessment has a long history, marked by both controversies and advances. Emerging technologies may be a potential solution to address the limitations of self-report dietary assessment methods. The Monitoring and Modeling Family Eating Dynamics (M2FED) study uses wrist-worn smartwatches to automatically detect real-time eating activity in the field. The ecological momentary assessment (EMA) methodology was also used to confirm whether eating occurred (ie, ground truth) and to measure other contextual information, including positive and negative affect, hunger, satiety, mindful eating, and social context. Objective This study aims to report on participant compliance (feasibility) to the 2 distinct EMA protocols of the M2FED study (hourly time-triggered and eating event–triggered assessments) and on the performance (validity) of the smartwatch algorithm in automatically detecting eating events in a family-based study. Methods In all, 20 families (58 participants) participated in the 2-week, observational, M2FED study. All participants wore a smartwatch on their dominant hand and responded to time-triggered and eating event–triggered mobile questionnaires via EMA while at home. Compliance to EMA was calculated overall, for hourly time-triggered mobile questionnaires, and for eating event–triggered mobile questionnaires. The predictors of compliance were determined using a logistic regression model. The number of true and false positive eating events was calculated, as well as the precision of the smartwatch algorithm. The Mann-Whitney U test, Kruskal-Wallis test, and Spearman rank correlation were used to determine whether there were differences in the detection of eating events by participant age, gender, family role, and height. Results The overall compliance rate across the 20 deployments was 89.26% (3723/4171) for all EMAs, 89.7% (3328/3710) for time-triggered EMAs, and 85.7% (395/461) for eating event–triggered EMAs. Time of day (afternoon odds ratio [OR] 0.60, 95% CI 0.42-0.85; evening OR 0.53, 95% CI 0.38-0.74) and whether other family members had also answered an EMA (OR 2.07, 95% CI 1.66-2.58) were significant predictors of compliance to time-triggered EMAs. Weekend status (OR 2.40, 95% CI 1.25-4.91) and deployment day (OR 0.92, 95% CI 0.86-0.97) were significant predictors of compliance to eating event–triggered EMAs. Participants confirmed that 76.5% (302/395) of the detected events were true eating events (ie, true positives), and the precision was 0.77. The proportion of correctly detected eating events did not significantly differ by participant age, gender, family role, or height (P>.05). Conclusions This study demonstrates that EMA is a feasible tool to collect ground-truth eating activity and thus evaluate the performance of wearable sensors in the field. The combination of a wrist-worn smartwatch to automatically detect eating and a mobile device to capture ground-truth eating activity offers key advantages for the user and makes mobile health technologies more accessible to nonengineering behavioral researchers.

BACKGROUND The field of dietary assessment has a long history, marked by both controversies and advances. Emerging technologies may be a potential solution to address the limitations of self-report dietary assessment methods. The Monitoring and Modeling Family Eating Dynamics (M2FED) study uses wrist-worn smartwatches to automatically detect real-time eating activity in the field. The ecological momentary assessment (EMA) methodology was also used to confirm whether eating occurred (ie, ground truth) and to measure other contextual information, including positive and negative affect, hunger, satiety, mindful eating, and social context. OBJECTIVE This study aims to report on participant compliance (feasibility) to the 2 distinct EMA protocols of the M2FED study (hourly time-triggered and eating event–triggered assessments) and on the performance (validity) of the smartwatch algorithm in automatically detecting eating events in a family-based study. METHODS In all, 20 families (58 participants) participated in the 2-week, observational, M2FED study. All participants wore a smartwatch on their dominant hand and responded to time-triggered and eating event–triggered mobile questionnaires via EMA while at home. Compliance to EMA was calculated overall, for hourly time-triggered mobile questionnaires, and for eating event–triggered mobile questionnaires. The predictors of compliance were determined using a logistic regression model. The number of true and false positive eating events was calculated, as well as the precision of the smartwatch algorithm. The Mann-Whitney U test, Kruskal-Wallis test, and Spearman rank correlation were used to determine whether there were differences in the detection of eating events by participant age, gender, family role, and height. RESULTS The overall compliance rate across the 20 deployments was 89.26% (3723/4171) for all EMAs, 89.7% (3328/3710) for time-triggered EMAs, and 85.7% (395/461) for eating event–triggered EMAs. Time of day (afternoon odds ratio [OR] 0.60, 95% CI 0.42-0.85; evening OR 0.53, 95% CI 0.38-0.74) and whether other family members had also answered an EMA (OR 2.07, 95% CI 1.66-2.58) were significant predictors of compliance to time-triggered EMAs. Weekend status (OR 2.40, 95% CI 1.25-4.91) and deployment day (OR 0.92, 95% CI 0.86-0.97) were significant predictors of compliance to eating event–triggered EMAs. Participants confirmed that 76.5% (302/395) of the detected events were true eating events (ie, true positives), and the precision was 0.77. The proportion of correctly detected eating events did not significantly differ by participant age, gender, family role, or height (P>.05). CONCLUSIONS This study demonstrates that EMA is a feasible tool to collect ground-truth eating activity and thus evaluate the performance of wearable sensors in the field. The combination of a wrist-worn smartwatch to automatically detect eating and a mobile device to capture ground-truth eating activity offers key advantages for the user and makes mobile health technologies more accessible to nonengineering behavioral researchers.

