Validity of Wrist-Wearable Activity Devices for Estimating Physical Activity in Adolescents: Comparative Study

Comparison of Physical Activity Measured by Self-Reported Physical Activity and Wearable Device Xiaomi MI2 Band in Preadolescent School Children - A Pilot Cross-Sectional Study

The purpose of this study is to compare physical activity measured by the wearable device Xiaomi Mi2 Band and self-reported physical activity by YPAQ in preadolescent school children. A pilot cross-sectional study was performed on a subsample (5%=n=60) of preadolescent children within a parallel-group feasibility intervention trial (n=1000). All children aged 9-11 years enrolled in the schools were included in the study and children with any physical disability were excluded. Self-reported physical activity was recorded through the modified version of the Youth Physical Activity Questionnaire (YPAQ) and automatic physical activity was measured by the Xiaomi Mi2 band over 7 days. Data from the Xiaomi Mi2 band was synchronized with its mobile application from where data was transferred to an excel sheet. Data on 7-day total physical activity in minutes and 7-day total step count were recorded by the Xiaomi Mi2 band. Student's t-tests were used to determine whether significant differences were present between self-reported physical activity and by Xiaomi Mi2 band. A Bland-Altman method was also used to assess the degree of agreement between the two methods of measuring physical activity. Mean ± SD age of the children was 9.6 (± 1.0) years and 31 (51.7 %) were boys. The mean ± SD time spent in physical activity reported by YPAQ was 457.5 (± 136) minutes and by the Xiaomi Mi2 band was 594.7 (± 183) minutes. The Bland-Altman plot identified a mean bias between the methods (YPAQ and Xiaomi Mi2 band) of -157.6 (95% CI: 296.3, -611.0) minutes of 7-day physical activity. Physical activity measured by a wearable device, the Xiaomi Mi2 band can give overestimated values of physical activity compared to self-reported physical activity in preadolescent school children. However, when PA is measured through step counts by the Xiaomi Mi2 band converted to minutes, it is comparable to PA measured by YPAQ.

Incorporating Wearable Technology for Enhanced Rehabilitation Monitoring after Hip and Knee Replacement

Osteoarthritis (OA) poses a growing challenge for the aging population, especially in the hip and knee joints, contributing significantly to disability and societal costs. Exploring the integration of wearable technology, this study addresses the limitations of traditional rehabilitation assessments in capturing real-world experiences and dynamic variations. Specifically, it focuses on continuously monitoring physical activity in hip and knee OA patients using automated unsupervised evaluations within the rehabilitation process. We analyzed data from 1144 patients who used a mobile health application after surgery; the activity data were collected using the Garmin Vivofit 4. Several parameters, such as the total number of steps per day, the peak 6-minute consecutive cadence (P6MC) and peak 1-minute cadence (P1M), were computed and analyzed on a daily basis. The results indicated that cadence-based measurements can effectively, and earlier, differ among patients with hip and knee conditions, as well as in the recovery process. Comparisons based on recovery status and type of surgery reveal distinctive trajectories, emphasizing the effectiveness of P6MC and P1M in detecting variations earlier than total steps per day. Furthermore, cadence-based measurements showed a lower inter-day variability (40%) compared to the total number of steps per day (80%). Automated assessments, including P1M and P6MC, offer nuanced insights into the patients' dynamic activity profiles.

Promoting child and adolescent health through wearable technology: A systematic review

Background

Wearable technology is used in healthcare to monitor the health of individuals. This study presents an updated systematic literature review of the use of wearable technology in promoting child and adolescent health, accompanied by recommendations for future research.

Methods

This review focuses on studies involving children and adolescents aged between 2 and 18 years, regardless of their health condition or disabilities. Studies that were published from 2016 to 2024, and which met the inclusion criteria, were extracted from four academic databases (i.e. PubMed, Cochrane, Embase, and Web of Science) using the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) protocol. Data on intervention purposes, interventions deployed, intervention duration, measurements, and the main outcomes of the studies were collected.

