Accelerometer Data Research Articles

Predicting physical functioning status in older adults: insights from wrist accelerometer sensors and derived digital biomarkers of physical activity.

Conventional physical activity (PA) metrics derived from wearable sensors may not capture the cumulative, transitions from sedentary to active, and multidimensional patterns of PA, limiting the ability to predict physical function impairment (PFI) in older adults. This study aims to identify unique temporal patterns and develop novel digital biomarkers from wrist accelerometer data for predicting PFI and its subtypes using explainable artificial intelligence techniques. Wrist accelerometer streaming data from 747 participants in the National Health and Aging Trends Study (NHATS) were used to calculate 231 PA features through time-series analysis techniques-Tsfresh. Predictive models for PFI and its subtypes (walking, balance, and extremity strength) were developed using 6 machine learning (ML) algorithms with hyperparameter optimization. The SHapley Additive exPlanations method was employed to interpret the ML models and rank the importance of input features. Temporal analysis revealed peak PA differences between PFI and healthy controls from 9:00 to 11:00 am. The best-performing model (Gradient boosting Tree) achieved an area under the curve score of 85.93%, accuracy of 81.52%, sensitivity of 77.03%, and specificity of 87.50% when combining wrist accelerometer streaming data (WAPAS) features with demographic data. The novel digital biomarkers, including change quantiles, Fourier transform (FFT) coefficients, and Aggregated (AGG) Linear Trend, outperformed traditional PA metrics in predicting PFI. These findings highlight the importance of capturing the multidimensional nature of PA patterns for PFI. This study investigates the potential of wrist accelerometer digital biomarkers in predicting PFI and its subtypes in older adults. Integrated PFI monitoring systems with digital biomarkers would improve the current state of remote PFI surveillance.

Interplay between physical activity volume and intensity with modeled life expectancy in women and men: A prospective cohort analysis

BackgroundThere is a lack of research examining the interplay between objectively measured physical activity volume and intensity with life expectancy. MethodsIndividuals from UK Biobank with wrist-worn accelerometer data were included. The average acceleration and intensity gradient were extracted to describe the physical activity volume and intensity profile. Mortality data were obtained from national registries. Adjusted life expectancies were estimated using parametric flexible survival models. Results40,953 (57.1%) women (median age = 61.9 years) and 30,820 (42.9%) men (63.1 years) were included. Over a median follow-up of 6.9 years, there were 1719 (2.4%) deaths (733 in women; 986 in men). At 60 years, life expectancy was progressively longer for higher physical activity volume and intensity profiles, reaching 95.6 years in women and 94.5 years in men at the 90th centile for both volume and intensity, corresponding to 3.4 (95% confidence interval (95%CI): 2.4–4.4) additional years in women and 4.6 (95%CI: 3.6–5.6) additional years in men compared to those at the 10th centiles. An additional 10-min or 30-min daily brisk walk was associated with 0.9 (95%CI: 0.5–1.3) and 1.4 (95%CI: 0.9–1.9) years longer life expectancy, respectively, in inactive women; and 1.4 (95%CI: 1.0–1.8) and 2.5 (95%CI: 1.9–3.1) years in inactive men. ConclusionHigher physical activity volumes were associated with longer life expectancy, with a higher physical activity intensity profile further adding to a longer life. Adding as little as a 10-min brisk walk to daily activity patterns may result in a meaningful benefit to life expectancy.

