Search

We present WearMoCap, an open-source library to track the human pose from smartwatch sensor data and leveraging pose predictions for ubiquitous robot control. WearMoCap operates in three modes: 1) a Watch Only mode, which uses a smartwatch only, 2) a novel Upper Arm mode, which utilizes the smartphone strapped onto the upper arm and 3) a Pocket mode, which determines body orientation from a smartphone in any pocket. We evaluate all modes on large-scale datasets consisting of recordings from up to 8 human subjects using a range of consumer-grade devices. Further, we discuss real-robot applications of underlying works and evaluate WearMoCap in handover and teleoperation tasks, resulting in performances that are within 2 cm of the accuracy of the gold-standard motion capture system. Our Upper Arm mode provides the most accurate wrist position estimates with a Root Mean Squared prediction error of 6.79 cm. To evaluate WearMoCap in more scenarios and investigate strategies to mitigate sensor drift, we publish the WearMoCap system with thorough documentation as open source. The system is designed to foster future research in smartwatch-based motion capture for robotics applications where ubiquity matters. www.github.com/wearable-motion-capture. [ABSTRACT FROM AUTHOR]

In the medical field, there are several very different movement disorders, such as tremors, Parkinson's disease, or Huntington's disease. A wide range of motor and non-motor symptoms characterizes them. It is evident that in the modern era, the use of smart wrist devices, such as smartwatches, wristbands, and smart bracelets is spreading among all categories of people. This diffusion is justified by the limited costs, ease of use, and less invasiveness (and consequently greater acceptability) than other types of sensors used for health status monitoring. This systematic review aims to synthesize research studies using smart wrist devices for a specific class of movement disorders. Following PRISMA-S guidelines, 130 studies were selected and analyzed. For each selected study, information is provided relating to the smartwatch/wristband/bracelet model used (whether it is commercial or not), the number of end-users involved in the experimentation stage, and finally the characteristics of the benchmark dataset possibly used for testing. Moreover, some articles also reported the type of raw data extracted from the smart wrist device, the implemented designed algorithmic pipeline, and the data classification methodology. It turned out that most of the studies have been published in the last ten years, showing a growing interest in the scientific community. The selected articles mainly investigate the relationship between smart wrist devices and Parkinson's disease. Epilepsy and seizure detection are also research topics of interest, while there are few papers analyzing gait disorders, Huntington's Disease, ataxia, or Tourette Syndrome. However, the results of this review highlight the difficulties still present in the use of the smartwatch/wristband/bracelet for the identified categories of movement disorders, despite the advantages these technologies could bring in the dissemination of low-cost solutions usable directly within living environments and without the need for caregivers or medical personnel. [ABSTRACT FROM AUTHOR]

This paper proposes a machine learning approach to detect threats using short-term PPG (photoplethysmogram) signals from a commercial smartwatch. In supervised learning, having accurately annotated training data is essential. However, a key challenge in the threat detection problem is the uncertainty regarding how accurately data labeled as 'threat' reflect actual threat responses since participants may react differently to the same experiments. In this paper, Gaussian Mixture Models are learned to remove ambiguously labeled training, and those models are also used to remove ambiguous test data. For the realistic test scenario, PPG measurements are collected from participants playing a horror VR (Virtual Reality) game, and the proposed method validates the superiority of our proposed approach in comparison with other methods. Also, the proposed filtering with GMM improves prediction accuracy by 23% compared to the method that does not incorporate the filtering. [ABSTRACT FROM AUTHOR]

Objectives: Atrial fibrillation (AF) is a common early arrhythmia after heart valve surgery that limits physical activity. We aimed to evaluate the criterion validity of the Apple Watch Series 5 single-lead electrocardiogram (ECG) for detecting AF in patients after heart valve surgery. Design: We enrolled 105 patients from the University Hospital of North Norway, of whom 93 completed the study. All patients underwent single-lead ECG using the smartwatch three times or more daily on the second to third or third to fourth postoperative day. These results were compared with continuous 2–4 days ECG telemetry monitoring and a 12-lead ECG on the third postoperative day. Results: On comparing the Apple Watch ECGs with the ECG monitoring, the sensitivity and specificity to detect AF were 91% (75, 100) and 96% (91, 99), respectively. The accuracy was 95% (91, 99). On comparing Apple Watch ECG with a 12-lead ECG, the sensitivity was 71% (62, 100) and the specificity was 92% (92, 100). Conclusion: The Apple smartwatch single-lead ECG has high sensitivity and specificity, and might be a useful tool for detecting AF in patients after heart valve surgery. [ABSTRACT FROM AUTHOR]