Results

A total of 53 studies involving 14,852 participants were reviewed. They focused on various aspects, including the ownership and use of wearable devices (n = 3), the feasibility (n = 22), effectiveness (n = 4), and adherence (n = 2) of intervention strategies, or a combination of multiple aspects (n = 22). Among the interventions deployed, Fitbit was the most frequently used, featuring in 26 studies, followed by ActiGraph (n = 11). In intervention studies, the majority of studies focused on pre-morbidity prevention (n = 26) and the treatment of illnesses (n = 20), with limited attention given to postoperative monitoring (n = 4).

Conclusions

The use of wearable technology by children and adolescents has proven to be both feasible and effective for health promotion. This systematic review summarizes existing research by exploring the use of wearable technology in promoting health across diverse youth populations, including healthy and unhealthy individuals. It examines health promotion at various stages of the disease continuum, including pre-disease prevention, in-disease treatment, and postoperative monitoring. Additionally, the review provides directions for future research.

Tracking of Systemic Lupus Erythematosus (SLE) Longitudinally Using Biosensor and Patient-Reported Data: A Report on the Fully Decentralized Mobile Study to Measure and Predict Lupus Disease Activity Using Digital Signals-The OASIS Study

(1) Objective: Systemic lupus erythematosus (SLE) is a complex disease involving immune dysregulation, episodic flares, and poor quality of life (QOL). For a decentralized digital study of SLE patients, machine learning was used to assess patient-reported outcomes (PROs), QOL, and biometric data for predicting possible disease flares. (2) Methods: Participants were recruited from the LupusCorner online community. Adults self-reporting an SLE diagnosis were consented and given a mobile application to record patient profile (PP), PRO, and QOL metrics, and enlisted participants received smartwatches for digital biometric monitoring. The resulting data were profiled using feature selection and classification algorithms. (3) Results: 550 participants completed digital surveys, 144 (26%) agreed to wear smartwatches, and medical records (MRs) were obtained for 68. Mining of PP, PRO, QOL, and biometric data yielded a 26-feature model for classifying participants according to MR-identified disease flare risk. ROC curves significantly distinguished true from false positives (ten-fold cross-validation: p < 0.00023; five-fold: p < 0.00022). A 25-feature Bayesian model enabled time-variant prediction of participant-reported possible flares (P(true) > 0.85, p < 0.001; P(nonflare) > 0.83, p < 0.0001). (4) Conclusions: Regular profiling of patient well-being and biometric activity may support proactive screening for circumstances warranting clinical assessment.

Microfluidic Wearable Devices for Sports Applications

This study aimed to systematically review the application and research progress of flexible microfluidic wearable devices in the field of sports. The research team thoroughly investigated the use of life signal-monitoring technology for flexible wearable devices in the domain of sports. In addition, the classification of applications, the current status, and the developmental trends of similar products and equipment were evaluated. Scholars expect the provision of valuable references and guidance for related research and the development of the sports industry. The use of microfluidic detection for collecting biomarkers can mitigate the impact of sweat on movements that are common in sports and can also address the issue of discomfort after prolonged use. Flexible wearable gadgets are normally utilized to monitor athletic performance, rehabilitation, and training. Nevertheless, the research and development of such devices is limited, mostly catering to professional athletes. Devices for those who are inexperienced in sports and disabled populations are lacking. Conclusions: Upgrading microfluidic chip technology can lead to accurate and safe sports monitoring. Moreover, the development of multi-functional and multi-site devices can provide technical support to athletes during their training and competitions while also fostering technological innovation in the field of sports science.