WISNet: A deep neural network based human activity recognition system

Nowadays, Human Activity Recognition (HAR) is a key research area with many ubiquitous innovative solutions, where both accelerometer and gyroscope data provide information about an observed person’s physical activity. HAR offers a diverse variety of important applications, including healthcare, burglary detection, workplace monitoring, and emergency identification. Traditional recognition approaches rely on extracting handmade features from the obtained data to identify the typeof human action. Additionally, the efficacy of these works is dependent upon the specific customized features that are chosen. One potential approach to tackle this issue is to utilize Convolutional Neural Networks (CNN) to automatically learn the relevant features. In this paper, we propose a deep learning model, WISNet, a custom 1D-CNN approach to recognize six complex human activities: Jogging, Walking Downstairs, Sitting, Standing, Walking and Climbing Upstairs. The model includes a Convolved Normalized Pooled (CNPM) Block to generate significant features from the initial layers. An Identity and Basic (IDBN) Block is incorporated to extract residual progressive features for capturing complex sequential data dependencies. Channel and Spatial attention (CASb) Block is integrated with the network to prioritize or minimize essential features based on relative weights. The proposed WISNet model achieved an enhanced accuracy and F1-score of 96.41 % and 0.95 for the HAR dataset by surpassing the existing transfer learning architectures such as Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Recurrent Neural Network (SimpleRNN). By strategically integrating the CNPM, IDBN, and CASb blocks, this study aims to tackle distinct challenges encountered in the classification process by enhancing the discernment of features essential for the precise identification of multi-class human activity recognition. The seamless integration of these blocks within the model plays a pivotal role in elevating the overall performance of the WISNet architecture. The work also validates WISNet with similar open-source datasets (UCI-HAR and KU-HAR) and dissimilar open-source datasets (Sleep state detection, Fall detection, and ECG Heartbeat).

Home ranges, habitat selection, and energy expenditure of Strix varia (Barred Owls): Understanding the full diel cycle matters for enhancing urban landscapes

Abstract We integrated GPS and accelerometer data to examine habitat selection and energy expenditure patterns across the diel cycle in Strix varia (Barred Owls), addressing a critical gap in wildlife research that often overlooks activity during the “inactive” phase. Owls in Baton Rouge, Louisiana, selected forests with tall canopies and open understories, particularly in affluent neighborhoods, supporting the “luxury effect” in urban biodiversity. Nocturnal home ranges were larger (31.8 ha) compared to diurnal home ranges (8.9 ha), indicating broader habitat use at night. The total area of preferred nocturnal habitat was 33% of the Baton Rouge study area, whereas preferred diurnal habitat comprised only 5%. Energy expenditure was inversely related to preference in nocturnal home ranges but increased with preference in diurnal home ranges. Our models were validated using independent data from Clemson, South Carolina, supporting the robustness of our analysis and revealing generalities in owl habitat selection across these regions. This research contributes to a deeper understanding of urban ecology, highlighting habitat components preferred by owls and possibly other forest-dwelling species. It emphasizes the difference in nocturnal and diurnal home range sizes, the scarcity of daytime refuges for S. varia in urban landscapes, and the variation in energy expenditure in preferred habitats. Our findings advocate for urban designs that accommodate wildlife activity throughout the day and night, and highlight the positive correlation between preferred owl habitat and affluent neighborhoods, underscoring the need for equitable distribution of green spaces to foster biodiversity across socioeconomic gradients. These insights will help develop strategies to enhance the ecological value of urban environments and the conservation of S. varia and associated forest-dwelling species in rapidly urbanizing areas.

Concurrent validity between self-reported International Physical Activity Questionnaire Short Form and Fibion accelerometer data among young adults in the UAE

Self-reported physical activity questionnaires (e.g., International Physical Activity Questionnaire, IPAQ) are a cost-effective, time-saving, and accessible method to assess sedentary behaviour and physical activity. There are conflicting findings regarding the validity of self-reported questionnaires in comparison to accelerometer-measured data in a free-living environment. This study aimed to investigate the concurrent validity between self-reported Arabic–English IPAQ short form (IPAQ-SF) and Fibion (Fibion Inc., Jyväskylä, Finland) accelerometer-measured sedentary and physical activity time among young adults. One hundred and one young healthy adults (mean age 20.8 ± 2.4 years) filled in the IPAQ short form (IPAQ-SF) and wore the Fibion device on the anterior thigh for ≥ 600 min per day for 4–7 days. Concurrent validity between the IPAQ-SF and Fibion accelerometer for sitting, walking, moderate activity, and vigorous activity time was assessed using the Spearman correlation coefficient (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document}) and Bland–Altman plots. Significant weak associations between IPAQ-SF and Fibion measurements were found for total activity time (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} = 0.4; P < 0.001) and for the duration of walking (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} = 0.3; P = 0.01), moderate (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} = 0.2; P = 0.02), and vigorous-intensity activities (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} = 0.4; P < 0.001). However, ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} was not significant (ρ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rho$$\\end{document} = − 0.2; P = 0.09) for sitting time. In addition, all the plots of the measured variables showed a proportional bias. A low association and agreement were found between self-reported IPAQ-SF scores and Fibion accelerometer measurements among young adults in the UAE. Adult sedentary and physical activity measurements should be obtained objectively with accelerometers rather than being limited to self-reported measures.