Background: Smartwatches can use sensors to collect and send data to medical teams and family members through the platform of the Internet of things (IoT). The data are first analysed on the platform and the final results are used by the medical team. Aims: This paper reviews and categorises studies conducted in the field of the Internet of things based on smartwatches. Methods: The covered papers have been published over 13 years from 2010 to 2022. The search yielded 227 papers out of which 43 papers were reviewed after screening. The search keywords were “wearables, internet of things, smartwatches, smart bracelet, healthcare, and disease”. The search covered databases including PubMed, ScienceDirect, and IEEE. Results: Smartwatches are used in three fields of healthcare, including palliative care, speech therapy, diagnosis, disease prevention, rehabilitation, and health improvement. Conclusion: Smartwatches are not free of drawbacks and have not received the attention they deserve in the healthcare field. Given the potential of smartwatches, they can be useful in the health sector. Keywords: Disease, IOT, Smartwatch, Wearable

The article offers a framework called WatchLogger for keystroke detection and recognition of typed words using a smartwatch's sensors, addressing potential privacy risks associated with wearable devices. Topics include the use of audio and accelerometer signals for detecting typed words, the development of an ensemble classification model to improve word recognition accuracy, and the creation of the WTW-100 dataset for evaluating performance.

AbstractCorrectional work is associated with high levels of stress and poor sleep quality. Although previous research has primarily relied on correctional officers’ perceptions of these outcomes, biometric indicators can provide more objective and continuous information. Using daily data points collected from smartwatches worn by 15 prison staff over a six-week period with a single-subject ABA research design involving two control phases and a mindfulness activity phase, this pilot study establishes a proof of concept for using wearable biometric sensor devices to study correctional staff health and well-being. By applying longitudinal mixed effects regression models with a GAMLSS framework, this study finds that biometric measures are sensitive to change, such that stress was reduced and sleep quality improved among participants during the mindfulness activity phase. Participating staff complied with and felt positively about the research protocols. Several important lessons for advancing measurement in future correctional health and wellness research are discussed. [ABSTRACT FROM AUTHOR]

This paper proposes an outlier-robust pedestrian walking direction estimation method. The outliers caused by the unexpected behavior of pedestrians, e.g., wiping sweat, are detected by exploiting the eigenvalue characteristics of the principal components obtained by principal component analysis (PCA) on the distribution of the acceleration measurements. Once the outliers are detected, we solve a robust PCA problem with a newly defined stable principal component pursuit (SPCP) in the inertial sensor measurement domain to recover a low-rank matrix from the acceleration measurement matrix. Eventually, from this outlier-removed low-rank matrix, we estimate the correct walking direction. The performance of the proposed method was evaluated through experiments on several behaviors defined as unexpected behavior of pedestrians. In the outlier-inducing scenario, the proposed method using robust PCA via SPCP outperformed the existing methods by about 70% with a mean error of 4.83°. Furthermore, in the extended scenario, the robust PCA via SPCP outperformed the existing methods by 70–78% with a mean error of 3.50°, improving the robustness of the PCA-based walking direction estimation method. [ABSTRACT FROM AUTHOR]

Background: Obesity in childhood and adolescence represents a major public health problem, mostly attributed to dietary and physical activity factors. We aimed to determine the dietary and physical activity habits of participants before and after the implementation of a personalized, multidisciplinary, lifestyle intervention program for the management of obesity in the context of the Horizon Research Project 'BigO: Big Data against Childhood Obesity'. Methods: Three hundred and eighty-six (n = 386) children and adolescents (mean age ± SD: 12.495 ± 1.988 years, 199 males and 187 females) participated in the study prospectively. Based on body mass index (BMI), subjects were classified as having obesity (n = 293, 75.9%) and overweight (n = 93, 24.1%) according to the International Obesity Task Force (IOTF) cut-off points. We implemented a personalized, multidisciplinary, lifestyle intervention program providing guidance on diet, sleep, and exercise, and utilized the BigO technology platform to objectively record data collected via a Smartphone and Smartwatch for each patient. Results: Following the intervention, a statistically significant decrease was noted in the consumption of cheese, cereal with added sugar, savory snacks, pasta, and fried potatoes across both BMI categories. Also, there was an increase in daily water intake between meals among all participants (p = 0.001) and a reduction in the consumption of evening snack or dinner while watching television (p < 0.05). Boys showed a decrease in the consumption of savory snacks, fried potato products, and pasta (p < 0.05), an increase in the consumption of sugar-free breakfast cereal (p < 0.05), and drank more water between meals daily (p < 0.001). Conclusions: Our findings suggest that a personalized, multidisciplinary, lifestyle intervention improves the dietary habits of children and adolescents. [ABSTRACT FROM AUTHOR]

