Assessing the impact of body location on the accuracy of detecting daily activities with accelerometer data.
Ontology highlight
ABSTRACT:
SUBMITTER: Dang X
PROVIDER: S-EPMC10838735 | biostudies-literature | 2024 Feb
REPOSITORIES: biostudies-literature
Publications
Assessing the impact of body location on the accuracy of detecting daily activities with accelerometer data.
Dang Xiangnan X Li Wentao W Zou Jasmine J Cong Brian B Guan Yuanfang Y
iScience 20240106 2
Recent advancements in digital biomarkers have highlighted the importance of accelerometer and gyroscope data for monitoring activities, identifying motion-related diseases, and assessing disease severity. Prior studies predominantly limit sensor placement to one or two locations. Here, we conducted a trial focusing on the impact of sensor placement in predicting 21 common activities using convolutional neural networks (CNN) and long short-term memory networks (LSTM). Our research found that the ...[more]
Similar Datasets
Project description:BACKGROUND:There has been an increasing interest in understanding the usefulness of wrist-based accelerometer data for physical activity (PA) assessment due to the ease of use and higher user compliance than other body placements. PA assessment studies have relied on machine learning methods which take accelerometer data in forms of variables, or feature vectors. METHODS:In this work, we introduce automated shape feature derivation methods to transform epochs of accelerometer data into feature vectors. As the first step, recurring patterns in the collected data are identified and placed in a codebook. Similarities between epochs of accelerometer data and codebook's patterns are the basis of feature calculations. In this paper, we demonstrate supervised and unsupervised approaches to learn codebooks. We evaluated these methods and compared them with the standard statistical measures for PA assessment. The experiments were performed on 146 participants who wore an ActiGraph GT3X+ accelerometer on the right wrist and performed 33 activities of daily living. RESULTS:Our evaluations show that the shape feature derivation methods were able to perform comparably with the standard wrist model (F1-score: 0.89) for identifying sedentary PAs (F1-scores of 0.86 and 0.85 for supervised and unsupervised methods, respectively). This was also observed for identifying locomotion activities (F1-scores: 0.87, 0.83, and 0.81 for the standard wrist, supervised, unsupervised models, respectively). All the wrist models were able to estimate energy expenditure required for PAs with low error (rMSE: 0.90, 0.93, and 0.90 for the standard wrist, supervised, and unsupervised models, respectively). CONCLUSION:The automated shape feature derivation methods offer insights into the performed activities by providing a summary of repeating patterns in the accelerometer data. Furthermore, they could be used as efficient alternatives (or additions) for manually engineered features, especially important for cases where the latter fail to provide sufficient information to machine learning methods for PA assessment.
| S-EPMC6290590 | biostudies-other
Project description:The dataset presented in this paper presents a dataset related to three motionless activities, including driving, watching TV, and sleeping. During these activities, the mobile device may be positioned in different locations, including the pants pockets, in a wristband, over the bedside table, on a table, inside the car, or on other furniture, for the acquisition of accelerometer, magnetometer, gyroscope, GPS, and microphone data. The data was collected by 25 individuals (15 men and 10 women) in different environments in Covilhã and Fundão municipalities (Portugal). The dataset includes the sensors' captures related to a minimum of 2000 captures for each motionless activity, which corresponds to 2.8 h (approximately) for each one. This dataset includes 8.4 h (approximately) of captures for further analysis with data processing techniques, and machine learning methods. It will be useful for the complementary creation of a robust method for the identification of these type of activities.
| S-EPMC8956627 | biostudies-literature
Project description:The dataset presented in this paper is related to the performance of five Activities of Daily Living (ADL) with motion, such as walking, running, standing, walking upstairs, and walking downstairs. These activities were performed with a mobile device in a waistband, containing the data acquired from accelerometer, magnetometer, and gyroscope sensors. These data include the motion data, which allow the characterization of the different types of movement. The data acquisition was performed in open environments by 25 individuals (15 man, and 10 woman) in the Covilhã, and Fundão municipalities (Portugal). The data related to the different sensors was acquired with a sampling rate of 100 Hz by the accelerometer, 50 Hz by the magnetometer, and 100 Hz by the gyroscope sensors. It includes the captures related to a minimum of 2000 captures for each ADL, which corresponds to 2.8 h (approximately) for each ADL. In total, this dataset includes 13.9 h (approximately) of captures. These data can be reused for the implementation of data processing techniques, and artificial intelligence methods.