Validation of an accelerometer system for measuring physical activity and sedentary behavior in healthy children and adolescents

The study aims to assess the concurrent validity of the SENS motion® accelerometer system for device-based measurement of physical activity and sedentary behavior in healthy children and adolescents. Thirty-six healthy children and adolescents (mean ± standard deviation (SD) age, 10.2 ± 2.3 years) were fitted with three SENS sensors while performing standardized activities including walking, fast walking, sitting/lying, and arm movements. Data from the sensors were compared with video observations (reference criteria). The agreement between SENS motion® and observation was analyzed using Student's t-test and illustrated in Bland-Altman plots. The concurrent validity was further evaluated using intraclass correlation coefficient (ICC) and was expressed as standard error of measurement (SEM) and minimal detectable change (MDC). Strong agreement was found between SENS and observation for walking time, sedentary time, and lying time. In contrast, moderate agreement was observed for number of steps, sitting time, and time with and without arm movement. ICC2.1 values were overall moderate to excellent (0.5-0.94), with correspondingly low SEM% for walking time, sedentary time, lying time, and time with arm movement (2-9%). An acceptable SEM% level was reached for both steps and sitting time (11% and 12%). For fast walking time, the results showed a weak agreement between the measurement methods, and the ICC value was poor.

CONCLUSION

SENS motion® seems valid for detecting physical activity and sedentary behavior in healthy children and adolescents with strong agreement and moderate to excellent ICC values. Furthermore, the explorative results on arm movements seem promising.

WHAT IS KNOWN

• Inactivity and sedentary behavior follow an increasing trend among children and adolescents. • SENS motion® seems to be valid for measuring physical activity and sedentary behavior in adults and elderly patients.

WHAT IS NEW

• SENS motion® seems valid with strong agreement between video observations and SENS measurement, and ICC values are moderate to excellent when measuring physical activity and sedentary behavior in healthy children and adolescents. • SENS motion® seems promising for detection of arm movements.

Strategies to Improve Physical Activity and Nutrition Behaviours in Children and Adolescents: A Review

Despite widespread acknowledgement of the multifarious health benefits of physical activity (PA), including prevention and control of obesity, an overwhelming majority of children and adolescents are not sufficiently active to realise such benefits. Concurrently, young people are significantly impacted by the rapid global rise of sedentarism, and suboptimal dietary patterns during key phases of development. Regrettably, the cumulative effects of unhealthy behaviours during the growing years predisposes young people to the early stages of several chronic conditions, including obesity. Clear and consistent approaches are urgently needed to improve eating and activity behaviours of children and adolescents. Based on existing evidence of "best bets" to prevent and control obesity and its comorbidities, we present a set of non-negotiable strategies as a 'road map' to achieving prevention and improving the health of children and adolescents.

Validity of the Xiaomi Mi Band 2, 3, 4 and 5 Wristbands for Assessing Physical Activity in 12-to-18-Year-Old Adolescents under Unstructured Free-Living Conditions. Fit-Person Study

The purpose was to assess the validity of four generations of Xiaomi Mi Band wristbands for the assessment of step count and physical activity (PA) levels among adolescents aged 12-18 years under free-living conditions. One hundred adolescents were invited to participate in the present study. The final sample consisted of 62 high-school students (34 females), aged 12-18 years old (Mage = 14.1 ± 1.6 years), who wore an ActiGraph accelerometer on their hip (PA and step count reference measures) and four activity wristbands (Xiaomi Mi Band 2, 3, 4, and 5) on their non-dominant wrist during the waking time of one day. Results showed that the agreement between daily PA levels (i.e., slow, brisk, and slow-brisk pace walking, total PA and moderate-to-vigorous PA) measured by Xiaomi Mi Band wristbands and the accelerometer were poor (ICC, 95% CI = 0.06-0.78, 0.00-0.92; MAPE = 50.1-150.6%). However, agreement between daily step count measured by the accelerometer and the Xiaomi Mi Band wristbands were between acceptable (MAPE = 12.2-13.6%) to excellent (ICC, 95% CI = 0.94-0.95, 0.90-0.97). Furthermore, the Xiaomi Mi Band wristbands have a good to excellent validity for correctly classifying adolescents as meeting or not meeting the recommended 10,000 steps per day (P = 0.89-0.95, k = 0.71-0.87) and the recommended 60 minutes of moderate-to-vigorous PA per day (P = 0.89-0.94, k = 0.69-0.83). Furthermore, comparability between the four Xiaomi Mi Band generations were poor to excellent (ICC, 95% CI = 0.22-0.99, 0.00-1.00) for the daily PA levels outputs, although it was excellent (ICC, 95% CI = 0.99-1.00, 0.96-1.00; MAPE = 0.0-0.1%) for daily step count. Different models of Xiaomi Mi Band wristbands were comparable and presented good validity for measuring adolescents' step count, and they accurately classified adolescents as meeting or not meeting the PA recommendations under free-living conditions.

