Dataset Information

Estimating physical activity energy expenditure with the Kinect Sensor in an exergaming environment.

ABSTRACT: Active video games that require physical exertion during game play have been shown to confer health benefits. Typically, energy expended during game play is measured using devices attached to players, such as accelerometers, or portable gas analyzers. Since 2010, active video gaming technology incorporates marker-less motion capture devices to simulate human movement into game play. Using the Kinect Sensor and Microsoft SDK this research aimed to estimate the mechanical work performed by the human body and estimate subsequent metabolic energy using predictive algorithmic models. Nineteen University students participated in a repeated measures experiment performing four fundamental movements (arm swings, standing jumps, body-weight squats, and jumping jacks). Metabolic energy was captured using a Cortex Metamax 3B automated gas analysis system with mechanical movement captured by the combined motion data from two Kinect cameras. Estimations of the body segment properties, such as segment mass, length, centre of mass position, and radius of gyration, were calculated from the Zatsiorsky-Seluyanov's equations of de Leva, with adjustment made for posture cost. GPML toolbox implementation of the Gaussian Process Regression, a locally weighted k-Nearest Neighbour Regression, and a linear regression technique were evaluated for their performance on predicting the metabolic cost from new feature vectors. The experimental results show that Gaussian Process Regression outperformed the other two techniques by a small margin. This study demonstrated that physical activity energy expenditure during exercise, using the Kinect camera as a motion capture system, can be estimated from segmental mechanical work. Estimates for high-energy activities, such as standing jumps and jumping jacks, can be made accurately, but for low-energy activities, such as squatting, the posture of static poses should be considered as a contributing factor. When translated into the active video gaming environment, the results could be incorporated into game play to more accurately control the energy expenditure requirements.

SUBMITTER: Nathan D

PROVIDER: S-EPMC4441447 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimating physical activity energy expenditure with the Kinect Sensor in an exergaming environment.

Nathan David D Huynh Du Q du Q Rubenson Jonas J Rosenberg Michael M

PloS one 20150522 5

Active video games that require physical exertion during game play have been shown to confer health benefits. Typically, energy expended during game play is measured using devices attached to players, such as accelerometers, or portable gas analyzers. Since 2010, active video gaming technology incorporates marker-less motion capture devices to simulate human movement into game play. Using the Kinect Sensor and Microsoft SDK this research aimed to estimate the mechanical work performed by the hum ...[more]

PMID: 26000460

Similar Datasets

Project description:Wearable physical activity monitors are growing in popularity and provide the opportunity for large numbers of the public to self-monitor physical activity behaviours. The latest generation of these devices feature multiple sensors, ostensibly similar or even superior to advanced research instruments. However, little is known about the accuracy of their energy expenditure estimates. Here, we assessed their performance against criterion measurements in both controlled laboratory conditions (simulated activities of daily living and structured exercise) and over a 24 hour period in free-living conditions. Thirty men (n = 15) and women (n = 15) wore three multi-sensor consumer monitors (Microsoft Band, Apple Watch and Fitbit Charge HR), an accelerometry-only device as a comparison (Jawbone UP24) and validated research-grade multi-sensor devices (BodyMedia Core and individually calibrated Actiheart™). During discrete laboratory activities when compared against indirect calorimetry, the Apple Watch performed similarly to criterion measures. The Fitbit Charge HR was less consistent at measurement of discrete activities, but produced similar free-living estimates to the Apple Watch. Both these devices underestimated free-living energy expenditure (-394 kcal/d and -405 kcal/d, respectively; P<0.01). The multi-sensor Microsoft Band and accelerometry-only Jawbone UP24 devices underestimated most laboratory activities and substantially underestimated free-living expenditure (-1128 kcal/d and -998 kcal/d, respectively; P<0.01). None of the consumer devices were deemed equivalent to the reference method for daily energy expenditure. For all devices, there was a tendency for negative bias with greater daily energy expenditure. No consumer monitors performed as well as the research-grade devices although in some (but not all) cases, estimates were close to criterion measurements. Thus, whilst industry-led innovation has improved the accuracy of consumer monitors, these devices are not yet equivalent to the best research-grade devices or indeed equivalent to each other. We propose independent quality standards and/or accuracy ratings for consumer devices are required.