Smartwatches are wearable technologies mostly used to produce health-related data. This paper focuses on smartwatch uses in terms of surveillance mechanisms. We ask whether, in the example of smartwatch, wearable technologies used in self-regulation facilitate the self-optimization of human bodies. We refer to several scholarly works using the concepts of self-tracking culture, quantification, governance of self and self-optimization. We organize our literary and methodological sources in three dimensions to construct an operational analysis: quantified self, self-definition, and governance of the self. We conducted in-depth interviews with a total of thirteen people by using snowball sampling. The average duration of the interviews was 30 minutes. We recorded the interviews with the permission of the respondents. The most important criterion in choosing the people to be interviewed was that they had five months or more of experience using the watch since the smartwatch requires a certain amount of time to get used to it and develop a habit of use. All interviewees had university degrees and an income-generating profession, mostly white-collar. The paper argues that the smartwatch, as a tool of quantification, encourages users to monitor themselves in order to be responsible individuals for their own health. However, we also acknowledge that the use of smartwatch does not straightforwardly produce empowering or disempowering outcomes for the users. There are dualistic aspects in its use that require further sociological considerations. Although the smartwatch is a tool of monitoring, its different connotations must be understood in its specific relation to the users. [ABSTRACT FROM AUTHOR]

AbstractSmartwatches are widely used for tracking user physiological and fitness data and are efficient in health management and fitness promotion. However, smartwatch usage exhibits certain negative effects, such as anxiety and dependence. Although the presence of these negative effects has been verified, the widespread existence and degree of these effects on users are not sufficiently investigated. In this study, we explored the tracking anxiety and dependence of 509 smartwatch users based on physiological and fitness data. Our analysis results indicated that users became anxious when their physiological data were abnormal and experienced dependence when tracking sleep status, heart rate, and exercise. Furthermore, tracking anxiety and dependence influenced the smartwatch usage, even causing a few users to consider stopping its usage. Based on these results, we provide design implications for smartwatch designers to improve the user experience of tracking physiological and fitness data. [ABSTRACT FROM AUTHOR]

Presently, smartwatches are becoming increasingly popular; however, their small screen size poses challenges to visualization research, particularly specific data, for instance, fitness, sleep, and heart rate, visualizations. Previous studies represented real-time heart rates (RT-HRs) using heart rate values or heart rate values with an icon, and have made a preliminary exploration of heart rate data visualization on a smartwatch. However, which type of heart rate data users need most, how to visualize different types of heart rate data in smartwatch small screens, and how to allow users to quickly glance at their desired information have not been studied. In this study, we explore users' preferred heart rate data type and preferred visualization on a smartwatch. We found that the participants' preference scores for average heart rate and exercise intensity are higher than the scores of RT-HR and heart rate records, implying that most participants prefer interpretative data instead of raw data. In addition, participants' preference scores for visualizations were significantly different under different motivations and heart rate data types. Based on these findings, we present design implications for interface designers to better visualize specific data on a smartwatch. [ABSTRACT FROM AUTHOR]

Here, we propose an auxiliary earthquake emergency framework to facilitate a post-earthquake rapid response. Searching through the rubble of collapsed buildings is essentially a race against time, as time is highly correlated with the chances of trapped victims surviving. The framework here is centered on full GIS integration and smartwatch (SW) for transferring victims' vital data for search and rescue (SAR) operations considering the damage to the road network due to direct earthquake implications. The framework has two parts time-wise: pre- and post-earthquake. The first part assesses the initial situation under different earthquake scenarios, which calculates service areas for emergency rescue centers under different earthquake scenarios considering road blockages. Following an earthquake, the second part prioritizes victims and identifies critical rescue areas using an SW and initial assessments. The victims' accessibility, health condition, and injury risk are the criteria used to determine victims' rescue priority. The developed framework is then employed in an urban region for different earthquake scenarios. From a road blockage point of view, the critical areas are then recognized. The framework relies on GIS and SW technology for data transfer, but potential failures and challenges in post-earthquake scenarios, data availability, quality, timeliness, and ethical considerations like equity, cultural sensitivities, and privacy need to be addressed. Considering the golden rescue time, by integrating the latest technologies into management applications, the study's results can help emergency first responders make rapid and efficient decisions and better allocate medical and rescue resources just after an earthquake, reducing earthquake losses and saving more human lives. Moreover, it can provide insight into the initial road network situation following different earthquake scenarios for first responders to estimate the road network's initial situation; thus, they can operate better in real emergencies. [ABSTRACT FROM AUTHOR]

