scholarly journals Eating and Drinking Recognition in Free-Living Conditions for Triggering Smart Reminders

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2803 ◽  
Author(s):  
Diana Gomes ◽  
João Mendes-Moreira ◽  
Inês Sousa ◽  
Joana Silva
Keyword(s):  
Binary Classification ◽  
Developed Countries ◽  
Recognition Algorithm ◽  
Living Conditions ◽  
Classification Model ◽  
Classification Models ◽  
Free Living ◽  
Multi Class Classification ◽  
Medication Taking Behavior ◽  
Free Living Conditions

The increasingly aging society in developed countries has raised attention to the role of technology in seniors’ lives, namely concerning isolation-related issues. Independent seniors that live alone frequently neglect meals, hydration and proper medication-taking behavior. This work aims at eating and drinking recognition in free-living conditions for triggering smart reminders to autonomously living seniors, keeping system design considerations, namely usability and senior-acceptance criteria, in the loop. To that end, we conceived a new dataset featuring accelerometer and gyroscope wrist data to conduct the experiments. We assessed the performance of a single multi-class classification model when compared against several binary classification models, one for each activity of interest (eating vs. non-eating; drinking vs. non-drinking). Binary classification models performed consistently better for all tested classifiers (k-NN, Naive Bayes, Decision Tree, Multilayer Perceptron, Random Forests, HMM). This evidence supported the proposal of a semi-hierarchical activity recognition algorithm that enabled the implementation of two distinct data stream segmentation techniques, the customization of the classification models of each activity of interest and the establishment of a set of restrictions to apply on top of the classification output, based on daily evidence. An F1-score of 97% was finally attained for the simultaneous recognition of eating and drinking in an all-day acquisition from one young user, and 93% in a test set with 31 h of data from 5 different unseen users, 2 of which were seniors. These results were deemed very promising towards solving the problem of food and fluids intake monitoring with practical systems which shall maximize user-acceptance.

scholarly journals Machine Learning Models for Classifying Physical Activity in Free-Living Preschool Children

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4364 ◽  
Author(s):  
Matthew N. Ahmadi ◽  
Toby G. Pavey ◽  
Stewart G. Trost
Keyword(s):  
Machine Learning ◽  
Free Play ◽  
Living Conditions ◽  
Accelerometer Data ◽  
Classification Models ◽  
Activity Classification ◽  
Free Living ◽  
Percentage Points ◽  
Temporal Features ◽  
Free Living Conditions

Machine learning (ML) activity classification models trained on laboratory-based activity trials exhibit low accuracy under free-living conditions. Training new models on free-living accelerometer data, reducing the number of prediction windows comprised of multiple activity types by using shorter windows, including temporal features such as standard deviation in lag and lead windows, and using multiple sensors may improve the classification accuracy under free-living conditions. The objective of this study was to evaluate the accuracy of Random Forest (RF) activity classification models for preschool-aged children trained on free-living accelerometer data. Thirty-one children (mean age = 4.0 ± 0.9 years) completed a 20 min free-play session while wearing an accelerometer on their right hip and non-dominant wrist. Video-based direct observation was used to categorize the children’s movement behaviors into five activity classes. The models were trained using prediction windows of 1, 5, 10, and 15 s, with and without temporal features. The models were evaluated using leave-one-subject-out-cross-validation. The F-scores improved as the window size increased from 1 to 15 s (62.6%–86.4%), with only minimal improvements beyond the 10 s windows. The inclusion of temporal features increased the accuracy, mainly for the wrist classification models, by an average of 6.2 percentage points. The hip and combined hip and wrist classification models provided comparable accuracy; however, both the models outperformed the models trained on wrist data by 7.9 to 8.2 percentage points. RF activity classification models trained with free-living accelerometer data provide accurate recognition of young children’s movement behaviors under real-world conditions.