Breathing rate (BR), minute ventilation (VE), and other respiratory parameters are essential for real-time patient monitoring in many acute health conditions, such as asthma. The clinical standard for measuring respiration, namely Spirometry, is hardly suitable for continuous use. Wearables can track many physiological signals, like ECG and motion, yet not respiration. Deriving respiration from other modalities has become an area of active research. In this work, we infer respiratory parameters from wearable ECG and wrist motion signals. We propose a modular and generalizable classification-regression pipeline to utilize available context information, such as physical activity, in learning context-conditioned inference models. Morphological and power domain novel features from the wearable ECG are extracted to use with these models. Exploratory feature selection methods are incorporated in this pipeline to discover application-specific interpretable biomarkers. Using data from 15 subjects, we evaluate two implementations of the proposed pipeline: for inferring BR and VE. Each implementation compares generalized linear model, random forest, support vector machine, Gaussian process regression, and neighborhood component analysis as contextual regression models. Permutation, regularization, and relevance determination methods are used to rank the ECG features to identify robust ECG biomarkers across models and activities. This work demonstrates the potential of wearable sensors not only in continuous monitoring, but also in designing biomarker-driven preventive measures., Comment: 10 pages, 10 figures

BACKGROUND Inadequately managed pain is a serious problem for patients with cancer and those who care for them. Smart health systems can help with remote symptom monitoring and management, but they must be designed with meaningful end-user input. OBJECTIVE This study aims to understand the experience of managing cancer pain at home from the perspective of both patients and family caregivers to inform design of the Behavioral and Environmental Sensing and Intervention for Cancer (BESI-C) smart health system. METHODS This was a descriptive pilot study using a multimethod approach. Dyads of patients with cancer and difficult pain and their primary family caregivers were recruited from an outpatient oncology clinic. The participant interviews consisted of (1) open-ended questions to explore the overall experience of cancer pain at home, (2) ranking of variables on a Likert-type scale (0, no impact; 5, most impact) that may influence cancer pain at home, and (3) feedback regarding BESI-C system prototypes. Qualitative data were analyzed using a descriptive approach to identity patterns and key themes. Quantitative data were analyzed using SPSS; basic descriptive statistics and independent sample t tests were run. RESULTS Our sample (n=22; 10 patient-caregiver dyads and 2 patients) uniformly described the experience of managing cancer pain at home as stressful and difficult. Key themes included (1) unpredictability of pain episodes; (2) impact of pain on daily life, especially the negative impact on sleep, activity, and social interactions; and (3) concerns regarding medications. Overall, taking pain medication was rated as the category with the highest impact on a patient’s pain (=4.79), followed by the categories of wellness (=3.60; sleep quality and quantity, physical activity, mood and oral intake) and interaction (=2.69; busyness of home, social or interpersonal interactions, physical closeness or proximity to others, and emotional closeness and connection to others). The category related to environmental factors (temperature, humidity, noise, and light) was rated with the lowest overall impact (=2.51). Patients and family caregivers expressed receptivity to the concept of BESI-C and reported a preference for using a wearable sensor (smart watch) to capture data related to the abrupt onset of difficult cancer pain. CONCLUSIONS Smart health systems to support cancer pain management should (1) account for the experience of both the patient and the caregiver, (2) prioritize passive monitoring of physiological and environmental variables to reduce burden, and (3) include functionality that can monitor and track medication intake and efficacy; wellness variables, such as sleep quality and quantity, physical activity, mood, and oral intake; and levels of social interaction and engagement. Systems must consider privacy and data sharing concerns and incorporate feasible strategies to capture and characterize rapid-onset symptoms.