Smartphone GPS-Based Exposure to Greenspace and Walkability and Accelerometer-Assessed Physical Activity During Pregnancy and Early Postpartum-Evidence from the MADRES Cohort.

A growing number of studies have associated walkability and greenspace exposure with greater physical activity (PA) in women during pregnancy. However, most studies have focused on examining women's residential environments and neglected exposure in locations outside the home neighborhood. Using 350 person-days (N = 55 participants) of smartphone global positioning system (GPS) location and accelerometer data collected during the first and third trimesters and 4-6months postpartum from 55 Hispanic pregnant women from the Maternal and Developmental Risks from Environmental and Social Stressors (MADRES) study, we examined the day-level effect of women's exposure to walkability and greenspace on their PA outcomes during pregnancy and in the early postpartum period. Moderate-to-vigorous physical activity [MVPA] minutes per day was assessed using accelerometers. Walkability and greenspace were measured using geographic information systems (GIS) within women's daily activity spaces (i.e., places visited and routes taken) recorded using a smartphone GPS and weighted by time spent. We used a generalized linear mixed-effects model to estimate the effects of daily GPS-derived environmental exposures on day-level MVPA minutes. Results showed that women engaged in 23% more MVPA minutes on days when they had some versus no exposure to parks and open spaces in activity spaces (b = 1.23; 95%CI: 1.02-1.48). In addition, protective effects of daily greenspace and walkability exposure on MVPA were stronger in the first and third trimesters, among first-time mothers, and among women who had high pre-pregnancy body mass index (BMI) and lived in least-safe neighborhoods. Our results suggest that daily greenspace and walkability exposure are important for women's PA and associated health outcomes during pregnancy and early postpartum.

A Switched Approach for Smartphone-Based Pedestrian Navigation.

In this paper, we propose a novel switched approach to perform smartphone-based pedestrian navigation tasks even in scenarios where GNSS signals are unavailable. Specifically, when GNSS signals are available, the proposed approach estimates both the position and the average bias affecting the measurements from the accelerometers. This average bias is then utilized to denoise the accelerometer data when GNSS signals are unavailable. We test the effectiveness of denoising the acceleration measurements through the estimated average bias by a synthetic example. The effectiveness of the proposed approach is then validated through a real experiment which is conducted along a pre-planned 150 m path.

Daily steps are a predictor of, but perhaps not a modifiable risk factor for Parkinson's Disease: findings from the UK Biobank.