Lay people are now able to obtain one-lead electrocardiograms (ECG) using smartwatches, which facilitates documentation of arrhythmias. The accuracy of smartwatch derived ECG intervals has not been validated in children though. Home-based monitoring of ECG intervals using a smartwatch could improve monitoring of children, e.g. when taking QTc prolonging medications. The aim of this study was to validate the ECG intervals measured by smartwatch in comparison to standard 12-lead ECGs in children and adolescents. Prospective study of children (age 5—17 years) at the outpatient clinic of a national pediatric heart center. Patients underwent a smartwatch ECG (ScanWatch, Withings) and a simultaneous standard 12-lead ECG. ECG intervals were measured both automatically and manually from the smartwatch ECG and the 12-lead ECG. Intraclass correlation coefficients and Bland–Altman plots were performed. 100 patients (54% male, median age 12.9 (IQR 8.7–15.6) were enrolled. The ICC calculated from the automated smartwatch and automated 12-lead ECG were excellent for heart rate (ICC 0.97, p < 0.001), good for the PR and QT intervals (ICC 0.86 and 0.8, p < 0.001), and moderate for the QRS duration and QTc interval (ICC 0.7 and 0.53, p < 0.001). When using manual measurements for the smartwatch ECG, validity was improved for the PR interval (ICC 0.93, p < 0.001), QRS duration (ICC 0.92, p < 0.001), QT (ICC 0.95, p < 0.001) and QTc interval (ICC 0.84, p < 0.001). Conclusion: Automated smartwatch intervals are most reliable measuring the heart rate. The automated smartwatch QTc intervals are less reliable, but this may be improved by manual measurements. What is Known: In adults, smartwatch derived ECG intervals measured manually have previously been shown to be accurate, though agreement for automated QTc may be fair. What is New: In children, automated smartwatch QTc intervals are less reliable than RR, PR, QRS and uncorrected QT interval. Accuracy of the QTc can be improved by peroforming manual measurements. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic exposed the vulnerabilities of global health care systems, underscoring the need for innovative solutions to meet the demands of an aging population, workforce shortages, and rising physician burnout. In recent years, wearable technology has helped segue various medical specialties into the digital era, yet its adoption in vascular surgery remains limited. This article explores the applications of wearable devices in vascular surgery and explores their potential outlets, such as enhancing primary and secondary prevention, optimizing perioperative care, and supporting surgical training. The integration of artificial intelligence and machine learning with wearable technology further expands its applications, enabling predictive analytics, personalized care, and remote monitoring. Despite the promising prospects, challenges such as regulatory complexities, data security, and interoperability must be addressed. As the digital health movement unfolds, wearable technology could play a pivotal role in reshaping vascular surgery while offering cost-effective, accessible, and patient-centered care. [ABSTRACT FROM AUTHOR]

This work examines swipe-based interactions on smart devices, like smartphones and smartwatches, that detect vibration signals through defined swipe surfaces. We investigate how these devices, held in users' hands or worn on their wrists, process vibration signals from swipe interactions and ambient noise using a support vector machine (SVM). The work details the signal processing workflow involving filters, sliding windows, feature vectors, SVM kernels, and ambient noise management. It includes how we separate the vibration signal from a potential swipe surface and ambient noise. We explore both software and human factors influencing the signals: the former includes the computational techniques mentioned, while the latter encompasses swipe orientation, contact, and movement. Our findings show that the SVM classifies swipe surface signals with an accuracy of 69.61% when both devices are used, 97.59% with only the smartphone, and 99.79% with only the smartwatch. However, the classification accuracy drops to about 50% in field user studies simulating real-world conditions such as phone calls, typing, walking, and other undirected movements throughout the day. The decline in performance under these conditions suggests challenges in ambient noise discrimination, which this work discusses, along with potential strategies for improvement in future research. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Sportive is the property of Journal of Sportive and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