Agreement between Fitbit and ActiGraph Estimates of Physical Activity in Young Children

Physical activity (PA) estimates from the Fitbit Flex 2 were compared to those from the ActiGraph GT9X Link in 123 elementary school children. Steps and intensity-specific estimates of PA and 3-month PA change were calculated using two different ActiGraph cut-points (Evenson and Romanzini). Fitbit estimates were 35% higher for steps compared to the ActiGraph. Fitbit and ActiGraph intensity-specific estimates were closest for sedentary and light PA while estimates of moderate and vigorous PA varied substantially depending upon the ActiGraph cut-points used. Spearman correlations between device estimates were higher for steps (rs=.70) than for moderate (rs =.54 to .55) or vigorous (rs =.29 to .48) PA. There was low concordance between devices in assessing PA changes over time. Agreement between Fitbit Flex 2 and ActiGraph estimates may depend upon the cut-points used to classify PA intensity. However, there is fair to good agreement between devices in ranking children's steps and MVPA.

Are Wrist-Worn Activity Trackers and Mobile Applications Valid for Assessing Physical Activity in High School Students? Wearfit Study

The purpose was to examine the validity of three wrist-worn commercial activity trackers (Samsung Galaxy Watch Active 2, Apple Watch Series 5, and Xiaomi Mi Band 5) and six mobile apps (Pedometer and Pacer for android and iPhone mobiles, Google Fit for android, and Apple Health for iPhone mobiles) for estimating high school students' steps and physical activity (PA) under free-living conditions. A sample of 56 (27 females; mean age = 14.7 years) and 51 (25 females; mean age = 14.0 years) high school students participated in Study 1 and 2, respectively. Study 1: Students performed a 200-meter course in four different conditions while wearing the wearables. Step counting through a video record was used as the golden standard. Study 2: Students wore the three wrist-worn commercial activity trackers during the waking time of one day, considering ActiGraph model wGT3X-BT accelerometers as a standard of reference. Afterward, the agreement between the PA scores measured by the commercial activity trackers and the video (study 1) or accelerometers (study 2) were calculated as follows: Equivalence test, Limits of Agreement (LOA); Mean Absolute Error (MAE); Mean Absolute Percentage Error (MAPE); and Intraclass Correlation Coefficient (ICC). Results showed that all the wearables presented excellent validity for assessing steps in structured free-living conditions (study 1; MAPE &lt; 5%), although their validity was between poor-excellent based on ICC (95% confidence interval) values (ICC = 0.56-1.00). Regarding Study 2, the Xiaomi wristband and the Samsung Watch presented acceptable-excellent (MAPE = 9.4-11.4%; ICC = 0.91-0.97) validity for assessing steps under unstructured free-living conditions (study 2). However, the Apple Watch presented questionable-excellent validity (MAPE = 18.0%; ICC = 0.69-0.95). Regarding moderate-to-vigorous PA (MVPA) and total PA, only the Apple Watch showed low-acceptable validity for MAPE value and questionable-excellent validity for the ICC values for MVPA assessment (MAPE = 22.6; ICC = 0.67-0.93). All wearables checked in this study have shown adequate validity results in order to assess steps in both structured and unstructured free-living conditions for both continuous and dichotomous variables. Moreover, for assessing MVPA, only the Apple Watch reported valid results for compliance or non-compliance with the daily PA recommendations. However, the results showed low validity for total PA and MVPA as continuous variables. In conclusion, depending on the user's/researcher's aim and context, one or another wearable activity tracker could be more adequate, mainly because of its valid measurements and its costs.

