Classifiers for Accelerometer-Measured Behaviors in Older Women

@article{Rosenberg2017ClassifiersFA,
  title={Classifiers for Accelerometer-Measured Behaviors in Older Women},
  author={Dori E. Rosenberg and Suneeta Godbole and Katherine Ellis and Chongzhi Di and Andrea Z. LaCroix and Jacqueline Kerr},
  journal={Medicine \& Science in Sports \& Exercise},
  year={2017},
  volume={49},
  pages={610–616}
}
Purpose Machine learning methods could better improve the detection of specific types of physical activities and sedentary behaviors from accelerometer data. No studies in older populations have developed and tested algorithms for walking and sedentary time in free-living daily life. Our goal was to rectify this gap by leveraging access to data from two studies in older women. Methods In study 1, algorithms were developed and tested in a sample of older women (N = 39, age range = 55–96 yr) in… 
Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
TLDR
This is among the first algorithms for sitting and standing for hip-worn accelerometer data to be trained from entirely free-living activPAL data, and the new algorithm detected prolonged sitting, which has been shown to be the most detrimental to health.
Segmenting accelerometer data from daily life with unsupervised machine learning
TLDR
The 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.
A Dual-Accelerometer System for Detecting Human Movement in a Free-living Environment.
TLDR
This validation study demonstrated that a dual accelerometer system previously validated in a laboratory setting also performs well in semi free-living conditions in children and adults.
Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults
TLDR
It is proposed that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry.
Accelerometer‐Derived Daily Life Movement Classified by Machine Learning and Incidence of Cardiovascular Disease in Older Women: The OPACH Study
TLDR
Describing the beneficial associations of physical activity in terms of common behaviors could help older adults accumulate physical activity.
A comparison of accelerometry analysis methods for physical activity in older adult women and associations with health outcomes over time
TLDR
All methods, except the individualized cut-point, had a significant relationship between change in PA and improved physical function and depressive symptoms and this study is among the first to compare accelerometry processing methods and their relationship to health.
Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers
TLDR
This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models and contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free- living settings.
Application of Raw Accelerometer Data and Machine-Learning Techniques to Characterize Human Movement Behavior: A Systematic Scoping Review.
TLDR
Machine-learning algorithms demonstrate good accuracy when predicting physical activity components; however, their application to free-living settings is currently uncertain.
Physical Activity Change in an RCT: Comparison of Measurement Methods.
TLDR
Intervention researchers are facing the issue of self-report measures introducing bias and accelerometer cut-points being insensi- tive, and machine learning approaches may bridge this gap.
...
...

References

SHOWING 1-10 OF 32 REFERENCES
Performance of Activity Classification Algorithms in Free-Living Older Adults.
TLDR
Algorithms developed on free-living accelerometer data were more accurate in classifying the activity type infree-living older adults than those on algorithms developed on laboratory accelerometers.
Objective Assessment of Physical Activity: Classifiers for Public Health.
TLDR
New machine learning classifiers developed from prescribed activities were considerably less accurate when applied to free-living populations or to a functionally different population (studies 2 and 3), but may have value when applications are applied to large cohort studies with existing hip accelerometer data.
Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification.
TLDR
Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm, particularly in comparison with traditional cut points.
Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough.
TLDR
An automatic classification algorithm initially developed using laboratory-acquired data to discriminate between 8 activity classes was applied to data collected in the field, and recalibrating the algorithm with data closer to real-life conditions and from an independent group of subjects proved useful for the detection of sedentary behaviors while in transports.
Using the SenseCam to improve classifications of sedentary behavior in free-living settings.
Predicting human movement with multiple accelerometers using movelets.
TLDR
It is possible to achieve high prediction accuracy at the second-level temporal resolution with very limited training data and to increase prediction accuracy from the simultaneous use of multiple accelerometers, a careful selection of integrative approaches is required.
Methods to estimate aspects of physical activity and sedentary behavior from high-frequency wrist accelerometer measurements.
TLDR
Preliminary investigation of the models' performance on two free-living people suggests that they may work well outside of controlled conditions.
Comparison of Self-Reported and Accelerometer-Assessed Physical Activity in Older Women
TLDR
Triaxial count data do not substantially reduce the difference between self-reported and accelerometer-assessed MVPA, and recent accelerometer models assess accelerations in three axes, instead of only the vertical axis.
Using accelerometers to measure physical activity in large-scale epidemiological studies: issues and challenges
TLDR
Important data on the health effects of light-intensity activity and sedentary behaviour will emerge from large-scale epidemiological studies collecting objective assessments of these behaviours.
...
...