ObjectiveThis study examined the accuracy of smartwatches in predicting running performance.MethodsA total of 154 amateur runners (123 males and 31 females) were recruited. After wearing the HUAWEI WATCH GT Runner for a minimum of six weeks, the runners' actual completion times for 5 km, 10 km, and half marathon distances were measured, resulting in 288 test instances. The predicted completion times for the same distances displayed on the watch on the test day were recorded simultaneously.ResultsThe actual and predicted performances for the 5, 10, and 21.1 km distances were highly correlated, with r ≥ 0.95 (p

We present WearMoCap, an open-source library to track the human pose from smartwatch sensor data and leveraging pose predictions for ubiquitous robot control. WearMoCap operates in three modes: 1) a Watch Only mode, which uses a smartwatch only, 2) a novel Upper Arm mode, which utilizes the smartphone strapped onto the upper arm and 3) a Pocket mode, which determines body orientation from a smartphone in any pocket. We evaluate all modes on large-scale datasets consisting of recordings from up to 8 human subjects using a range of consumer-grade devices. Further, we discuss real-robot applications of underlying works and evaluate WearMoCap in handover and teleoperation tasks, resulting in performances that are within 2 cm of the accuracy of the gold-standard motion capture system. Our Upper Arm mode provides the most accurate wrist position estimates with a Root Mean Squared prediction error of 6.79 cm. To evaluate WearMoCap in more scenarios and investigate strategies to mitigate sensor drift, we publish the WearMoCap system with thorough documentation as open source. The system is designed to foster future research in smartwatch-based motion capture for robotics applications where ubiquity matters. www.github.com/wearable-motion-capture.

Advances in wearable technologies now allow modern smartwatches to collect body composition estimates through bioelectrical impedance techniques embedded within their design. However, this technique is susceptible to increased measurement error when postural changes alter body fluid distribution. The purpose of this study was to evaluate the effects of postural orientation on body composition and total body water (TBW) estimates produced by smartwatch bioelectrical impedance analysis (SWBIA) and determine its agreement with criterion measures. For this cross-sectional evaluation, 117 (age: 21.4±3.0 y; BMI: 25.3±5.7 kg/m2) participants (F:69, M:48) completed SWBIA measurements while in the seated, standing, and supine positions, then underwent criterion dual-energy X-ray absorptiometry (DXA) and bioelectrical impedance spectroscopy (BIS) assessments. In the combined sample and females, body fat percent, fat mass, and fat-free mass using SWBIA were significantly different between the supine and standing positions (all p

Self-direction skill (SDS) is an essential 21st-century skill that can help learners be independent and organized in their quest for knowledge acquisition. While some studies considered learners from higher education levels as the target audience, providing opportunities to start the SDS practice by K12 learners is still rare. Further, practicing such skills requires a concrete context and scaffolding during the skill acquisition. This article introduces the Goal Oriented Active Learner (GOAL) system that facilitates SDS acquisition in learners utilizing daily activities as context. The GOAL architecture integrates learning logs from online environments and physical activity logs from wearable trackers to provide a data-rich environment for the learners to acquire and practice their SDS. The GOAL users follow DAPER, a five-phase process model, to utilize the affordances in the system while practicing SDS. We implemented the GOAL system at a K12 public institution in Japan in 2019. Learners used the online environments for extensive reading and smartwatches for tracking walking and sleeping activities. This study analyzes detailed interaction patterns in GOAL while learners planned and monitored their self-directed actions. The results illustrate the strategies for DAPER behaviors that emerge in different activity contexts. We discuss the potentials and challenges of this technology ecosystem that connects learners’ learning logs and physical activity logs, specifically in the K12 context in Japan and, more generally, from the learning analytics research perspective to provide a context to practice SDS.