Higher physical activity levels have been suggested as a potential modifiable risk factor for lowering the risk of incident Parkinson's disease (PD). This study uses objective measures of physical activity to investigate the role of reverse causation in the observed association. To investigate the association between accelerometer-derived daily step count and incident PD, and to assess the impact of reverse causation on this association. This prospective cohort study involved a follow-up period with a median duration of 7.9 years, with participants who wore wrist-worn accelerometers for up to 7 days. The study was conducted within the UK Biobank, a large, population-based cohort. The analysis included 94,696 participants aged 43-78 years (56% female) from the UK Biobank who provided valid accelerometer data and did not have prevalent PD. Daily step counts were derived using machine learning models to determine the median daily step count over the monitoring period. The primary outcome was incident PD, identified through hospital admission and death records. Cox proportional hazards regression models estimated hazard ratios (HR) and 95% confidence intervals (CI) for the association between daily step count and incident PD, with adjustments for various covariates and evaluation of reverse causation by splitting follow-up periods. During a median follow-up of 7.9 years (IQR: 7.4-8.4), 407 incident PD cases were identified. An inverse linear association was observed between daily step count and incident PD. Participants in the highest quintile of daily steps (>12,369 steps) had an HR of 0.41 (95% CI 0.31-0.54) compared to the lowest quintile (<6,276 steps; HR 1.00; 95% CI 0.84-1.19). A per 1,000 step increase was associated with an HR of 0.92 (95% CI 0.89-0.94). However, after excluding the first six years of follow-up, the association was not significant (HR 0.96, 95% CI 0.92-1.01). The observed association between higher daily step count and lower incident PD is likely influenced by reverse causation, suggesting changes in physical activity levels occur years before PD diagnosis. While step counts may serve as a predictor for PD, they may not represent a modifiable risk factor. Further research with extended follow-up periods is warranted to better understand this relationship and account for reverse causation.

Inequality in Physical Activity in Organized Group Settings for Children: A Cross-Sectional Study.

Adult-led organized settings for children (eg,classrooms) provide opportunities for physical activity (PA). The structure of setting time may influence inequalities (ie,unequalness) in the distribution of PA. This study examined differences in PA inequality by setting and time-segment purpose in time-segmented organized group settings for children. PA and setting meetings were assessed using accelerometer and video observation data from school, before-/after-school, and youth club groups (n = 30) for third- through sixth-grade children (n = 699) in 2 rural US communities. Meetings (n = 130) were time-segmented into smaller units (sessions; n = 835). Each session was assigned a purpose code (eg,PA). Accelerometer data were paired with the meetings and sessions, and the Gini coefficient quantified inequality in activity counts and moderate to vigorous PA minutes for each segment. Beta generalized estimating equations examined differences in PA inequality by setting and session purpose. Activity count inequality was lowest (P < .05) during youth club meetings (Gini = 0.17, 95% CI, 0.14-0.20), and inequality in moderate to vigorous PA minutes was greatest (P < .01) during school (Gini = 0.34, 95% CI, 0.30-0.38). Organized PA sessions (Gini = 0.20, 95% CI, 0.17-0.23) had lower activity count inequality (P < .0001) than academic (Gini = 0.30, 95% CI, 0.27-0.34), enrichment (Gini = 0.31, 95% CI, 0.27-0.36), and nonactive recreation (Gini = 0.30, 95% CI, 0.25-0.34) sessions. Inequality in moderate to vigorous PA minutes was lower (P < .05) in organized PA (Gini = 0.26, 95% CI, 0.20-0.32) and free play (Gini = 0.28, 95% CI, 0.19-0.39) than other sessions. PA inequality differed by setting time structure, with lower inequality during organized PA sessions. The Gini coefficient can illuminate PA inequalities in organized settings and may inform population PA improvement efforts in rural communities.

Recognizing salat activity using deep learning models via smartwatch sensors

In this study, we focus on human activity recognition, particularly aiming to distinguish the activity of praying (salat) from other daily activities. To achieve this goal, we have created a new dataset named HAR-P (Human activity recognition for Praying), which includes eight different activities: walking, running, sitting, standing, walking upstairs, walking downstairs, typing with a keyboard, and praying (salat). The HAR-P dataset was collected from 50 male individuals, who wore smartwatches on their dominant wrists. We compare the activity classification performance using three state-of-the-art algorithms from the literature: Long Short-Term Memory, Convolutional Long Short-Term Memory, and Convolutional Neural Network—Long Short-Term Memory. To assess the influence of sensors, data from accelerometer, gyroscope, linear acceleration sensor, and magnetic field sensor were utilized. The impact of individual sensor data as well as combinations thereof was investigated. The highest classification accuracy within single sensor groups, reaching 95.7%, was achieved using the accelerometer data with the Convolutional Long Short-Term Memory method. Combining two sensor groups resulted in an increase in accuracy of up to 9%. The highest accuracy of 96.4% was obtained by utilizing three sensor groups together with the Convolutional Neural Network—Long Short-Term Memory method. Furthermore, the evaluation of sensor and model performance was conducted using the stratified k-fold cross-validation method with 5-folds. These findings contribute significantly to evaluating the performance of sensor combinations and different algorithms in activity classification. This study may provide an effective foundation for the automatic recognition and tracking of human activities and offer an applicable model, particularly for the recognition of religious practices such as praying.