Safety and Performance of the Omnipod®Hybrid Closed-Loop System in Adolescents with Type 1 Diabetes over Five Days Under Free-Living Conditions

Diabetes ◽  
2018 ◽  
Vol 67 (Supplement 1) ◽  
pp. 1376-P
Author(s):  
GREGORY P. FORLENZA ◽  
BRUCE BUCKINGHAM ◽  
JENNIFER SHERR ◽  
THOMAS A. PEYSER ◽  
JOON BOK LEE ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Closed Loop ◽  
Living Conditions ◽  
Loop System ◽  
Closed Loop System ◽  
Free Living ◽  
And Performance ◽  
Free Living Conditions

Safety and Performance of the Omnipod® Hybrid Closed-Loop System in Adults with Type 1 Diabetes over Five Days Under Free-Living Conditions

Diabetes ◽  
2018 ◽  
Vol 67 (Supplement 1) ◽  
pp. 207-OR
Author(s):  
BRUCE A. BUCKINGHAM ◽  
JENNIFER SHERR ◽  
GREGORY P. FORLENZA ◽  
THOMAS A. PEYSER ◽  
JOON BOK LEE ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Closed Loop ◽  
Living Conditions ◽  
Loop System ◽  
Closed Loop System ◽  
Free Living ◽  
And Performance ◽  
Free Living Conditions

scholarly journals Data-driven modelling approach to circadian temperature rhythm profiles in free-living conditions

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jari Lipsanen ◽  
Liisa Kuula ◽  
Marko Elovainio ◽  
Timo Partonen ◽  
Anu-Katriina Pesonen
Keyword(s):  
Skin Surface ◽  
Living Conditions ◽  
Data Driven ◽  
Physiological Data ◽  
Free Living ◽  
Physiological Level ◽  
Temperature Rhythm ◽  
Time Series Modelling ◽  
Circadian Preference ◽  
Free Living Conditions

AbstractThe individual variation in the circadian rhythms at the physiological level is not well understood. Albeit self-reported circadian preference profiles have been consolidated, their premises are grounded on human experience, not on physiology. We used data-driven, unsupervised time series modelling to characterize distinct profiles of the circadian rhythm measured from skin surface temperature in free-living conditions. We demonstrate the existence of three distinct clusters of individuals which differed in their circadian temperature profiles. The cluster with the highest temperature amplitude and the lowest midline estimating statistic of rhythm, or rhythm-adjusted mean, had the most regular and early-timed sleep–wake rhythm, and was the least probable for those with a concurrent delayed sleep phase, or eveningness chronotype. While the clusters associated with the observed sleep and circadian preference patterns, the entirely unsupervised modelling of physiological data provides a novel basis for modelling and understanding the human circadian functions in free-living conditions.

Invariance of Wearing Location of Omron-BI Pedometers: A Validation Study

2010 ◽  
Vol 7 (6) ◽  
pp. 706-717 ◽  
Author(s):  
Weimo Zhu ◽  
Miyoung Lee
Keyword(s):  
Validation Study ◽  
Absolute Error ◽  
Activity Monitor ◽  
Error Rates ◽  
Living Conditions ◽  
The Body ◽  
Validity And Reliability ◽  
Free Living ◽  
Climbing Stairs ◽  
Free Living Conditions

Background:The purpose of this study was to investigate the validity and reliability evidences of the Omron BI pedometer, which could count steps taken even when worn at different locations on the body.Methods:Forty (20 males and 20 females) adults were recruited to walk wearing 5 sets, 1 set at a time, of 10 BI pedometers during testing, 1 each at 10 different locations. For comparison, they also wore 2 Yamax Digi-Walker SW-200 pedometers and a Dynastream AMP 331 activity monitor. The subjects walked in 3 free-living conditions: a fat sidewalk, stairs, and mixed conditions.Results:Except for a slight decrease in accuracy in the pant pocket locations, Omron BI pedometers counted steps accurately across other locations when subjects walked on the fat sidewalk, and the performance was consistent across devices and trials. When the subjects climbed up stairs, however, the absolute error % of the pant pocket locations increased significantly (P < .05) and similar or higher error rates were found in the AMP 331 and SW-200s.Conclusions:The Omron BI pedometer can accurately count steps when worn at various locations on the body in free-living conditions except for front pant pocket locations, especially when climbing stairs.