Introduction: The effect of displayed step count in smartwatches on the accuracy of daily step-count estimation and the potential underlying psychological factors have not been revealed. The study aimed for the following: (i) To investigate whether the counting and reporting of daily steps by a smartwatch increases the daily step-count estimation accuracy and (ii) to elucidating underlying psychological factors. Methods: A total of 34 healthy men and women participants wore smartwatches for 4 weeks. In week 1 (baseline), 3 (follow-up 1), and 8 (followup 2), the number of smartwatch displayed steps was blinded for each participant. In week 2 (Intervention), the number of steps was not blinded. During baseline and follow-ups 1 and 2, the participants were instructed to estimate their number of steps four times per day. During the 4-week washout period between follow-ups 1 and 2, no feedback was provided. The Body Awareness Questionnaire and the Body Responsiveness Questionnaire (BRQ) were used to elucidate the psychological facets of the assumed estimation accuracy. Results: The mean absolute percentage error between the participants' steps count estimations and measured steps counts were 29.49% (at baseline), 0.54% (intervention), 11.89% (follow-up 1), and 15.14% (follow-up 2), respectively. There was a significant effect between baseline and follow-up 1 [t (61.7) = 3.433, p < 0.001] but not between follow-up 1 and followup 2 [t (60.3) = -0.288, p = 0.774]. Only the BRQ subscale "Suppression of Bodily Sensations" appeared to be significant at the Baseline (p = 0.012; Bonferroni adjusted p = 0.048) as a factor influencing step-count estimation accuracy. Conclusion: The counting and reporting of daily steps with a smartwatch allows improving the subjective estimation accuracy of daily step counts, with a stabilizing effect for at least 6 weeks. Especially individuals who tend to suppress their bodily sensations are less accurate in their daily step-count estimation before the intervention. [ABSTRACT FROM AUTHOR]

Background: The advancements in wearable technology have made the detection of arrhythmias more accessible. While smartwatches are commonly used to detect patients with atrial fibrillation, their effectiveness in the differential diagnosis of supraventricular tachycardias (SVT) lacks consensus. Methods: A study was conducted on 47 patients with documented SVTs on a 12-lead ECG. All patients in the cohort underwent electrophysiology study with induction of SVT. A 6th generation Apple Watch was used to record ECG tracings during baseline sinus rhythm and during induced SVT. Cardiology residents and attending cardiologists evaluated these recordings to diagnose the differential diagnosis of SVT. Results: The evaluation revealed 27 cases of typical atrioventricular nodal reentrant tachycardia (AVNRT), 11 cases of atrioventricular reentrant tachycardia (AVRT), and 9 cases of atrial tachycardia/atrial flutter (AT/AFL) among the induced tachycardias. Attending physicians achieved an accuracy of 66.0 to 76.6%, and residents demonstrated accuracy rates between 68.1 and 74.5%. Interrater reliability was assessed using Fleiss's Kappa method, resulting in a moderate level of agreement between residents (Kappa = 0.465, p < 0.001, 95% CI 0.30–0.63) and attendings (Kappa = 0.519, p < 0.001, 95% CI 0.35–0.68). The overall Kappa value was 0.417 (p < 0.001, 95% CI 0.34–0.49). Conclusions: Smartwatch recordings demonstrate moderate feasibility in diagnosing SVT when following a pre-specified algorithm. However, this diagnostic performance was lower than the accuracy obtained from 12-lead ECG tracings when blinded to procedure outcomes. [ABSTRACT FROM AUTHOR]

This study introduces a fall detection system utilizing an affordable consumer smartwatch and smartphone with edge computing capabilities for implementing AI algorithms. Due to the widespread use of these devices, the system as a whole is extremely accepted, easy to use, requires no tuning of any kind, and guarantees extended functioning for a long period. From a technical standpoint, falls are identified using AI techniques to analyze 3D raw data acquired by the smartwatch's built-in accelerometer. However, existing AI models for fall detection are often trained on simulated falls involving young people, which may not accurately represent the falls of elderly in unhealthy conditions, such as arthritis or Parkinson's disease, leading to limitations in detecting falls in this population. Additionally, variations in hardware features among different smartwatches can result in inconsistencies in accelerometer data measurements across X, Y, and Z orientations, further complicating accurate fall detection. To address the challenge of limited and device-specific datasets and to enhance model generalization across various devices, a Deep Transfer Learning approach is proposed. This method proves effective when data are poor. Specifically, the Continuous Wavelet Transform (CWT) is applied to raw accelerometer signals to convert them into 2D images, enabling the use of deep architectures for Transfer Learning. By employing CWT on 5 s time windowed raw accelerometer signals, heat maps (scalograms) are generated. Real-time accelerations sampled at 50 Hz are collected using a smartwatch application, transmitted via Bluetooth to a smartphone app, and converted into scalograms. These serve as input for pre-trained Deep Learning models to estimate fall probabilities. Preliminary tests on the Wrist Early Daily Activity and Fall Dataset (WEDA-FALL) show promising results with an accuracy of approximately 98%, underscoring the efficacy of utilizing wrist-worn wearable devices for processing raw accelerometer data. [ABSTRACT FROM AUTHOR]