A data-driven approach to detect upper limb functional use during daily life in breast cancer survivors using wrist-worn sensors

To gain insights into the impact of upper limb (UL) dysfunctions after breast cancer treatment, this study aimed to develop a temporal convolutional neural network (TCN) to detect functional daily UL use in breast cancer survivors using data from a wrist-worn accelerometer. A pre-existing dataset of 10 breast cancer survivors was used that contained raw 3-axis acceleration data and simultaneously recorded video data, captured during four daily life activities. The input of our TCN consists of a 3-axis acceleration sequence with a receptive field of 243 samples. The 4 ResNet TCN blocks perform dilated temporal convolutions with a kernel of size 3 and a dilation rate that increases by a factor of 3 after each iteration. Outcomes of interest were functional UL use (minutes) and percentage UL use. We found strong agreement between the video and predicted data for functional UL use (ICC = 0.975) and moderately strong agreement for %UL use (ICC = 0.794). The TCN model overestimated the functional UL use by 0.71 min and 3.06%. Model performance showed good accuracy, f1, and AUPRC scores (0.875, 0.909, 0.954, respectively). In conclusion, using wrist-worn accelerometer data, the TCN model effectively identified functional UL use in daily life among breast cancer survivors.

A Human Activity Recognition model based on CNN and Transformer

Abstract This study aims to utilize data from built-in sensors in smartphones for human activity recognition. By analyzing the three-dimensional accelerometer and gyroscope data in user behavior, accurate classification of eight common activity states is achieved, including walking, standing, sitting, squatting, going up stairs, going down stairs, climbing ladders, and descending ladders. To enhance the model’s generalization capability, a method combining Transformer neural networks with one-dimensional Convolutional Neural Networks (CNNs) is employed, along with data sample augmentation. Experimental results demonstrate a significant improvement in recognition accuracy compared to traditional models, indicating the potential for real-time application on smartphones and other devices. This approach provides essential technical support for predictive human-computer interaction on smart devices and holds extensive application prospects.

Decoding Human Activities: Analyzing Wearable Accelerometer and Gyroscope Data for Activity Recognition

Decoding Human Activities: Analyzing Wearable Accelerometer and Gyroscope Data for Activity Recognition

Seasonal migration patterns of Siberian Rubythroat (Calliope calliope) facing the Qinghai–Tibet Plateau

BackgroundSmall songbirds respond and adapt to various geographical barriers during their annual migration. Global flyways reveal the diverse migration strategies in response to different geographical barriers, among which are high-elevation plateaus. However, few studies have been focused on the largest and highest plateau in the world, the Qinghai–Tibet Plateau (QTP) which poses a significant barrier to migratory passerines. The present study explored the annual migration routes and strategies of a population of Siberian Rubythroats (Calliope calliope) that breed on the north-eastern edge of the QTP.MethodsOver the period from 2021 to 2023, we applied light-level geolocators (13 deployed, seven recollected), archival GPS tags (45 deployed, 17 recollected), and CAnMove multi-sensor loggers (with barometer, accelerometer, thermometer, and light sensor, 20 deployed, six recollected) to adult males from the breeding population of Siberian Rubythroat on the QTP. Here we describe the migratory routes and phenology extracted or inferred from the GPS and multi-sensor logger data, and used a combination of accelerometric and barometric data to describe the elevational migration pattern, flight altitude, and flight duration. All light-level geolocators failed to collect suitable data.ResultsBoth GPS locations and positions derived from pressure-based inference revealed that during autumn, the migration route detoured from the bee-line between breeding and wintering grounds, leading to a gradual elevational decrease. The spring route was more direct, with more flights over mountainous areas in western China. This different migration route during spring probably reflects a strategy for faster migration, which corresponds with more frequent long nocturnal migration flights and shorter stopovers during spring migration than in autumn. The average flight altitude (1856 ± 781 m above sea level) was correlated with ground elevation but did not differ between the seasons.ConclusionsOur finding indicates strong, season-dependent impact of the Qinghai–Tibet Plateau on shaping passerine migration strategies. We hereby call for more attention to the unexplored central-China flyway to extend our knowledge on the environment-migration interaction among small passerines.