Background An estimated 60%-90% of patients with cancer experience moderate to severe pain. Poorly managed cancer pain negatively affects the quality of life for both patients and their family caregivers and can be a particularly challenging symptom to manage at home. Mobile and wireless technology (“Smart Health”) has significant potential to support patients with cancer and their family caregivers and empower them to safely and effectively manage cancer pain. Objective This study will deploy a package of sensing technologies, known as Behavioral and Environmental Sensing and Intervention for Cancer (BESI-C), and evaluate its feasibility and acceptability among patients with cancer-family caregiver dyads. Our primary aims are to explore the ability of BESI-C to reliably measure and describe variables relevant to cancer pain in the home setting and to better understand the dyadic effect of pain between patients and family caregivers. A secondary objective is to explore how to best share collected data among key stakeholders (patients, caregivers, and health care providers). Methods This descriptive two-year pilot study will include dyads of patients with advanced cancer and their primary family caregivers recruited from an academic medical center outpatient palliative care clinic. Physiological (eg, heart rate, activity) and room-level environmental variables (ambient temperature, humidity, barometric pressure, light, and noise) will be continuously monitored and collected. Behavioral and experiential variables will be actively collected when the caregiver or patient interacts with the custom BESI-C app on their respective smart watch to mark and describe pain events and answer brief, daily ecological momentary assessment surveys. Preliminary analysis will explore the ability of the sensing modalities to infer and detect pain events. Feasibility will be assessed by logistic barriers related to in-home deployment, technical failures related to data capture and fidelity, smart watch wearability issues, and patient recruitment and attrition rates. Acceptability will be measured by dyad perceptions and receptivity to BESI-C through a brief, structured interview and surveys conducted at deployment completion. We will also review summaries of dyad data with participants and health care providers to seek their input regarding data display and content. Results Recruitment began in July 2019 and is in progress. We anticipate the preliminary results to be available by summer 2021. Conclusions BESI-C has significant potential to monitor and predict pain while concurrently enhancing communication, self-efficacy, safety, and quality of life for patients and family caregivers coping with serious illness such as cancer. This exploratory research offers a novel approach to deliver personalized symptom management strategies, improve patient and caregiver outcomes, and reduce disparities in access to pain management and palliative care services. International Registered Report Identifier (IRRID) DERR1-10.2196/16178

Gait impairment in Multiple Sclerosis (MS) can result from muscle weakness, physical fatigue, lack of coordination, and other symptoms. Walking speed, as measured by a number of clinician-administered walking tests, is the primary measure of gait impairment used by clinical researchers, but inertial gait features from body-worn sensors have been proven to add clinical value. This paper seeks to understand and differentiate the physiological significance of four such features with proven value in MS to facilitate adoption by clinical researchers and incorporation in gait monitoring and analysis systems. In addition, this information can be used to select features which might be appropriate in other forms of disability. Two of the four features are computed using the dynamic time warping (DTW) algorithm: the “DTW Score” is based on the usual DTW distance, and the “Warp Score” is based on the warping length. The third feature, based on kernel density estimation (KDE), is the “KDE Peak” value. Finally, the “Causality Index” is based on the phase slope index between inertial signals from different body parts. Relationships between these measures and the aforementioned gait-related symptoms are determined by applying factor analysis to three common, clinical walking outcomes, then correlating the inertial measures as well as walking speed to each extracted factor. Statistically significant differences in correlation coefficients to the three extracted clinical factors support their distinct physiological meaning and suggest they may have complimentary roles in the analysis of MS-related walking disability.