Wearable devices are playing an important role in our daily lives. Nowadays, wearable devices have transformative implications for health, technology, connectivity, humancomputer interaction, and data analytics. Their importance lies in their ability to enhance various aspects of life and contribute to the ongoing evolution of digital landscapes. At the heart of smartwatch design, the processor takes center stage, driving the majority of advancements in smartwatch technology. This paper presents an experimental comparative study of ARM 64-bit processors, analyzing their performance and impact on power consumption, CPU usage, and battery temperature. We evaluate the characteristics of four smartwatch processors: Snapdragon W5+, Snapdragon Wear4100, Exynos W920, and Exynos W930. All of those smartwatches are equipped with ARM 64-bit processors. Our results indicate that none of the four selected smartwatches excelled in all aspects; each exhibits superiority over the others in specific features while being surpassed by others in different attributes. [ABSTRACT FROM AUTHOR]

Self-direction skill (SDS) is an essential 21st-century skill that can help learners be independent and organized in their quest for knowledge acquisition. While some studies considered learners from higher education levels as the target audience, providing opportunities to start the SDS practice by K12 learners is still rare. Further, practicing such skills requires a concrete context and scaffolding during the skill acquisition. This article introduces the Goal Oriented Active Learner (GOAL) system that facilitates SDS acquisition in learners utilizing daily activities as context. The GOAL architecture integrates learning logs from online environments and physical activity logs from wearable trackers to provide a data-rich environment for the learners to acquire and practice their SDS. The GOAL users follow DAPER, a five-phase process model, to utilize the affordances in the system while practicing SDS. We implemented the GOAL system at a K12 public institution in Japan in 2019. Learners used the online environments for extensive reading and smartwatches for tracking walking and sleeping activities. This study analyzes detailed interaction patterns in GOAL while learners planned and monitored their self-directed actions. The results illustrate the strategies for DAPER behaviors that emerge in different activity contexts. We discuss the potentials and challenges of this technology ecosystem that connects learners' learning logs and physical activity logs, specifically in the K12 context in Japan and, more generally, from the learning analytics research perspective to provide a context to practice SDS. [ABSTRACT FROM AUTHOR]

Purpose of Review: To provide the reader with an overview of how smartwatches may be used for arrhythmia detection, diagnosis, and management. Recent Findings: Various rhythm-monitoring wearable devices are currently available in the consumer market. Studies are ongoing to evaluate the impact of smartwatches in clinical decision making and cardiovascular outcomes. Recognizing their consumer friendliness and potential for long-term rhythm monitoring, clinical practice guidelines acknowledge the utility of smartwatches in specific clinical scenarios and potential for expanded use cases in the future. Summary: Smartwatches have excellent accuracy for detection of atrial fibrillation, but are not yet validated for use in management of other types of arrhythmias. Clinician involvement is paramount to differentiate clinically relevant arrhythmias from noise and to guide management strategies such as anticoagulation when atrial fibrillation is diagnosed. Future research should be directed towards assessing the impact of smartwatches on clinical decision making and outcomes among diverse patient groups. [ABSTRACT FROM AUTHOR]

Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing interest in developing portable and personal devices for measuring air quality and surrounding pollutants, partly due to the need for ventilation in the aftermath of COVID-19 situation. Moreover, the monitoring of hazardous chemical agents is a focus for ensuring compliance with safety standards and is an indispensable component in safeguarding human welfare. Air quality measurement is conducted by public institutions with high precision but costly equipment, which requires constant calibration and maintenance by highly qualified personnel for its proper operation. Such devices, used as reference stations, have a low spatial resolution since, due to their high cost, they are usually located in a few fixed places in the city or region to be studied. However, they also have a low temporal resolution, providing few samples per hour. To overcome these drawbacks and to provide people with personalized and up-to-date air quality information, a personal device (smartwatch) based on MEMS gas sensors has been developed. The methodology followed to validate the performance of the prototype was as follows: firstly, the detection capability was tested by measuring carbon dioxide and methane at different concentrations, resulting in low detection limits; secondly, several experiments were performed to test the discrimination capability against gases such as toluene, xylene, and ethylbenzene. principal component analysis of the data showed good separation and discrimination between the gases measured. [ABSTRACT FROM AUTHOR]