Nutrition-Related Mobile Application for Daily Dietary Self-Monitoring

Nutrition apps for mobile devices such as smartphones are becoming more widely available. They can help ease the arduous chore of documenting intake for nutritional assessment and self-monitoring. This allows people to control food intake, support their participation in physical activities, and promote a healthy lifestyle. However, there remains a lack of research regarding systematic analysis mapping studies in this area. The objective of this study is to identify dietary self-monitoring implementation strategies on a mobile application. This study analyzed 205 journals from the Scopus database using the descriptive-analytic method. The records used in this exploration study were those released between 2007 and 2021 that were collected based on the keywords “dietary self-monitoring,” or “nutrition application,” or “nutrition apps,” and “calorie application.” Data analysis was conducted using the VOSviewer and NVivo software analytical tools. The results show that research studies on dietary self-monitoring increased in 2017. Results also indicated that the country that contributed the most to this topic was China. The study on mobile applications for dietary self-monitoring revealed seven clusters of dominant themes: attitude to improved dietary behaviors, parameters for disease diagnosis, noncommunicable diseases, methods, nutrition algorithms, mobile health applications, and body mass index. This study also analyzed research trends by year. The current research trends are about dietary self-monitoring using a mobile application that can upgrade people's lifestyles, enable real-time meal recording and the convenience of automatically calculating the calorie content of foods consumed, and potentially improve the delivery of health behavior modification interventions to large groups of people. The researchers summarized the recent advances in dietary self-monitoring research to shed light on their research frontier, trends, and hot topics through bibliometric analysis and network visualization. These findings may provide valuable guidance for future research and perspectives in this rapidly developing field.

Personalized Metabolic Avatar: A Data Driven Model of Metabolism for Weight Variation Forecasting and Diet Plan Evaluation

Development of predictive computational models of metabolism through mechanistic models is complex and resource demanding, and their personalization remains challenging. Data-driven models of human metabolism would constitute a reliable, fast, and continuously updating model for predictive analytics. Wearable devices, such as smart bands and impedance balances, allow the real time and remote monitoring of physiological parameters, providing for a flux of data carrying information on user metabolism. Here, we developed a data-driven model of end-user metabolism, the Personalized Metabolic Avatar (PMA), to estimate its personalized reactions to diets. PMA consists of a gated recurrent unit (GRU) deep learning model trained to forecast personalized weight variations according to macronutrient composition and daily energy balance. The model can perform simulations and evaluation of diet plans, allowing the definition of tailored goals for achieving ideal weight. This approach can provide the correct clues to empower citizens with scientific knowledge, augmenting their self-awareness with the aim to achieve long-lasting results in pursuing a healthy lifestyle.

Pre-sleep Protein Supplementation Affects Energy Metabolism and Appetite in Sedentary Healthy Adults

Purpose

To assess the acute effect of pre-sleep protein supplementation combined with resistance exercise on energy metabolism (including 24-h total energy expenditure (TEE), sleep energy expenditure (SEE), basal energy expenditure (BEE), glycolipid oxidation, and appetite of sedentary adults.

Methods

A total of thirty-one sedentary participants completed this randomized, double-blind, crossover study. Participants completed the following 24-h experimental conditions in random order in the Human Calorimeter chamber: (1) 40-g protein supplementation with dinner before a nighttime resistance exercise, and followed by pre-sleep placebo intake (PRO-PLA); (2) placebo intake with dinner before a nighttime resistance exercise, and followed by pre-sleep 40-g protein supplementation (PLA-PRO); and (3) placebo supplementation both with dinner and pre-sleep combined with a nighttime resistance exercise (PLA). Subjective appetite score before breakfast the next day was evaluated using the visual analog scale.

