Field based assessment of a tri-axial accelerometers validity to identify steps and reliability to quantify external load

Bursais, Abdulmalek K.; Gentles, Jeremy A.; Albujulaya, Naif M.; Stone, Michael H.

doi:10.3389/fphys.2022.942954

Cited by 2 publications

(1 citation statement)

References 33 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These studies have used inertial sensors such as acceleration sensors and gyroscopes, or heart-rate sensors. In particular, acceleration sensors have been often used in studies on physical activity monitoring ( Qi et al, 2018 ; Bursais et al, 2022 ; Huber et al, 2022 ; Werner et al, 2022 ). They are widely installed in consumer wearable devices and smartphones ( Johnston et al, 2019 ), and features estimated from recorded accelerations such as postures, are useful for understanding the patient’s condition, risks, and lifestyle ( Antar et al, 2019 ; Pohl et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Ensemble averaging for categorical variables: Validation study of imputing lost data in 24-h recorded postures of inpatients

Ogasawara

Mukaino²,

Matsuura³

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Acceleration sensors are widely used in consumer wearable devices and smartphones. Postures estimated from recorded accelerations are commonly used as features indicating the activities of patients in medical studies. However, recording for over 24 h is more likely to result in data losses than recording for a few hours, especially when consumer-grade wearable devices are used. Here, to impute postures over a period of 24 h, we propose an imputation method that uses ensemble averaging. This method outputs a time series of postures over 24 h with less lost data by calculating the ratios of postures taken at the same time of day during several measurement-session days. Whereas conventional imputation methods are based on approaches with groups of subjects having multiple variables, the proposed method imputes the lost data variables individually and does not require other variables except posture. We validated the method on 306 measurement data from 99 stroke inpatients in a hospital rehabilitation ward. First, to classify postures from acceleration data measured by a wearable sensor placed on the patient’s trunk, we preliminary estimated possible thresholds for classifying postures as ‘reclining’ and ‘sitting or standing’ by investigating the valleys in the histogram of occurrences of trunk angles during a long-term recording. Next, the imputations of the proposed method were validated. The proposed method significantly reduced the missing data rate from 5.76% to 0.21%, outperforming a conventional method.

show abstract