Background: Elucidating the association between heart rate variability (HRV) metrics obtained through non-invasive methods and mental health symptoms could provide an accessible approach to mental health monitoring. This study explores the correlation between HRV, estimated using photoplethysmography (PPG) signals, and self-reported symptoms of depression and anxiety. Methods: A 4-week longitudinal study was conducted among 47 participants. Time–domain and frequency–domain HRV metrics were derived from PPG signals collected via smartwatches. Mental health symptoms were evaluated using the Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) at baseline, week 2, and week 4. Results: Among the investigated HRV metrics, RMSSD, SDNN, SDSD, LF, and the LF/HF ratio were significantly associated with the PHQ-9 score, although the number of significant correlations was relatively small. Furthermore, only SDNN, SDSD and LF showed significant correlations with the GAD-7 score. All HRV metrics showed negative correlations with self-reported clinical symptoms. Conclusions: Our findings indicate the potential of PPG-derived HRV metrics in monitoring mental health, thereby providing a foundation for further research. Notably, parasympathetically biased HRV metrics showed weaker correlations with depression and anxiety scores. Future studies should validate these findings in clinically diagnosed patients. [ABSTRACT FROM AUTHOR]

AbstractDespite growing interest in User Experience (UX), the empirical testing of UX models, particularly the interdependence of UX dimensions and their impact on user satisfaction, remains limited. This study fills this gap by examining a UX model for smartwatch and smartphone users through an online survey and partial least squares (PLS) regression analysis. Our findings reveal that both instrumental and non-instrumental qualities, alongside the emotions elicited by mobile devices, are interconnected and crucial to users. Notably, instrumental qualities tend to elicit negative emotions, whereas non-instrumental qualities elicit predominantly positive emotions. The observed relationships among various UX factors and user satisfaction underscore the significance of the proposed UX model and, more broadly, highlight the importance of UX research in deciphering the psychological processes encountered when individuals interact with technology. [ABSTRACT FROM AUTHOR]

Purpose: Patients undergoing radiation therapy (RT) often experience psychological anxiety that manifests as muscle contraction. Our study explored psychological anxiety in these patients by using biological signals recorded using a smartwatch. Materials and Methods: Informed consent was obtained from participating patients prior to the initiation of RT. The patients wore a smartwatch from the waiting room until the conclusion of the treatment. The smartwatch acquired data related to heart rate features (average, minimum, and maximum) and stress score features (average, minimum, and maximum). On the first day of treatment, we analyzed the participants' heart rates and stress scores before and during the treatment. The acquired data were categorized according to sex and age. For patients with more than three days of data, we observed trends in heart rate during treatment relative to heart rate before treatment (HRtb) over the course of treatment. Statistical analyses were performed using the Wilcoxon signedrank test and paired t-test. Results: Twenty-nine individuals participated in the study, of which 17 had more than 3 days of data. During treatment, all patients exhibited elevated heart rates and stress scores, particularly those in the younger groups. The HRtb levels decreased as treatment progresses. Conclusion: Patients undergoing RT experience notable psychological anxiety, which tends to diminish as the treatment progresses. Early stage interventions are crucial to alleviate patient anxiety during RT. [ABSTRACT FROM AUTHOR]

In recent years, indoor or at-home sports have experienced significant growth. However, monotony is a common challenge in these static physical activities. Exergames, a genre of video games that combines physical activity and entertainment, have emerged as an attractive solution. Nevertheless, running on a treadmill and engaging in other activities simultaneously presents additional challenges. The balance and concentration required during running while interacting with a video game demand a special focus on the design of the Exergame. This paper presents a mobile Exergame designed specifically for treadmill running, utilizing interaction with a smartwatch. The game offers natural environments where, through smartwatch technology, it interprets the player's movements, transforming them into running speed and interactive actions by detecting gestures within the game. The main objective is to provide users with a satisfying gaming experience tailored to the characteristics of treadmill running. Particular emphasis has been placed on prioritizing the playful component of this Exergame, recognizing its relevance in the context of treadmill running. To evaluate the achievement of objectives and the proposed hypothesis, a comparative study was conducted between the proposed Exergame and a treadmill running simulator. Participants experienced both experiences and subsequently completed the Game Experience Questionnaire (GEQ), specifically the In-game GEQ version. The results obtained indicate that participants had a better gaming experience in the Exergame than in the simulator. These findings highlight the importance of prioritizing the playful component in Exergames and provide guidelines for future improvements and developments in the field. [ABSTRACT FROM AUTHOR]