Association of accelerometer-derived “weekend warrior” moderate to vigorous physical activity, chronic kidney disease and acute kidney injury

ObjectiveTo examine the relationship between an accelerometer-derived “weekend warrior” pattern, characterized by achieving the most moderate to vigorous physical activity (MVPA) over 1–2 days, as opposed to more evenly distributed patterns, with risk of chronic kidney disease (CKD) and acute kidney injury (AKI). Methods77,977 participants without prior kidney diseases and with usable accelerometer data (collected between 2013 and 2015) were included from the UK Biobank. Three physical activity patterns were compared: active weekend warrior pattern (achieving ≥150 min MVPA per week and accumulating ≥50 % of total MVPA in 1–2 days), active regular pattern (achieving ≥150 min MVPA but not meeting active weekend warrior criteria per week), and inactive pattern (<150 min MVPA per week). The study outcomes included incident CKD and AKI, ascertained through self-report data and data linkage with primary care, hospital admissions, and death registry records. ResultsDuring a median follow-up of 6.8 years, 1324 participants developed CKD and 1515 developed AKI. In multivariable-adjusted models, when compared with inactive participants, individuals with active weekend warrior pattern (CKD: hazard ratio [HR], 0.79, 95 % confidence interval [CI], 0.69–0.89; AKI: HR, 0.70, 95 %CI, 0.62–0.79) and those with active regular pattern (CKD: HR, 0.81, 95 %CI, 0.69–0.95; AKI: HR, 0.79, 95 %CI, 0.68–0.91) exhibited a similar and significantly lower risk of incident CKD and AKI. Similar findings were observed at the median threshold of ≥230.4 min of MVPA per week. ConclusionConcentrated MVPA within 1 to 2 days is as effective as distributed ones in decreasing the risk of renal outcomes.

Processing of Sedentary Time and Its Reference Equation in Patients with COPD.

Sedentary time (ST) is associated with mortality independent of moderate-to-vigorous physical activity in patients with COPD. The proper processing methods for the measurement data and factors related to ST are still unknown. We investigated several conditions for determining the proper processing of ST accelerometric data and created a reference equation for ST using ST-related factors. In Study 1, we evaluated the minimum required number of days to obtain repeatability at different measurement times and assessed the effects of rainy days or weekend days on ST in patients with COPD. In Study 2, we detected the ST-related factors among 28 parameters and created a reference equation for ST using the detected factors. In Study 1, 38 patients with stable COPD were analyzed. The minimum number of days required for repeatability was 3 for 8-h wearing and 2 for 10-h wearing. The ST was significantly prolonged on rainy days, but not on weekends. In Study 2, 216 patients with stable COPD were analyzed. BMI, FEV1%pred, 6MWD, and mMRC were detected as ST-related factors, and a reference equation could be created using these four factors. The equation was validated for patients whose ST was ≥ 6 h. By using properly processed measurement data of ST, we created a reference equation for assessing ST that is expected to be useful for providing individual guidance on the shortening of ST to patients with COPD.