scholarly journals Substantial Intra-Individual Variability in Post-Prandial Time to Peak in Controlled and Free-Living Conditions in Children with Type 1 Diabetes

Nutrients ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 4154
Author(s):  
Emily Bell ◽  
Sabrina Binkowski ◽  
Elaine Sanderson ◽  
Barbara Keating ◽  
Grant Smith ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Individual Variability ◽  
Living Conditions ◽  
Optimal Time ◽  
Daily Routine ◽  
Free Living ◽  
Continuous Glucose Monitor ◽  
Time To Peak ◽  
Free Living Conditions

The optimal time to bolus insulin for meals is challenging for children and adolescents with type 1 diabetes (T1D). Current guidelines to control glucose excursions do not account for individual differences in glycaemic responses to meals. This study aimed to examine the within- and between-person variability in time to peak (TTP) glycaemic responses after consuming meals under controlled and free-living conditions. Participants aged 8–15 years with T1D ≥ 1 year and using a continuous glucose monitor (CGM) were recruited. Participants consumed a standardised breakfast for six controlled days and maintained their usual daily routine for 14 free-living days. CGM traces were collected after eating. Linear mixed models were used to identify within- and between-person variability in the TTP after each of the controlled breakfasts, free-living breakfasts (FLB), and free-living dinners (FLD) conditions. Thirty participants completed the study (16 females; mean age and standard deviation (SD) 10.5 (1.9)). The TTP variability was greater within a person than the variability between people for all three meal types (between-person vs within-person SD; controlled breakfast 18.5 vs 38.9 minutes; FLB 14.1 vs 49.6 minutes; FLD 5.7 vs 64.5 minutes). For the first time, the study showed that within-person variability in TTP glycaemic responses is even greater than between-person variability.

Validity, Reliability and Sensitivity to Change of Three Consumer-grade Activity Trackers in Controlled and Free-living Conditions among Older Adults (Preprint)

2021 ◽  
Author(s):  
Kaja Kastelic ◽  
Marina Dobnik ◽  
Stefan Loefler ◽  
Christian Hofer ◽  
Nejc Šarabon
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
Intraclass Correlation ◽  
Sleep Time ◽  
Living Conditions ◽  
Percentage Error ◽  
Sensitivity To Change ◽  
Free Living ◽  
Activity Trackers ◽  
Free Living Conditions

BACKGROUND Wrist worn consumer-grade activity trackers are popular devices, developed mainly for personal use, but with the potential to be used also for clinical and research purposes. OBJECTIVE The objective of this study was to explore the validity, reliability and sensitivity to change of movement behaviours metrics from three popular activity trackers (POLAR Vantage M, Garmin Vivosport and Garmin Vivoactive 4s) in controlled and free-living conditions when worn by older adults. METHODS Participants (n = 28; 74 ± 5 years) underwent a videotaped laboratory protocol while wearing all three activity trackers. On a separate occasion, participants wore one (randomly assigned) activity tracker and a research grade physical activity monitor ActiGraph wGT3X-BT simultaneously for six consecutive days for comparisons. RESULTS Both Garmin activity trackers showed excellent performance for step counts, with mean absolute percentage error (MAPE) below 20 % and intraclass correlation coefficient (ICC2,1) above 0.90 (P < .05), while Polar Vantage M substantially over counted steps (MAPE = 84 % and ICC2,1 = 0.37 for free-living conditions). MAPE for sleep time was within 10 % for all the trackers tested, while far beyond 20 % for all the physical activity and calories burned outputs. Both Garmin trackers showed fair agreement (ICC2,1 = 0.58–0.55) for measuring calories burned when compared with ActiGraph. CONCLUSIONS Garmin Vivoactive 4s showed overall best performance, especially for measuring steps and sleep time in healthy older adults. Minimal detectible change was consistently lower for an average day measures than for a single day measure, but still relatively high. The results provided in this study could be used to guide choice on activity trackers aiming for different purposes – individual use/care, longitudinal monitoring or in clinical trial setting.

Sign in / Sign up

Export Citation Format

Share Document