Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type

Classification of Free-Living Body Posture with ECG Patch Accelerometers: Application to the Multicenter AIDS Cohort Study

Purpose

As health studies increasingly monitor free-living heart performance via ECG patches with accelerometers, researchers will seek to investigate cardio-electrical responses to physical activity and sedentary behavior, increasing demand for fast, scalable methods to process accelerometer data. We extend a posture classification algorithm for accelerometers in ECG patches when researchers do not have ground-truth labels or other reference measurements (i.e., upright measurement).

Methods

Men living with and without HIV in the Multicenter AIDS Cohort study wore the Zio XT® for up to two weeks (n = 1,250). Our novel extensions for posture classification include (1) estimation of an upright posture for each individual without a reference upright measurement; (2) correction of the upright estimate for device removal and re-positioning using novel spherical change-point detection; and (3) classification of upright and recumbent periods using a clustering and voting process rather than a simple inclination threshold used in other algorithms. As no posture labels exist in the free-living environment, we perform numerous sensitivity analyses and evaluate the algorithm against labelled data from the Towson Accelerometer Study, where participants wore accelerometers at the waist.

Results

On average, 87.1% of participants were recumbent at 4am and 15.5% were recumbent at 1pm. Participants were recumbent 54 minutes longer on weekends compared to weekdays. Performance was good in comparison to labelled data in a separate, controlled setting (accuracy = 96.0%, sensitivity = 97.5%, specificity = 95.9%).

Conclusions

Posture may be classified in the free-living environment from accelerometers in ECG patches even without measuring a standard upright position. Furthermore, algorithms that fail to account for individuals who rotate and re-attach the accelerometer may fail in the free-living environment.

Monitoring mobility in older adults using a Global Positioning System (GPS) smartwatch and accelerometer: A validation study

There is growing interest in identifying valid and reliable methods for detecting early mobility limitations in aging populations. A multi-sensor approach that combines accelerometry with Global Positioning System (GPS) devices could provide valuable insights into late-life mobility decline; however, this innovative approach requires more investigation. We conducted a series of two experiments with 25 older participants (66.2±8.5 years) to determine the validity of a GPS enabled smartwatch (TicWatch S2 and Pro 3 Ultra GPS) and separate accelerometer (ActiGraph wGT3X-BT) to collect movement, navigation and body posture data relevant to mobility. In experiment 1, participants wore the TicWatchS2 and ActiGraph simultaneously on the wrist for 3 days. In experiment 2, participants wore the TicWatch Pro 2 Ultra GPS on the wrist and ActiGraph on the thigh for 3 days. In both experiments participants also carried a Qstarz data logger for trips outside the home. The TicWatch Pro 3 Ultra GPS performed better than the S2 model and was similar to the Qstarz in all tested trip-related measures, and it was able to estimate both passive and active trip modes. Both models showed similar results to the gold standard Qstarz in life-space-related measures. The TicWatch S2 demonstrated good to excellent overall agreement with the ActiGraph algorithms for the time spent in sedentary and non-sedentary activities, with 84% and 87% agreement rates, respectively. Under controlled conditions, the TicWatch Pro 3 Ultra GPS consistently measured step count in line with the participants' self-reported data, with a bias of 0.4 steps. The thigh-worn ActiGraph algorithm accurately classified sitting and lying postures (97%) and standing postures (90%). Our multi-sensor approach to monitoring mobility has the potential to capture both accelerometer-derived movement data and trip/life-space data only available through GPS. In this study, we found that the TicWatch models were valid devices for capturing GPS and raw accelerometer data, making them useful tools for assessing real-life mobility in older adults.

Companion: A Pilot Randomized Clinical Trial to Test an Integrated Two-Way Communication and Near-Real-Time Sensing System for Detecting and Modifying Daily Inactivity among Adults >60 Years-Design and Protocol

Supervised personal training is most effective in improving the health effects of exercise in older adults. Yet, low frequency (60 min, 1-3 sessions/week) of trainer contact limits influence on behavior change outside sessions. Strategies to extend the effect of trainer contact outside of supervision and that integrate meaningful and intelligent two-way communication to provide complex and interactive problem solving may motivate older adults to "move more and sit less" and sustain positive behaviors to further improve health. This paper describes the experimental protocol of a 16-week pilot RCT (N = 46) that tests the impact of supplementing supervised exercise (i.e., control) with a technology-based behavior-aware text-based virtual "Companion" that integrates a human-in-the-loop approach with wirelessly transmitted sensor-based activity measurement to deliver behavior change strategies using socially engaging, contextually salient, and tailored text message conversations in near-real-time. Primary outcomes are total-daily and patterns of habitual physical behaviors after 16 and 24 weeks. Exploratory analyses aim to understand Companion's longitudinal behavior effects, its user engagement and relationship to behavior, and changes in cardiometabolic and cognitive outcomes. Our findings may allow the development of a more scalable hybrid AI Companion to impact the ever-growing public health epidemic of sedentariness contributing to poor health outcomes, reduced quality of life, and early death.