Results

The SEE values were significantly higher by a mean of 21.7 kcal and 33.3 kcal in PRO-PLA (318.3 ± 44.3 kcal) and PLA-PRO (329.9 ± 45.2 kcal), respectively, than in PLA (296.6 ± 46.6 kcal). In addition, the SEE values for PLA-PRO was also significantly higher by 11.6 kcal than that for PRO-PLA. Further, the fullness the next morning was significantly higher by 30.8% in PLA-PRO (43.9 ± 23.5 mm) than in PLA (33.5 ± 26.6 mm). These effects remained after adjustment for 24-h energy intake.

Conclusion

Pre-sleep protein supplementation combined with resistance exercise can significantly increase the SEE and fullness in the next morning, indicating a possible strategy to improve sleep energy metabolism in the sedentary population.

The Effectiveness of Wearable Devices as Physical Activity Interventions for Preventing and Treating Obesity in Children and Adolescents: Systematic Review and Meta-analysis

Background

The prevalence of obesity in children and adolescents remains a global public health issue. Wearable devices may offer new opportunities for prevention and intervention in obesity. Previous systematic reviews have only examined the effect of the wearable device interventions on preventing and treating obesity in adults. However, no systematic review has provided an evaluation of wearable devices as physical activity interventions for preventing and treating obesity in children and adolescents.

Objective

The purpose of this review and meta-analysis was to evaluate the effectiveness of wearable devices as physical activity interventions on obesity-related anthropometric outcomes in children and adolescents.

Methods

Research articles retrieved from PubMed, EMBASE, Cochrane Library, Scopus, and EBSCO from inception to February 1, 2021, were reviewed. The search was designed to identify studies utilizing wearable devices for preventing and treating obesity in children and adolescents. The included studies were evaluated for risk of bias following the Cochrane recommendation. Meta-analyses were conducted to evaluate the effectiveness of wearable devices as physical activity interventions on body weight, body fat, BMI z-score (BMI-Z), BMI, and waist circumference. Subgroup analyses were performed to determine whether the characteristics of the interventions had an impact on the effect size.

Results

A total of 12 randomized controlled trials (3227 participants) were selected for meta-analysis. Compared with the control group, wearable device interventions had statistically significant beneficial effects on BMI (mean difference [MD] –0.23; 95% CI –0.43 to –0.03; P=.03; I²=2%), BMI-Z (MD –0.07; 95% CI –0.13 to –0.01; P=.01; I²=81%), body weight (MD –1.08; 95% CI –2.16 to –0.00; P=.05; I²=58%), and body fat (MD –0.72; 95% CI –1.19 to –0.25; P=.003; I²=5%). However, no statistically significant effect was found on waist circumference (MD 0.55; 95% CI –0.21 to 1.32; P=.16; I²=0%). The subgroup analysis showed that for participants with overweight or obesity (MD –0.75; 95% CI –1.18 to –0.31; P<.01; I²=0%), in the short-term (MD –0.62; 95% CI –1.03 to –0.21; P<.01; I²=0%), wearable-based interventions (MD –0.56; 95% CI –0.95 to –0.18; P<.01; I²=0%) generally resulted in greater intervention effect size on BMI.

Conclusions

Evidence from this meta-analysis shows that wearable devices as physical activity interventions may be useful for preventing and treating obesity in children and adolescents. Future research is needed to identify the most effective physical activity indicators of wearable devices to prevent and treat obesity in children and adolescents.