Background Habitual physical activity (HPA) measurement addresses the impact of MS on real-world walking, yet its interpretation is confounded by the competing influences of MS-associated walking capacity and physical activity behaviors. Objective To develop specific measures of MS-associated walking capacity through statistically sophisticated HPA analysis, thereby more precisely defining the real-world impact of disease. Methods Eighty-eight MS and 38 control subjects completed timed walks and patient-reported outcomes in clinic, then wore an accelerometer for 7 days. HPA was analyzed with several new statistics, including the maximum step rate (MSR) and habitual walking step rate (HWSR), along with conventional methods, including average daily steps. HPA statistics were validated using clinical walking outcomes. Results The six-minute walk (6MW) step rate correlated most strongly with MSR (r = 0.863, p Conclusions Conventional HPA statistics are poor measures of capacity due to variability in activity behaviors. The MSR and HWSR are valid, specific measures of real-world capacity which capture subjects’ highest step rate and preferred step rate, respectively.

Energy harvesting is a promising solution to the limited battery lifetimes of body sensor nodes. Self-powered sensor systems capable of quasi-perpetual operation enable the possibility of truly continuous monitoring of patients beyond the clinic. However, the discontinuous and dynamic characteristics of harvesting in real-world scenarios-and their implications for the design and operation of self-powered systems-are not yet well understood. This paper presents a mobile energy harvesting and data collection (EHDC) platform designed to provide a deeper understanding of energy harvesting dynamics. The EHDC platform monitors and records the instantaneous usable power generated by body-worn harvesters, while also collecting human activity and environmental data to provide a comprehensive real-world evaluation of two energy harvesting modalities common to body sensor networks: solar and thermoelectric. The platform was initially validated with benchtop tests and later with real-world deployments on two subjects. 7-h-long multimodal energy harvesting profiles were generated, and the environmental and behavioral data were used to expand upon previously developed Kalman filter based mathematical models for energy harvesting prediction. Results confirm the validity of the EHDC platform and harvesting models, establishing the potential for longer term monitoring of energy harvesting characteristics; thus, informing the design and operation of self-powered body sensor networks.

Relying on solar energy alone to power water monitoring stations limits the ability to monitor water resources in low-light locations, such as for streams with dense tree canopy cover. To address this limitation, water monitoring stations could have a supplementary micro hydro-turbine to harvest kinetic energy from streamflow. To explore this possibility, we simulated the energy harvesting potential at 42 locations with long term stream velocity records and determined the canopy cover for streams across the contiguous United States (CONUS). Results show that a site with typical streamflow velocity and dense evergreen tree canopy would have 1.6 times less sample loss, from 68% to 43%, after adding hydro energy harvesters. Many streams across the CONUS with dense canopy cover could benefit from this, especially headwater streams and streams in the Southeastern US where many watersheds have more than 50% of their stream length under dense tree canopy cover.

Distant emotion recognition (DER) extends the application of speech emotion recognition to the very challenging situation that is determined by variable speaker to microphone distances. The performance of conventional emotion recognition systems degrades dramatically as soon as the microphone is moved away from the mouth of the speaker. This is due to a broad variety of effects such as background noise, feature distortion with distance, overlapping speech from other speakers, and reverberation. This paper presents a novel solution for DER, addressing the key challenges by identification and deletion of features from consideration which are significantly distorted by distance, creating a novel, called Emo2vec, feature modeling and overlapping speech filtering technique, and the use of an LSTM classifier to capture the temporal dynamics of speech states found in emotions. A comprehensive evaluation is conducted on two acted datasets (with artificially generated distance effect) as well as on a new emotional dataset of spontaneous family discussions with audio recorded from multiple microphones placed in different distances. Our solution achieves an average 91.6%, 90.1% and 89.5% accuracy for emotion happy, angry and sad, respectively, across various distances which is more than a 16% increase on average in accuracy compared to the best baseline method.

Wearable systems have become popular in recent years, especially in health sensing applications where they enable long-term monitoring of patients. However, the majority of these devices are powered by batteries and regularly need to be recharged, creating not only issues of user compliance but also the potential for missing critical sensing events. Energy harvesting presents a promising solution to extend the lifetime of the batteries or even completely replace them for continuous self-powered operation. Thermoelectric generators (TEGs) provide the potential for self-powered wearables by harvesting the heat generated by the human body. However, environmental dynamics and human behavior - specifically airflow around the TEG - affects the harvestable energy, resulting in a highly dynamic energy source that can affect the potential for self-powered operation. In this project, we designed a wearable data collection platform that records environmental and behavioral data with a concentration on airflow around the wrist. This platform collects traces based on real-world environmental and behavioral dynamics, enabling exploration of energy harvesting dynamics and the potential for TEG-powered wearable applications.

BACKGROUND An estimated 60%-90% of patients with cancer experience moderate to severe pain. Poorly managed cancer pain negatively affects the quality of life for both patients and their family caregivers and can be a particularly challenging symptom to manage at home. Mobile and wireless technology (“Smart Health”) has significant potential to support patients with cancer and their family caregivers and empower them to safely and effectively manage cancer pain. OBJECTIVE This study will deploy a package of sensing technologies, known as Behavioral and Environmental Sensing and Intervention for Cancer (BESI-C), and evaluate its feasibility and acceptability among patients with cancer-family caregiver dyads. Our primary aims are to explore the ability of BESI-C to reliably measure and describe variables relevant to cancer pain in the home setting and to better understand the dyadic effect of pain between patients and family caregivers. A secondary objective is to explore how to best share collected data among key stakeholders (patients, caregivers, and health care providers). METHODS This descriptive two-year pilot study will include dyads of patients with advanced cancer and their primary family caregivers recruited from an academic medical center outpatient palliative care clinic. Physiological (eg, heart rate, activity) and room-level environmental variables (ambient temperature, humidity, barometric pressure, light, and noise) will be continuously monitored and collected. Behavioral and experiential variables will be actively collected when the caregiver or patient interacts with the custom BESI-C app on their respective smart watch to mark and describe pain events and answer brief, daily ecological momentary assessment surveys. Preliminary analysis will explore the ability of the sensing modalities to infer and detect pain events. Feasibility will be assessed by logistic barriers related to in-home deployment, technical failures related to data capture and fidelity, smart watch wearability issues, and patient recruitment and attrition rates. Acceptability will be measured by dyad perceptions and receptivity to BESI-C through a brief, structured interview and surveys conducted at deployment completion. We will also review summaries of dyad data with participants and health care providers to seek their input regarding data display and content. RESULTS Recruitment began in July 2019 and is in progress. We anticipate the preliminary results to be available by summer 2021. CONCLUSIONS BESI-C has significant potential to monitor and predict pain while concurrently enhancing communication, self-efficacy, safety, and quality of life for patients and family caregivers coping with serious illness such as cancer. This exploratory research offers a novel approach to deliver personalized symptom management strategies, improve patient and caregiver outcomes, and reduce disparities in access to pain management and palliative care services. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/16178

The ability to detect subtle changes in movement patterns is the most important step towards early and accurate detection of aberrant movement patterns that lead to Anterior Cruciate Ligament (ACL) reinjury which is a common and costly disease resulting in surgical reconstruction and rehabilitation costs well over $3 billion annually. Various types of commercially available wearable motion sensors have been used to assess gait and mobility characteristics in patients performing activities that resemble the demand for sports and in native sport environments. However, the question of to what extent the sensor data could be used to develop predictive models and aid in treatment decision making that may improve care in patients with an ACL injury. Therefore, this paper explores the influences of cross-validation strategies (e.g., record-wise, subject-wise) in developing machine learning models to predict the attributes of an ACL injury that play a significant role in clinical decision-making process including gender, left and right involved limbs, and comparison between patients and healthy controls. Six machine learning models were developed to examine the influences and experimental results demonstrated the performance of the models varied depending on the cross-validation methods and revealed practical implications for clinical decision-making process regarding ACL injury.

Exposure to air pollutants poses major health risk for patients with chronic pulmonary diseases such as asthma, bronchitis, and emphysema. Such risk can be mitigated by continuous exposure tracking. The effective dose of exposure is directly proportional to the respiratory minute volume, aka minute ventilation (VE). Till date, the clinical standard for measuring VE is Spirometry, a highly invasive and cumbersome modality, which is not suitable for continuous day-to-day use. This paper presents a novel non-invasive method toward continuous assessment of VE using a wrist-mount wearable motion sensor. Data from 25 healthy subjects were collected while they performed ambulatory and sedentary activities and physical exercises. Noise and artifacts of the motion signal are removed and the processed signal is used to extract explanatory features. The features are used to train and evaluate multiple regression models, among which, the probabilistic Gaussian process regression achieves the best performance in inferring VE from the wearable motion signal. The effects of inter- and intra-personal variations are explored to demonstrate the potential of the proposed method for continuously monitoring pollutant exposure risk in respiratory health applications.

Agitation in persons with dementia (PWD) poses major health risks both for themselves and for their caregivers. Passive sensing based continuous behavior tracking can prevent the escalation of such episodes. But, predicting such behavior from sensor streams, especially in real-world residential settings, is still an active area of research. Major challenges include the sparsity, unpredictability, and variations in such behavior, as well as the "weak" annotations from real-world participants. This paper proposes a novel approach to overcome these issues in predicting agitation episodes from the PWD's wrist motion data. In a transdisciplinary study on dementia dyads residing in their homes, the PWD motion is continuously sensed from their smart watch inertial sensors, while agitation episodes are actively marked by the caregivers. The data from 10 residential deployments, each with 30 days duration, are analyzed in this paper, and multiple-instance learning (MIL) based models are implemented to learn from such sparse and weakly annotated data. These models are compared with single-instance models in predicting the agitated behavior. The results show the potential of MIL models in sparsely labeled behavior inference from wearables in-the-wild.

With the advancement of wearable sensor technology, the use of inertial body sensors in the field of Medicine and Healthcare has increased drastically. Researchers have found that gait data is useful for identifying various motion impairments. Current research in gait analysis is incorporating the features extracted from video data, which is hard to analyze and requires expensive video capture equipment to collect data in slow motion. In this study, we utilized the ability of inertial body sensors to capture gait features of individuals with Anterior Cruciate Ligament (ACL) injury. This study also leverages the causality-based approach to find the coordination between different features of gait data. Gait data during walking, jogging, and running was collected from 131 subjects in which 109 have ACL injury. We then utilized this data to incorporate the gait assessment technique, which uses causality analysis to predict various classes of subjects based on health condition, impacted limb, and impacted limb based on gender. Performance metrics of various machine learning (ML) algorithms were compared to observe the best performing algorithm and used it to evaluate the confidence of individual subjects prediction that aids personalized classification.

Continuous assessment of air pollutant exposure is vital for patients with chronic pulmonary diseases such as asthma, bronchitis, and emphysema. The effective dose of such exposure is directly proportional to the minute ventilation, aka respiratory minute volume (V E ). Spirometry – still the clinical standard for measuring V E – is highly invasive and not suitable for continuous use in most applications. This paper presents a novel non-invasive method toward continuous assessment of VE using a chest-mount wearable ECG sensor. Data are collected from 25 healthy subjects while performing ambulatory and sedentary activities and physical exercises. The ECG signal is processed to overcome challenges associated with baseline drifting, noisy skin contact, and motion artifacts, and to extract robust and explanatory ECG features. These features are used to train and evaluate multiple regression models, among which, the Gaussian process regression models achieve the lowest error in both learning and inferring V E from the wearable ECG signal. The impacts of inter- and intrapersonal variations on the model performance are shown to reveal the potential of the proposed method for continuous monitoring of pollutant exposure risk in respiratory health applications.

After decades of evolution, measuring instruments for quantitative gait analysis have become an important clinical tool for assessing pathologies manifested by gait abnormalities. However, such instruments tend to be expensive and require expert operation and maintenance besides their high cost, thus limiting them to only a small number of specialized centers. Consequently, gait analysis in most clinics today still relies on observation-based assessment. Recent advances in wearable sensors, especially inertial body sensors, have opened up a promising future for gait analysis. Not only can these sensors be more easily adopted in clinical diagnosis and treatment procedures than their current counterparts, but they can also monitor gait continuously outside clinics - hence providing seamless patient analysis from clinics to free-living environments. The purpose of this paper is to provide a systematic review of current techniques for quantitative gait analysis and to propose key metrics for evaluating both existing and emerging methods for qualifying the gait features extracted from wearable sensors. It aims to highlight key advances in this rapidly evolving research field and outline potential future directions for both research and clinical applications.