Low power activity monitoring using accelerometer data from an inertial measurement unit (IMU)

Low power activity monitoring using accelerometer data from an inertial measurement unit (IMU)

A study on machine learning-based prediction of cerebellar ataxia using gait analysis and accelerometer data

In the neurological field, predicting Cerebellar Ataxia (CA) is based on analyzing gait values of human actions. Analyzing Gait (AoG) can potentially guide effective treatment strategies. This study aimed to create a machine-learning model for predicting AoG using gait patterns indicative of pre-AoG conditions. During the execution of designed walking tasks to provokeAoG, accelerometers were attached to the lower back of 21 subjects as they performed 12 different walking positions to collect acceleration impulses. The participants engaged in walking exercises for one minute at 12 different walking speeds on a split-belt treadmill, ranging from 0.6 to 1.7 m/s in 0.1 m/s increments. The speed sequence was randomized and concealed from the subjects to minimize fatigue effects. Prior research studies have surveyed machine-learning algorithms such as support vector machine (SVM) and k-nearest neighbors (KNN). These algorithms demonstrate strong performance, especially when the dataset is trivial, and the classification is binary. SVM, KNN, decision trees, and XGBoost algorithms were utilized in the proposed study on the CA dataset. Our findings revealed that the AdaBoost algorithm, with its high precision, offers a more precise categorisation of the severity of CA disease, instilling confidence in the study's findings.

The associations of chronic pain and 24-h movement behaviors with incident mental disorders: evidence from a large-scale cohort study

BackgroundChronic pain was associated with a higher risk of mental disorders (e.g., depression and anxiety). However, the role of 24-h movement behaviors in the association remains unclear.MethodsA total of 72,800 participants with accelerometer data and free of mental disorders from the UK Biobank were analyzed. The compositional mediation model and isotemporal substitution model were used to explore the associations between chronic pain, 24-h movement behaviors, and the incidence of overall mental disorders, depression, and anxiety.ResultsWith a median follow-up of 13.36 years, participants with chronic pain had a higher rate of incident overall mental disorders (hazard ratio (HR): 1.281, 95% confidence interval (CI): 1.219 to 1.344), anxiety (HR: 1.391, 95% CI: 1.280 to 1.536), and depression (HR: 1.703, 95% CI: 1.551 to 1.871). Increased sedentary behavior (SB) and reduced moderate-to-vigorous physical activity (MVPA) caused by chronic pain both increased the risk of mental disorders. Twenty-four-hour movement behaviors explained the relationship between chronic pain and overall mental disorders, depression, and anxiety by 10.77%, 5.70%, and 6.86%, respectively. Interaction effects were found between MVPA and chronic pain when predicting the incidence of depression and between MVPA, sleep (SLP), and chronic pain when predicting the incidence of mental disorders. People with chronic pain would recommend at least 0.5 h per day of MVPA and 7 h per day of SLP and restricting SB below 11.5 h per day.ConclusionsTwenty-four-hour movement behaviors played a significant mediating role in the association between chronic pain and mental disorders. Individuals with chronic pain should engage in more MVPA, less sedentary behavior, and have 7-h sleep per day.

Smartphone IMU Sensors for Human Identification through Hip Joint Angle Analysis.

Gait monitoring using hip joint angles offers a promising approach for person identification, leveraging the capabilities of smartphone inertial measurement units (IMUs). This study investigates the use of smartphone IMUs to extract hip joint angles for distinguishing individuals based on their gait patterns. The data were collected from 10 healthy subjects (8 males, 2 females) walking on a treadmill at 4 km/h for 10 min. A sensor fusion technique that combined accelerometer, gyroscope, and magnetometer data was used to derive meaningful hip joint angles. We employed various machine learning algorithms within the WEKA environment to classify subjects based on their hip joint pattern and achieved a classification accuracy of 88.9%. Our findings demonstrate the feasibility of using hip joint angles for person identification, providing a baseline for future research in gait analysis for biometric applications. This work underscores the potential of smartphone-based gait analysis in personal identification systems.