Project description:Accurate, nonintrusive, and feasible methods are needed to predict energy expenditure (EE) and physical activity (PA) levels in preschoolers. Herein, we validated cross-sectional time series (CSTS) and multivariate adaptive regression splines (MARS) models based on accelerometry and heart rate (HR) for the prediction of EE using room calorimetry and doubly labeled water (DLW) and established accelerometry cut points for PA levels.Fifty preschoolers, mean ± SD age of 4.5 ± 0.8 yr, participated in room calorimetry for minute-by-minute measurements of EE, accelerometer counts (AC) (Actiheart and ActiGraph GT3X+), and HR (Actiheart). Free-living 105 children, ages 4.6 ± 0.9 yr, completed the 7-d DLW procedure while wearing the devices. AC cut points for PA levels were established using smoothing splines and receiver operating characteristic curves.On the basis of calorimetry, mean percent errors for EE were -2.9% ± 10.8% and -1.1% ± 7.4% for CSTS models and -1.9% ± 9.6% and 1.3% ± 8.1% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. On the basis of DLW, mean percent errors were -0.5% ± 9.7% and 4.1% ± 8.5% for CSTS models and 3.2% ± 10.1% and 7.5% ± 10.0% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. Applying activity EE thresholds, final accelerometer cut points were determined: 41, 449, and 1297 cpm for Actiheart x-axis; 820, 3908, and 6112 cpm for ActiGraph vector magnitude; and 240, 2120, and 4450 cpm for ActiGraph x-axis for sedentary/light, light/moderate, and moderate/vigorous PA (MVPA), respectively. On the basis of confusion matrices, correctly classified rates were 81%-83% for sedentary PA, 58%-64% for light PA, and 62%-73% for MVPA.The lack of bias and acceptable limits of agreement affirms the validity of the CSTS and MARS models for the prediction of EE in preschool-aged children. Accelerometer cut points are satisfactory for the classification of sedentary, light, and moderate/vigorous levels of PA in preschoolers.

Project description:BackgroundResearch has shown the feasibility of human activity recognition using wearable accelerometer devices. Different studies have used varying numbers and placements for data collection using sensors.ObjectiveThis study aims to compare accuracy performance between multiple and variable placements of accelerometer devices in categorizing the type of physical activity and corresponding energy expenditure in older adults.MethodsIn total, 93 participants (mean age 72.2 years, SD 7.1) completed a total of 32 activities of daily life in a laboratory setting. Activities were classified as sedentary versus nonsedentary, locomotion versus nonlocomotion, and lifestyle versus nonlifestyle activities (eg, leisure walk vs computer work). A portable metabolic unit was worn during each activity to measure metabolic equivalents (METs). Accelerometers were placed on 5 different body positions: wrist, hip, ankle, upper arm, and thigh. Accelerometer data from each body position and combinations of positions were used to develop random forest models to assess activity category recognition accuracy and MET estimation.ResultsModel performance for both MET estimation and activity category recognition were strengthened with the use of additional accelerometer devices. However, a single accelerometer on the ankle, upper arm, hip, thigh, or wrist had only a 0.03-0.09 MET increase in prediction error compared with wearing all 5 devices. Balanced accuracy showed similar trends with slight decreases in balanced accuracy for the detection of locomotion (balanced accuracy decrease range 0-0.01), sedentary (balanced accuracy decrease range 0.05-0.13), and lifestyle activities (balanced accuracy decrease range 0.04-0.08) compared with all 5 placements. The accuracy of recognizing activity categories increased with additional placements (accuracy decrease range 0.15-0.29). Notably, the hip was the best single body position for MET estimation and activity category recognition.ConclusionsAdditional accelerometer devices slightly enhance activity recognition accuracy and MET estimation in older adults. However, given the extra burden of wearing additional devices, single accelerometers with appropriate placement appear to be sufficient for estimating energy expenditure and activity category recognition in older adults.

Dataset Information

Estimating physical activity energy expenditure with the Kinect Sensor in an exergaming environment.

Publications

Estimating physical activity energy expenditure with the Kinect Sensor in an exergaming environment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets