Health Tracking Research Articles

Health tracking media and the production of operational space: A critical analysis of Qantas Wellbeing App

This article examines the production of operational space amidst the rise of self- and data-tracking media, through the case study of the Qantas Wellbeing App. We draw on the operational paradigm in media studies to envisage how the Qantas Wellbeing App is embedded in the social-material relations between its users and the app, and the broader data-platform economy. By conceptualising the Qantas Wellbeing App as an operational media, the inquiry focuses on its designs and techniques that prompt users to fulfil prescribed tasks and follow instructions. We follow Lefebvre's conceptualisation of the production of space to evaluate three sets of social relations reconfigured by the Qantas Wellbeing App: human-to-human, human-to-machine, and data-to-data. By relying on qualitative evidence collected from an auto-ethnographic approach, our analyses focus on (1) spatial practices and (2) social relations constructed around the Qantas Wellbeing App between the authors to argue that social space is becoming a programmed reality that adheres to the logic of technological automation. Our analysis here affirms the app's capacity and objective to modify human behaviours and to evaluate how the app has recalibrated the authors’ respective and shared social spaces to create the needed condition of behaviour changes among the users. As social space is centred around human relations and activities, human agency and lives become secondary in an operational regime, which relies on data synchronisation to prosecute for the operational space and life.

Real-Life Wheelchair Mobility Metrics from IMUs.

Daily wheelchair ambulation is seen as a risk factor for shoulder problems, which are prevalent in manual wheelchair users. To examine the long-term effect of shoulder load from daily wheelchair ambulation on shoulder problems, quantification is required in real-life settings. In this study, we describe and validate a comprehensive and unobtrusive methodology to derive clinically relevant wheelchair mobility metrics (WCMMs) from inertial measurement systems (IMUs) placed on the wheelchair frame and wheel in real-life settings. The set of WCMMs includes distance covered by the wheelchair, linear velocity of the wheelchair, number and duration of pushes, number and magnitude of turns and inclination of the wheelchair when on a slope. Data are collected from ten able-bodied participants, trained in wheelchair-related activities, who followed a 40 min course over the campus. The IMU-derived WCMMs are validated against accepted reference methods such as Smartwheel and video analysis. Intraclass correlation (ICC) is applied to test the reliability of the IMU method. IMU-derived push duration appeared to be less comparable with Smartwheel estimates, as it measures the effect of all energy applied to the wheelchair (including thorax and upper extremity movements), whereas the Smartwheel only measures forces and torques applied by the hand at the rim. All other WCMMs can be reliably estimated from real-life IMU data, with small errors and high ICCs, which opens the way to further examine real-life behavior in wheelchair ambulation with respect to shoulder loading. Moreover, WCMMs can be applied to other applications, including health tracking for individual interest or in therapy settings.

Effective fall detection and post-fall breath rate tracking using a low-cost CW Doppler radar sensor

Existing low-cost Doppler radar-based fall detection systems encounter challenges due to false alarms and the absence of post-fall health tracking, significantly impacting their accuracy and overall compatibility for fall detection. This paper presents a cost-effective, robust solution for a fall detection system with the post-fall health tracking facility using a 3.18 GHz continuous-wave Doppler radar sensor. The experimental data acquisition is conducted in-house under the guidance of a healthcare expert, involving various activities such as standing, sitting, sleeping, running, walking, falling, sit-to-stand, and stand-to-sit transitions. We propose an algorithm comprising four hierarchical stages, each with specific objectives. Considering the complexity, the model is trained differently for each stage to optimize the classification accuracy. The system architecture is designed to minimize computational costs and power consumption through modular implementation in stages, utilizing low-power equipment and incorporating traditional machine-learning algorithms. Experimental results demonstrate a fall detection accuracy of 93.24% and breath rate measurement error of 2.26%, which is competitive with recent state-of-the-art approaches. Obtained results highlight the effectiveness of the proposed system in addressing the challenges of false alarms and post-fall health tracking while maintaining cost-efficiency and accuracy in fall detection.

Overage labor, value perceptions, and happiness in urban older adults’ lives: Empirical evidence from China

BackgroundOver the past four decades, China has seen a rapid increase in the level of urbanization, along with an increasing number of older adults. How to promote active aging in the midst of rapid urbanization has become a new challenge for the Chinese government and all sectors of society. This study attempts to verify the relationship between overage labor and happiness in life, and further explore the possible mediating role of multidimensional value perceptions. MethodBased on 5010 valid samples from the 2011, 2013, 2015, and 2018 China Health and Aging Tracking Survey datasets (CHARLS), the study explored and tested the differences in happiness in life between older adults with overage labor and retired older adults. In addition, this study further examined the mediating role of multidimensional value perceptions using a mediation model. Results(1) Urban older adults with overage labor had significantly higher levels of happiness in life compared to urban retired older adults. (2) The higher level of life happiness of urban older adults with overage labor depends on their perceptions of different values; (3) Specifically, the realization of value perceptions in personal, family and social dimensions through labor contributes to the life happiness of urban older adults with overage labor. ConclusionThere is a significant difference between urban old adults with overage labor and urban retired old adults in terms of happiness in life. At the same time, the study confirmed that all three aspects of value perceptions, such as personal, family and social, are the mediating mechanisms between overage labor and urban old adults in terms of happiness in life.

Is Workload Associated With Internal Impingement in Professional Baseball Pitchers? An Analysis of Days of Rest, Innings Pitched, and Batters Faced.

Internal impingement is a common cause of shoulder pain and dysfunction in baseball pitchers. The purpose of this study was to determine if the amount of rest days between outings, the number of innings pitched in each outing, and the number of batters faced in each outing are risk factors for internal impingement in professional baseball pitchers. It was hypothesized that a higher workload would significantly increase a pitcher's risk of developing internal impingement. Case-control study; Level of evidence, 3. All professional (Major and Minor League) baseball pitchers who were diagnosed with internal impingement between 2011 and 2017 were identified using the Major League Baseball's Health and Injury Tracking System. A separate player usage data set was used to determine workload. The authors compared workload variables (days of rest, innings pitched, and batters faced per game) between each of 4 injury-exposure groups (pitchers with documented internal impingement <2, <6, <12, and >12 weeks after a game) and a control group of pitchers with no internal impingement using Student t tests or Mann-Whitney U tests. In a within-pitcher paired analysis of the injury groups, the workload variables during 3 acute periods (<2, <6, and <12 weeks preinjury) were compared with the baseline values (>12 weeks preinjury). Overall, there were 624 professional baseball pitchers diagnosed with internal impingement during the study period. Compared with pitcher games (n = 213,964), pitchers in all 4 injury-exposure groups had significantly more innings pitched per game (P ≤ .003 for all) and faced significantly more batters per game (P < .001 for all). There were significantly more starting pitchers in each of the injury-exposure groups when compared with the controls (P < .001 for all). However, when comparing acute and baseline workloads in the pitchers diagnosed with internal impingement, there were no significant differences in the number of innings pitched, batters faced, or days of rest. This analysis revealed significantly greater pitcher workload and percentage of starting pitchers in professional baseball players diagnosed with internal impingement when compared with healthy controls. However, this injury did not seem to be associated with an acute increase in workload.

Recent Trends in Wearable Electronic Textiles (e-Textiles): A Mini Review

Wearable electronic textiles (e-textiles) have the ability to sense, respond, and adjust in multiple environmental stimuli, which can interact with the human brain's capability for cognition, reasoning, and activation. Moreover, they have the ability to generate and store energy, keep track of the wearer's health, and react to varying situations. Conductive polymers, metal-wrapped yarns, as well as, carbon nanotubes with silver, copper, and gold nanoparticles are used in a variety of yarn structures to design circuits, switches, and fabrics directly. Knitting, stitching, embroidery, and other integration techniques are used to combine electronic components and electrical interconnects to develop flexible electronic clothing and smart wearables. For this purpose, controlled sensors, actuators, conductive embroidered or printed fabric, planer yarn, data transfer devices, conductive inks, electromagnetic shielding, power supply, and other components are incorporated in e-textiles design. Despite the progress made so far, wearable e-textiles still, lack the required performance and device features along with the issues related to complex fabrication techniques, end-of-life processing and sustainability. Hence, this review aims to discuss the recent developments, which address the future challenges concerning electronic (e-textiles).

Meniscal Injuries Are Decreasing but Are Increasingly Being Treated Surgically With Excellent Return to Play Rates in Professional Baseball Players

The purposes of this study were to determine the incidence and key characteristics of meniscus injuries in professional baseball players, assess current treatment strategies, determine the return to play rates at any level (RTP) and at the same level (RSL), and identify prognostic factors that predict injury severity. After approval from the Major League Baseball (MLB) Research Committee and our institutional review board, the MLB Health and Injury Tracking System was used to identify meniscus injuries occurring across MLB and Minor League Baseball (MiLB) from 2011 to 2017. Analyzed injuries occurred during normal baseball activity in a player who was active on an MLB or MiLB roster and resulted in at least 1 day missed. A total of 293 professional baseball players sustained 314 meniscus injuries from 2011 to 2017 (7 years) for a mean of 44.9 injuries/y. Pitchers were the most injured position (31.8%), followed by infielders (26.4%). Catchers and infielders missed the most median number of days (50 days). When comparing injuries to landing leg vs push-off leg in pitchers, injury to the push-off leg resulted in significantly more days missed per injury compared to the lead leg (59.6 vs 39.9 days, P= .048). Overall, RTP was 93.0%, while RSL was 84.4%. Over 7 professional baseball seasons, 314 meniscus injuries occurred in 293 players. Pitchers and catchers were most injured, and overall, the number of meniscal injuries per year declined while the percentage of injuries that required surgery increased over time. High rates of RTP were observed. Level IV, therapeutic case series.

Perceived Impact of Digital Health Maturity on Patient Experience, Population Health, Health Care Costs, and Provider Experience: Mixed Methods Case Study

Background Health care organizations understand the importance of new technology implementations; however, the best strategy for implementing successful digital transformations is often unclear. Digital health maturity assessments allow providers to understand the progress made toward technology-enhanced health service delivery. Existing models have been criticized for their lack of depth and breadth because of their technology focus and neglect of meaningful outcomes. Objective We aimed to examine the perceived impacts of digital health reported by health care staff employed in health care organizations across a spectrum of digital health maturity. Methods A mixed methods case study was conducted. The digital health maturity of public health care systems (n=16) in Queensland, Australia, was examined using the quantitative Digital Health Indicator (DHI) self-assessment survey. The lower and upper quartiles of DHI scores were calculated and used to stratify sites into 3 groups. Using qualitative methods, health care staff (n=154) participated in interviews and focus groups. Transcripts were analyzed assisted by automated text-mining software. Impacts were grouped according to the digital maturity of the health care worker’s facility and mapped to the quadruple aims of health care: improved patient experience, improved population health, reduced health care cost, and enhanced provider experience. Results DHI scores ranged between 78 and 193 for the 16 health care systems. Health care systems in the high-maturity category (n=4, 25%) had a DHI score of ≥166.75 (the upper quartile); low-maturity sites (n=4, 25%) had a DHI score of ≤116.75 (the lower quartile); and intermediate-maturity sites (n=8, 50%) had a DHI score ranging from 116.75 to 166.75 (IQR). Overall, 18 perceived impacts were identified. Generally, a greater number of positive impacts were reported in health care systems of higher digital health maturity. For patient experiences, higher maturity was associated with maintaining a patient health record and tracking patient experience data, while telehealth enabled access and flexibility across all digital health maturity categories. For population health, patient journey tracking and clinical risk mitigation were reported as positive impacts at higher-maturity sites, and telehealth enabled health care access and efficiencies across all maturity categories. Limited interoperability and organizational factors (eg, strategy, policy, and vision) were universally negative impacts affecting health service delivery. For health care costs, the resource burden of ongoing investments in digital health and a sustainable skilled workforce was reported. For provider experiences, the negative impacts of poor usability and change fatigue were universal, while network and infrastructure issues were negative impacts at low-maturity sites. Conclusions This is one of the first studies to show differences in the perceived impacts of digital maturity of health care systems at scale. Higher digital health maturity was associated with more positive reported impacts, most notably in achieving outcomes for the population health aim.

Provision of Digital Health Technologies for Opioid Use Disorder Treatment by US Health Care Organizations

Digital health technologies may expand organizational capacity to treat opioid use disorder (OUD). However, it remains unclear whether these technologies serve as substitutes for or complements to traditional substance use disorder (SUD) treatment resources in health care organizations. To characterize the use of patient-facing digital health technologies for OUD by US organizations with accountable care organization (ACO) contracts. This cross-sectional study analyzed responses to the 2022 National Survey of Accountable Care Organizations (NSACO), collected between October 1, 2021, and June 30, 2022, from US organizations with Medicare and Medicaid ACO contracts. Data analysis was performed between December 15, 2022, and January 6, 2023. Treatment resources for SUD (eg, an addiction medicine specialist, sufficient staff to treat SUD, medications for OUD, a specialty SUD treatment facility, a registry to identify patients with OUD, or a registry to track mental health for patients with OUD) and organizational characteristics (eg, organization type, Medicaid ACO contract). The main outcomes included survey-reported use of 3 categories of digital health technologies for OUD: remote mental health therapy and tracking, virtual peer recovery support programs, and digital recovery support for adjuvant cognitive behavior therapy (CBT). Statistical analysis was conducted using descriptive statistics and multivariable logistic regression models. Overall, 276 of 505 organizations responded to the NSACO (54.7% response rate), with a total of 304 respondents. Of these, 161 (53.1%) were from a hospital or health system, 74 (24.2%) were from a physician- or medical group-led organization, and 23 (7.8%) were from a safety-net organization. One-third of respondents (101 [33.5%]) reported that their organization used at least 1 of the 3 digital health technology categories, including remote mental health therapy and tracking (80 [26.5%]), virtual peer recovery support programs (46 [15.1%]), and digital recovery support for adjuvant CBT (27 [9.0%]). In an adjusted analysis, organizations with an addiction medicine specialist (average marginal effect [SE], 32.3 [4.7] percentage points; P < .001) or a registry to track mental health (average marginal effect [SE], 27.2 [3.8] percentage points; P < .001) were more likely to use at least 1 category of technology compared with otherwise similar organizations lacking these capabilities. In this cross-sectional study of 276 organizations with ACO contracts, organizations used patient-facing digital health technologies for OUD as complements to available SUD treatment capabilities rather than as substitutes for unavailable resources. Future studies should examine implementation facilitators to realize the potential of emerging technologies to support organizations facing health care practitioner shortages and other barriers to OUD treatment delivery.

The impact of neighborhood mental health on the mental health of older adults

BackgroundIn this article, we use cross-sectional data obtained from the 2018 China Health and Aging Tracking Survey (CHARLS) to examine the impact of neighborhood mental health at the community level on the mental health of older adults aged 60 years and older.MethodsNMH is the average mental health of older adults in the same community, excluding the older adults themselves. The explained variable mental health in this paper was measured using the simple CES-D depression scale. The mediating variables were social connectedness, social participation and social inclusion, and the instrumental variables were physical exercise and amusement. regression analysis was conducted using OLS regression models, two-stage least squares (IV-2SLS) instrumental variables to address the two-way causality of NMH and MH, and KHB decomposition was used to investigate the effect mechanism.ResultsBaseline regressions showed that the neighborhood mental health effect positively influenced the mental health of older adults (Coef. = 0.356, 95% CI 0.315,0.397). The neighborhood mental health effect estimated by IV-2SLS (Coef. = 0.251, 95% CI 0.096,0.405) was higher than the OLS regression, indicating endogeneity. The mediated effects of KHB showed total (Coef. = 0.356, 95% CI 0.314,0.398), direct (Coef. = 0.281, 95% CI 0.232,0.330), and indirect effects (Coef. = 0.075, 95% CI 0.049,0.101). While the total effect was 1.266 times higher than the direct effect, 21.03% of the total effect came from mediating variables.ConclusionsFirst, the neighborhood mental health effect has a positive impact on the mental health of older adults, but there are heterogeneous differences based on gender, age, and place of residence. Second, the results of the IV-2SLS estimation showed that the effect of the neighborhood mental health effect was underestimated if endogenous problems were not controlled for. Third, the effect of neighborhood mental health on older adults' mental health was tested to be stable. Moreover, social connectedness, social participation, and social interaction are important mediating mechanisms for the effect of neighborhood mental health on older adults' mental health. This study provides new perspectives and ideas for an in-depth understanding of the mental health of older adults in the context of social transformation in China.

Intergenerational caregiving on mental health of middle-aged and older adults in China: empirical insights.

The impact of intergenerational caregiving on the mental health of providers remains a controversial topic, especially in countries like China where it is prevalent. Given the country's aging population and recent liberalization of the two-child policy, understanding the effects of intergenerational caregiving on the mental health of middle-aged and older adult(s) individuals is crucial. This study aimed to explore the impact of intergenerational caregiving on mental health among middle-aged and older adult(s) individuals. We analyzed data from the China Health and Aging Tracking Survey (CHARLS) 2013, consisting of 6602 participants finally. Personal information, family structure, financial support, health status, and physical measurements were selected for analysis. Correlation and regression analyses were used for relationships among variables controlling for potential confounding variables. Mental health status was evaluated using the depression self-rating scale. There is a significant positive effect of intergenerational care on the mental health of middle-aged and older adult(s) people. Additionally, we re-profiled intergenerational care variables by considering the number and length of intergenerational caregivers, and found that the effects remained significant. Furthermore, the effects of intergenerational care vary across subgroups based on gender, age, nature of usual residence, marital status, and physical health status. Finally, we identified two mechanisms through which intergenerational caregiving positively affects mental health: intergenerational financial support and intergenerational spiritual support. These findings have important implications for policymakers, healthcare professionals, and family members in promoting the mental health of middle-aged and older adult(s) individuals in China.

A Focus on Contraception in the Wake of Dobbs.

A Focus on Contraception in the Wake of Dobbs.

Health monitoring of the Veresk Bridge by comparing the results of precision instrument measurements and modelling with Abaqus software and wavelet function

Identification and classification of structural failures is a vital aspect of bridge maintenance. When local structural damage is identified without delay, its repair is less expensive and problematic than in the case of general damage. To determine seismic vulnerability or post-seismic damage, structural health assessments are frequently performed on bridges, dams, and buildings. The aim of this study is to keep track of the overall health of the Veresk Railway Bridge, which has been in service for over 90 years. For this purpose, the structure was modeled in the ABAQUS finite element software. Mode shapes of the structure were then extracted, the positions were determined as maximum points using MATLAB software, and a wavelet function was applied to these shapes. The results showed that the wavelet function is highly accurate and its results are close to the real values measured for the bridge.

The Impact of "Reverse Feedback" on Elderly Labor Participation

This article is based on the 2018 China Health and Elderly Care Tracking Survey (CHARLS) data and uses the Logit model and propensity score matching method (PSM) to estimate the impact of "reverse feeding" behavior on elderly labor participation. Research has shown that providing financial support to children by elderly parents can encourage them to enter the labor market; The behavior of intergenerational care will inhibit their entry into the labor market; Providing economic support for children is more significant for elderly individuals living alone and men, while the negative impact of intergenerational care is more significant among women and elderly people living with their children. Therefore, it is necessary to further optimize the supply and service of early childhood care resources, protect the rights and interests of women to participate in labor, and improve the elderly care security system to build a scientific and reasonable elderly employment security system.

Rapidly adaptable automated interpretation of point-of-care COVID-19 diagnostics

BackgroundPoint-of-care diagnostic devices, such as lateral-flow assays, are becoming widely used by the public. However, efforts to ensure correct assay operation and result interpretation rely on hardware that cannot be easily scaled or image processing approaches requiring large training datasets, necessitating large numbers of tests and expert labeling with validated specimens for every new test kit format.MethodsWe developed a software architecture called AutoAdapt POC that integrates automated membrane extraction, self-supervised learning, and few-shot learning to automate the interpretation of POC diagnostic tests using smartphone cameras in a scalable manner. A base model pre-trained on a single LFA kit is adapted to five different COVID-19 tests (three antigen, two antibody) using just 20 labeled images.ResultsHere we show AutoAdapt POC to yield 99% to 100% accuracy over 726 tests (350 positive, 376 negative). In a COVID-19 drive-through study with 74 untrained users self-testing, 98% found image collection easy, and the rapidly adapted models achieved classification accuracies of 100% on both COVID-19 antigen and antibody test kits. Compared with traditional visual interpretation on 105 test kit results, the algorithm correctly identified 100% of images; without a false negative as interpreted by experts. Finally, compared to a traditional convolutional neural network trained on an HIV test kit, the algorithm showed high accuracy while requiring only 1/50th of the training images.ConclusionsThe study demonstrates how rapid domain adaptation in machine learning can provide quality assurance, linkage to care, and public health tracking for untrained users across diverse POC diagnostic tests.

The Role of Pragmatic Competence in the Language Proficiency of Saudi EFL Learners

English language learning programs are always evolving to suit the needs of the changing demands of the learners. In Saudi Arabia, English programs are solely focused on achieving language proficiency through teaching learners’ vocabulary and grammar only, excluding other important language constructs such as pragmatics. This research investigates the relationship between pragmatic proficiency and language proficiency by administering an MDCT (multiple-choice discourse completion task) survey test on 80 Saudi health track students who are enrolled in King Abdul-Aziz English language institution. The test questions were adopted from Çetınavci and Öztürk’s original MDCT instrument, designed to focus on testing knowledge of implied meaning “implicatures”. The results were analyzed using SPSS to measure the correlation between pragmatic proficiency and language proficiency and observe the most difficult implicature the students found. The findings indicate that there is no linear relationship between the students’ English proficiency and their pragmatic proficiency.

Cloud-based wearable mental health tracking system with intelligent psychotherapy

In order to provide mental healthcare services to people who do not have access to professional psychiatrists, a Cloud-based Wearable Mental Health Tracking System with Intelligent Psychotherapy is introduced with four major steps: multimodal data collection from various sources, mental health issue predictions from machine learning models, intelligent VR psychotherapy to solve mental disorders, and pacification effect monitoring and feedback sending to adjust the psychotherapy methodology. The solution incorporates multiple front-end technologies including Big Data, Cloud Computing, Machine Learning, IoT, VR, and Blockchain.

Expansion of Telehealth Availability for Mental Health Care After State-Level Policy Changes From 2019 to 2022

Although telehealth services expanded rapidly during the COVID-19 pandemic, the association between state policies and telehealth availability has been insufficiently characterized. To investigate the associations between 4 state policies and telehealth availability at outpatient mental health treatment facilities throughout the US. This cohort study measured whether mental health treatment facilities offered telehealth services each quarter from April 2019 through September 2022. The sample comprised facilities with outpatient services that were not part of the US Department of Veterans Affairs system. Four state policies were identified from 4 different sources. Data were analyzed in January 2023. For each quarter, implementation of the following policies was indexed by state: (1) payment parity for telehealth services among private insurers; (2) authorization of audio-only telehealth services for Medicaid and Children's Health Insurance Program (CHIP) beneficiaries; (3) participation in the Interstate Medical Licensure Compact (IMLC), permitting psychiatrists to provide telehealth services across state lines; and (4) participation in the Psychology Interjurisdictional Compact (PSYPACT), permitting clinical psychologists to provide telehealth services across state lines. The primary outcome was the probability of a mental health treatment facility offering telehealth services in each quarter for each study year (2019-2022). Information on the facilities was obtained from the Mental Health and Addiction Treatment Tracking Repository based on the Substance Abuse and Mental Health Services Administration Behavioral Health Treatment Service Locator. Separate multivariable fixed-effects regression models were used to estimate the difference in the probability of offering telehealth services after vs before policy implementation, adjusting for characteristics of the facility and county in which the facility was located. A total of 12 828 mental health treatment facilities were included. Overall, 88.1% of facilities offered telehealth services in September 2022 compared with 39.4% of facilities in April 2019. All 4 policies were associated with increased odds of telehealth availability: payment parity for telehealth services (adjusted odds ratio [AOR], 1.11; 95% CI, 1.03-1.19), reimbursement for audio-only telehealth services (AOR, 1.73; 95% CI, 1.64-1.81), IMLC participation (AOR, 1.40, 95% CI, 1.24-1.59), and PSYPACT participation (AOR, 1.21, 95% CI, 1.12-1.31). Facilities that accepted Medicaid as a form of payment had lower odds of offering telehealth services (AOR, 0.75; 95% CI, 0.65-0.86) over the study period, as did facilities in counties with a higher proportion (>20%) of Black residents (AOR, 0.58; 95% CI, 0.50-0.68). Facilities in rural counties had higher odds of offering telehealth services (AOR, 1.67; 95% CI, 1.48-1.88). Results of this study suggest that 4 state policies that were introduced during the COVID-19 pandemic were associated with marked expansion of telehealth availability for mental health care at mental health treatment facilities throughout the US. Despite these policies, telehealth services were less likely to be offered in counties with a greater proportion of Black residents and in facilities that accepted Medicaid and CHIP.

BMAR

A requirement of cross-modal signal processing is accurate signal alignment. Though simple on a single device, accurate signal synchronization becomes challenging as soon as multiple devices are involved, such as during activity monitoring, health tracking, or motion capture---particularly outside controlled scenarios where data collection must be standalone, low-power, and support long runtimes. In this paper, we present BMAR, a novel synchronization method that operates purely based on recorded signals and is thus suitable for offline processing. BMAR needs no wireless communication between devices during runtime and does not require any specific user input, action, or behavior. BMAR operates on the data from devices worn by the same person that record barometric pressure and acceleration---inexpensive, low-power, and thus commonly included sensors in today's wearable devices. In its first stage, BMAR verifies that two recordings were acquired simultaneously and pre-aligns all data traces. In a second stage, BMAR refines the alignment using acceleration measurements while accounting for clock skew between devices. In our evaluation, three to five body-worn devices recorded signals from the wearer for up to ten hours during a series of activities. BMAR synchronized all signal recordings with a median error of 33.4 ms and reliably rejected non-overlapping signal traces. The worst-case activity was sleeping, where BMAR's second stage could not exploit motion for refinement and, thus, aligned traces with a median error of 3.06 s.

Towards Efficient Emotion Self-report Collection Using Human-AI Collaboration

Emotion-aware services are increasingly used in different applications such as gaming, mental health tracking, video conferencing, and online tutoring. The core of such services is usually a machine learning model that automatically infers its user's emotions based on different biological indicators (e.g., physiological signals and facial expressions). However, such machine learning models often require a large number of emotion annotations or ground truth labels, which are typically collected as manual self-reports by conducting long-term user studies, commonly known as Experience Sampling Method (ESM). Responding to repetitive ESM probes for self-reports is time-consuming and fatigue-inducing. The burden of repetitive self-report collection leads to users responding arbitrarily or dropping out from the studies, compromising the model performance. To counter this issue, we, in this paper, propose a Human-AI Collaborative Emotion self-report collection framework, HACE, that reduces the self-report collection effort significantly. HACE encompasses an active learner, bootstrapped with a few emotion self-reports (as seed samples), and enables the learner to query for only not-so-confident instances to retrain the learner to predict the emotion self-reports more efficiently. We evaluated the framework in a smartphone keyboard-based emotion self-report collection scenario by performing a 3-week in-the-wild study (N = 32). The evaluation of HACE on this dataset (≈11,000 typing sessions corresponding to more than 200 hours of typing data) demonstrates that it requires 46% fewer self-reports than the baselines to train the emotion self-report detection model and yet outperforms the baselines with an average self-report detection F-score of 85%. These findings demonstrate the possibility of adopting such a human-AI collaborative approach to reduce emotion self-report collection efforts.