Walking ability can be degraded by a number of pathologies, including movement disorders, stroke, and injury. Personal activity tracking devices gather inertial data needed to measure walking quality, but the required algorithmic methods are an active area of study. To detect changes in walking ability, the similarity between a person's current gait cycles and their known baseline gait cycles may be measured on an ongoing basis. This strategy requires a similarity measure robust to variability encountered in an outpatient scenario, including changes in walking surface, walking speed, and sensor orientation. Here we propose rotation, scale, and offset invariant dynamic time warping (RSOI-DTW), a variant of the well-known dynamic time warping (DTW) algorithm, as a generalization of DTW appropriate for three-dimensional inertial data. RSOI-DTW is invariant under rotation, scaling, and offset, yet it preserves the salient features of gait cycles required for gait monitoring. To support this claim, gait cycles from 21 subjects walking with four different styles were compared using both DTW and RSOI-DTW. The data show that RSOI-DTW converges quickly and achieves rotation, scale, and offset invariance. Both algorithms distinguish persons and detect abnormal walking, but only RSOI-DTW does so in the presence of sensor rotation. Variations in walking speed pose a challenge for both algorithms, but performance is improved by collecting baseline information at a variety of speeds.

The six-minute walk (6MW) is a common walking outcome in multiple sclerosis (MS) thought to measure fatigability in addition to overall walking disability. However, direct evidence of 6MW induced gait deterioration is limited by the difficulty of measuring qualitative changes in walking.This study aims to (1) define and validate a measure of fatigue-related gait deterioration based on data from body-worn sensors; and (2) use this measure to detect gait deterioration induced by the 6MW.Gait deterioration was assessed using the Warp Score, a measure of similarity between gait cycles based on dynamic time warping (DTW). Cycles from later minutes were compared to baseline cycles in 89 subjects with MS and 29 controls. Correlation, corrected (partial) correlation, and linear regression were used to quantify relationships to walking and fatigue outcomes.Warp Scores rose between minute 3 and minute 6 in subjects with mild and moderate disability (p0.001). Statistically significant correlations (p0.001) to the MS walking scale (MSWS-12), modified fatigue impact scale (MFIS) physical subscale, and cerebellar and pyramidal functional system scores (FSS) were observed even after controlling for walking speed. Regression of MSWS-12 scores on Warp Scores and walking speed explained 73.9% of response variance. Correlations to individual MSWS-12 and MFIS items strongly suggest a relationship to fatigability.The Warp Score has been validated in MS subjects as an objective measure of fatigue-related gait deterioration. Progressive changes to gait cycles induced by the 6MW often appeared in later minutes, supporting the importance of sustained walking in clinical assessment.

Inertial body sensors have emerged in recent years as an effective tool for evaluating mobility impairment resulting from various diseases, disorders, and injuries. For example, body sensors have been used in 6-min walk (6 MW) tests for multiple sclerosis (MS) patients to identify gait features useful in the study, diagnosis, and tracking of the disease. However, most studies to date have focused on features localized to the lower or upper extremities and do not provide a holistic assessment of mobility. This paper presents a causality analysis method focused on the coordination between extremities to identify subtle whole-body mobility impairment that may aid disease diagnosis. This method was developed for and utilized in an MS pilot study with 41 subjects (28 persons with MS (PwMS) and 13 healthy controls) performing 6 MW tests. Compared with existing methods, the causality analysis provided better discrimination between healthy controls and PwMS and a deeper understanding of MS disease impact on mobility.

Human motion has been reported as having great relevance to various disease, disorder, injuries and emotional state. Therefore, motion assessment using inertial body sensor networks (BSNs) is gaining popularity as an outcome measure in clinical study and neuroscience research. The efficacy of motion assessment heavily relies on the accurate temporal clustering of human motion into actions on various time scales. However, two human factors in real-world deployments of inertial BSNs make such motion assessment challenging: mounting errors (where sensor displacement and orientation do not match what is assumed by processing algorithms) and insecure mounting (where sensors are loosely worn causing them to shake during operations). In order to enhance the robustness of human actions clutsering from real-world BSN data, this work leverages dynamical systems modeling with the considerations of human factors. By proposing a computational body-model framework called the piecewise linear dynamical model (PLDM), we derive a robust method to segment time series data of inertial BSNs in real-world deployment with human factors into motion primitives and actions. We test the proposed method on three different inertial BSN datasets, extract actions on different temporal scales and recognize the actions into clusters. The experimental results demonstrate the effectiveness of our approach.