Personalized Self-Monitoring of Energy Balance through Integration in a Web-Application of Dietary, Anthropometric, and Physical Activity Data

Self-monitoring of weight, diet and physical activity is a valuable component of behavioral weight loss treatment. The validation and user-friendliness of this approach is not optimal since users are selected from homogeneous pools and rely on different applications, increasing the burden and achieving partial, generic and/or unrelated information about their metabolic state. Moreover, studies establishing type, time, duration, and adherence criteria for self-monitoring are lacking. In this study, we developed a digital web-based application (ArmOnIA), which integrates dietary, anthropometric, and physical activity data and provides a personalized estimation of energy balance. Moreover, we determined type, time, duration, and adherence criteria for self-monitoring to achieve significant weight loss in a highly heterogeneous group. A single-arm, uncontrolled prospective study on self-monitored voluntary adults for 7 months was performed. Hierarchical clustering of adherence parameters yielded three behavioral approaches: high (HA), low (LA), and medium (MA) adherence. Average BMI decrease is statistically significant between LA and HA. Moreover, we defined thresholds for the minimum frequencies and duration of dietary and weight self-monitoring. This approach can provide the correct clues to empower citizens with scientific knowledge, augmenting their self-awareness with the aim of achieving long-lasting results when pursuing a healthy lifestyle.

Wristbands in Home-Based Rehabilitation-Validation of Heart Rate Measurement

The possibility of using a smartwatch as a rehabilitation tool to monitor patients’ heart rates during exercise has gained the attention of many researchers. This study aimed to evaluate the accuracy and precision of the HR measurement performed by two wrist monitors: the Fitbit Charge 4 and the Xiaomi Mi Band 5. Thirty-one healthy volunteers were asked to perform a stress test on a treadmill. Their heart rates were recorded simultaneously by the wristbands and an electrocardiogram (ECG) at 1 min intervals. The mean absolute error percentage (MAPE), Lin’s concordance correlation coefficient (LCCC), and Bland–Altman analysis were calculated to compare the precision and accuracy of heart rate measurements. The estimated validation criteria were MAPE < 10% and LCCC < 0.8. The overall MAPE and LCCC of the Fitbit were 10.19% (±11.79%) and 0.753 (95% CI: 0.717–0.785), respectively. The MAPE and LCCC of the Xiaomi were 6.89% (±9.75) and 0.903 (0.886–0.917), respectively. The precision and accuracy of both devices decreased with the increased exercise intensity. The accuracy of wearable wrist-worn heart rate monitors varies and depends on the intensity of training. Therefore, the decision to use such a device as a heart rate monitor during in-home rehabilitation should be made with caution.

Physical activity analysis for the elderly person in free-living conditions

A growing amount of people are beginning to monitor themselves with the rapid emergence of a wide variety of cost-effective personal sensing instruments. To measure different facets of personal life, innovation helps people better understand their lifestyles, enhance their work quality, or maximize various health factors, allowing free-living. Although vast amounts of raw information on the provisioning and physiological parameters have been obtained much more straightforward, making use of all the information remains a significant task. The article introduces the Physical Activity Analysis Framework (PAAF) for the Elderly Person in Free-Living Conditions. In the framework, the acceleration signals split into overlapped windows and derive information in each frame’s frequency domain. The framework’s sensors sense the activity and evaluate a profound learning structure dependent on each window’s progressive networks. The proposed IoT model has multiple layers separately connected with each sensor, and the critical element integrates the outputs of all sensors for the classification of physical activity. In longer cycles, the model combines the window decision with a substantial increase in its efficiency. The model in the research has been evaluated using labelled free-living pilot data. Eventually, discover the use of the proposed models from a broader lifestyle intervention analysis in unlabeled, free-living data. The results show that the proposed model performs well for both labelled and unlabeled data. The experimental analyses of an older person in living conditions with their daily activities to be monitored via IoT system as Meditation effect analysis ratio is 86.6%, Physical activity ratio is 87.12%, Physical disability ratio is 87.1%, Exercise satisfaction ratio is 85.05%, and Self-efficacy ratio is 93.5%.