| S-EPMC7735969 | biostudies-literature
Project description:ObjectiveThis paper aims to identify periods of depression using geolocation movements recorded from mobile phones in a prospective community study of individuals with bipolar disorder (BD).MethodsAnonymized geographic location recordings from 22 BD participants and 14 healthy controls (HC) were collected over 3 months. Participants reported their depressive symptomatology using a weekly questionnaire (QIDS-SR16). Recorded location data were preprocessed by detecting and removing imprecise data points and features were extracted to assess the level and regularity of geographic movements of the participant. A subset of features were selected using a wrapper feature selection method and presented to 1) a linear regression model and a quadratic generalized linear model with a logistic link function for questionnaire score estimation; and 2) a quadratic discriminant analysis classifier for depression detection in BD participants based on their questionnaire responses. R esults: HC participants did not report depressive symptoms and their features showed similar distributions to nondepressed BD participants. Questionnaire score estimation using geolocation-derived features from BD participants demonstrated an optimal mean absolute error rate of 3.73, while depression detection demonstrated an optimal (median ± IQR) [Formula: see text] score of 0.857 ± 0.022 using five features (classification accuracy: 0.849 ± 0.016; sensitivity: 0.839 ± 0.014; specificity: 0.872 ± 0.047).ConclusionThese results demonstrate a strong link between geographic movements and depression in bipolar disorder. S ignificance: To our knowledge, this is the first community study of passively recorded objective markers of depression in bipolar disorder of this scale. The techniques could help individuals monitor their depression and enable healthcare providers to detect those in need of care or treatment.
| S-EPMC5947818 | biostudies-literature
Project description:PurposeAccelerometers are increasingly used to obtain valuable descriptors of physical activity for health research. The cut-points approach to segment accelerometer data is widely used in physical activity research but requires resource expensive calibration studies and does not make it easy to explore the information that can be gained for a variety of raw data metrics. To address these limitations, we present a data-driven approach for segmenting and clustering the accelerometer data using unsupervised machine learning.MethodsThe data used came from five hundred fourteen-year-old participants from the Millennium cohort study who wore an accelerometer (GENEActiv) on their wrist on one weekday and one weekend day. A Hidden Semi-Markov Model (HSMM), configured to identify a maximum of ten behavioral states from five second averaged acceleration with and without addition of x, y, and z-angles, was used for segmenting and clustering of the data. A cut-points approach was used as comparison.ResultsTime spent in behavioral states with or without angle metrics constituted eight and five principal components to reach 95% explained variance, respectively; in comparison four components were identified with the cut-points approach. In the HSMM with acceleration and angle as input, the distributions for acceleration in the states showed similar groupings as the cut-points categories, while more variety was seen in the distribution of angles.ConclusionOur unsupervised classification approach learns a construct of human behavior based on the data it observes, without the need for resource expensive calibration studies, has the ability to combine multiple data metrics, and offers a higher dimensional description of physical behavior. States are interpretable from the distributions of observations and by their duration.
| S-EPMC6326431 | biostudies-literature
Project description:The detection of activities of daily living (ADL) and the detection of falls is of utmost importance for addressing the issue of serious injuries and death as a consequence of elderly people falling. Wearable sensors can provide a viable solution for monitoring people in danger of falls with minimal external involvement from health or care home workers. In this work, we recorded accelerometer data from 35 healthy individuals performing various ADLs, as well as falls. Spatial and frequency domain features were extracted and used for the training of machine learning models with the aim of distinguishing between fall and no fall events, as well as between falls and other ADLs. Supervised classification experiments demonstrated the efficiency of the proposed approach, achieving an F1-score of 98.41% for distinguishing between fall and no fall events, and an F1-score of 88.11% for distinguishing between various ADLs, including falls. Furthermore, the created dataset, named "ShimFall&ADL" will be publicly released to facilitate further research on the field.
| S-EPMC7378757 | biostudies-literature
Project description:Although accelerometry data are widely utilized to estimate physical activity and sedentary behavior among children age 3 years or older, for toddlers age 1 and 2 year(s), accelerometry data recorded during such behaviors have been far less examined. In particular, toddler's unique behaviors, such as riding in a stroller or being carried by an adult, have not yet been examined. The objective of this study was to describe accelerometry signal outputs recorded during participation in nine types of behaviors (i.e., running, walking, climbing up/down, crawling, riding a ride-on toy, standing, sitting, riding in a stroller/wagon, and being carried by an adult) among toddlers. Twenty-four toddlers aged 13 to 35 months (50% girls) performed various prescribed behaviors during free play in a commercial indoor playroom while wearing ActiGraph wGT3X-BT accelerometers on a hip and a wrist. Participants' performances were video-recorded. Based on the video data, accelerometer data were annotated with behavior labels to examine accelerometry signal outputs while performing the nine types of behaviors. Accelerometer data collected during 664 behavior assessments from the 21 participants were used for analysis. Hip vertical axis counts for walking were low (median = 49 counts/5 s). They were significantly lower than those recorded while a toddler was "carried" by an adult (median = 144 counts/5 s; p < 0.01). While standing, sitting, and riding in a stroller, very low hip vertical axis counts were registered (median ≤ 5 counts/5 s). Although wrist vertical axis and vector magnitude counts for "carried" were not higher than those for walking, they were higher than the cut-points for sedentary behaviors. Using various accelerometry signal features, machine learning techniques showed 89% accuracy to differentiate the "carried" behavior from ambulatory movements such as running, walking, crawling, and climbing. In conclusion, hip vertical axis counts alone may be unable to capture walking as physical activity and "carried" as sedentary behavior among toddlers. Machine learning techniques that utilize additional accelerometry signal features could help to recognize behavior types, especially to differentiate being "carried" from ambulatory movements.