Detecting Sleep and Nonwear in 24-h Wrist Accelerometer Data from the National Health and Nutrition Examination Survey

INTRODUCTION

Estimating physical activity, sedentary behavior, and sleep from wrist-worn accelerometer data requires reliable detection of sensor nonwear and sensor wear during both sleep and wake.

PURPOSE

This study aimed to develop an algorithm that simultaneously identifies sensor wake-wear, sleep-wear, and nonwear in 24-h wrist accelerometer data collected with or without filtering.

METHODS

Using sensor data labeled with polysomnography ( n = 21) and directly observed wake-wear data ( n = 31) from healthy adults, and nonwear data from sensors left at various locations in a home ( n = 20), we developed an algorithm to detect nonwear, sleep-wear, and wake-wear for "idle sleep mode" (ISM) filtered data collected in the 2011-2014 National Health and Nutrition Examination Survey. The algorithm was then extended to process original raw data collected from devices without ISM filtering. Both algorithms were further validated using a polysomnography-based sleep and wake-wear data set ( n = 22) and diary-based wake-wear and nonwear labels from healthy adults ( n = 23). Classification performance (F1 scores) was compared with four alternative approaches.

RESULTS

The F1 score of the ISM-based algorithm on the training data set using leave-one-subject-out cross-validation was 0.95 ± 0.13. Validation on the two independent data sets yielded F1 scores of 0.84 ± 0.60 for the data set with sleep-wear and wake-wear and 0.94 ± 0.04 for the data set with wake-wear and nonwear. The F1 score when using original, raw data was 0.96 ± 0.08 for the training data sets and 0.86 ± 0.18 and 0.97 ± 0.04 for the two independent validation data sets. The algorithm performed comparably or better than the alternative approaches on the data sets.

CONCLUSIONS

A novel machine-learning algorithm was designed to recognize wake-wear, sleep-wear, and nonwear in 24-h wrist-worn accelerometer data that are applicable for ISM-filtered data or original raw data.

Investigating Microtemporal Processes Underlying Health Behavior Adoption and Maintenance: Protocol for an Intensive Longitudinal Observational Study (Preprint)

Background

Objective

Methods

Results

Conclusions

International Registered Report Identifier (IRRID)

Signaligner Pro: A Tool to Explore and Annotate Multi-day Raw Accelerometer Data

Human activity recognition using wearable accelerometers can enable in-situ detection of physical activities to support novel human-computer interfaces. Many of the machine-learning-based activity recognition algorithms require multi-person, multi-day, carefully annotated training data with precisely marked start and end times of the activities of interest. To date, there is a dearth of usable tools that enable researchers to conveniently visualize and annotate multiple days of high-sampling-rate raw accelerometer data. Thus, we developed Signaligner Pro, an interactive tool to enable researchers to conveniently explore and annotate multi-day high-sampling rate raw accelerometer data. The tool visualizes high-sampling-rate raw data and time-stamped annotations generated by existing activity recognition algorithms and human annotators; the annotations can then be directly modified by the researchers to create their own, improved, annotated datasets. In this paper, we describe the tool's features and implementation that facilitate convenient exploration and annotation of multi-day data and demonstrate its use in generating activity annotations.

Machine Learning to Quantify Physical Activity in Children with Cerebral Palsy: Comparison of Group, Group-Personalized, and Fully-Personalized Activity Classification Models

Pattern recognition methodologies, such as those utilizing machine learning (ML) approaches, have the potential to improve the accuracy and versatility of accelerometer-based assessments of physical activity (PA). Children with cerebral palsy (CP) exhibit significant heterogeneity in relation to impairment and activity limitations; however, studies conducted to date have implemented “one-size fits all” group (G) models. Group-personalized (GP) models specific to the Gross Motor Function Classification (GMFCS) level and fully-personalized (FP) models trained on individual data may provide more accurate assessments of PA; however, these approaches have not been investigated in children with CP. In this study, 38 children classified at GMFCS I to III completed laboratory trials and a simulated free-living protocol while wearing an ActiGraph GT3X+ on the wrist, hip, and ankle. Activities were classified as sedentary, standing utilitarian movements, or walking. In the cross-validation, FP random forest classifiers (99.0–99.3%) exhibited a significantly higher accuracy than G (80.9–94.7%) and GP classifiers (78.7–94.1%), with the largest differential observed in children at GMFCS III. When evaluated under free-living conditions, all model types exhibited significant declines in accuracy, with FP models outperforming G and GP models in GMFCS levels I and II, but not III. Future studies should evaluate the comparative accuracy of personalized models trained on free-living accelerometer data.