| S-EPMC6678133 | biostudies-literature
Project description:BackgroundObjective assessments of sedentary behavior and physical activity (PA) by using accelerometer-based wearable devices are ever expanding, given their importance in the global context of health maintenance. This study aimed to determine the reliability and validity of a new accelerometer-based analyzer (Fibion) for detecting different PAs and estimating energy expenditure (EE) during a simulated free-living day.MethodsThe study consisted of two parts: a reliability (n = 18) and a validity (n = 19) test. Reliability was assessed by a 45 min protocol of repeated sitting, standing, and walking (i.e., 3 × 15 min, repeated twice), using both Fibion and ActiGraph. Validity was assessed by a 12 h continuous sequence tasks of different types (sitting, standing, walking, and cycling) and intensities (light [LPA], moderate [MPA], and vigorous [VPA]) of PA. Two Fibion devices were worn on the thigh (FT) and in the pocket (FP), respectively and were compared with criteria measures, such as direct observation (criterion 1) and oxygen consumption by a portable gas analyzer, K4b2 (criterion 2).ResultsFT (intra-class correlation coefficients (ICCs): 0.687-0.806) provided similar reliability as the Actigraph (ICCs: 0.661-0.806) for EE estimation. However, the measurement error (ME) of FT compared to the actual time records indicated an underestimation of duration by 5.1 ± 1.2%, 3.8 ± 0.3% and 14.9 ± 2.6% during sitting, walking, and standing, respectively. During the validity test, FT but not FP showed a moderate agreement but lager variance with the criteria (1 and 2) in assessing duration of sitting, long sitting, LPA, MPA, and VPA (p > 0.05, ICCs: 0.071-0.537), as well as for EE estimation of standing, LPA, MPA, and VPA (p > 0.05, ICCs: 0.673-0.894).ConclusionsFT provided similar reliability to that of the Actigraph. However, low correlations between subsequent measurements of both devices indicated large random MEs, which were somewhat diminished during the simulated 12 h real-life test. Furthermore, FT may accurately determine the types, intensities of PA and EE during prolonged periods with substantial changes in postures, indicating that the location of the accelerometer is essential. Further study with a large cohort is needed to confirm the usability of Fibion, especially for detecting the low-intensity PAs.
| S-EPMC6186411 | biostudies-literature
Project description:ObjectiveChronic obstructive pulmonary disease (COPD) is characterized by airflow limitation; however, pulmonary function does not fully account for patients' functional difficulties. The primary aim of the study was to determine the association between several domains of cognition and daily activity among those with COPD.MethodEighty-nine former smokers completed a neuropsychological battery including measures across multiple domains of cognition, pulmonary function measures, and daily activity questionnaires. Using a cross-sectional design, we compared daily activity between former smokers with and without COPD using two measures (St. George's Respiratory Questionnaire [SGRQ] Activity Subscale and Lawton Instrumental Activities of Daily Living [IADL] Scale) and examined the association between cognition and daily activity among those with COPD.ResultsAs expected, former smokers with COPD reported more difficulty than those without COPD on both activity measures (SGRQ Activity Subscale p < .001; Lawton IADL Scale p = .040). Among former smokers with COPD, poorer delayed recall was associated with more difficulty with daily activities (SGRQ Activity Subscale) (p = .038) while adjusting for severity of airflow limitation, exercise tolerance, oxygen use, dyspnea, and symptoms of anxiety and depression.ConclusionThe findings suggest that cognition is associated with daily activity in patients with COPD. Future research should examine whether cognitive interventions may help to maximize patients' engagement in daily activities.
| S-EPMC8500183 | biostudies-literature
Project description:The purpose of this study was to develop peak ground reaction force (pGRF) and peak loading rate (pLR) prediction equations for high-impact activities in adult subjects with a broad range of body masses, from normal weight to severe obesity. A total of 78 participants (27 males; 82.4 ± 20.6 kg) completed a series of trials involving jumps of different types and heights on force plates while wearing accelerometers at the ankle, lower back, and hip. Regression equations were developed to predict pGRF and pLR from accelerometry data. Leave-one-out cross-validation was used to calculate prediction accuracy and Bland-Altman plots. Body mass was a predictor in all models, along with peak acceleration in the pGRF models and peak acceleration rate in the pLR models. The equations to predict pGRF had a coefficient of determination (R2) of at least 0.83, and a mean absolute percentage error (MAPE) below 14.5%, while the R2 for the pLR prediction equations was at least 0.87 and the highest MAPE was 24.7%. Jumping pGRF can be accurately predicted through accelerometry data, enabling the continuous assessment of mechanical loading in clinical settings. The pLR prediction equations yielded a lower accuracy when compared to the pGRF equations.
| S-EPMC9960291 | biostudies-literature