Dataset Information

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis.

ABSTRACT: Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands ? 3 , 8 ? and ? 8 , 15 ? Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.

SUBMITTER: Charvatova H

PROVIDER: S-EPMC7085619 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis.

Charvátová Hana H Procházka Aleš A Vyšata Oldřich O

Sensors (Basel, Switzerland) 20200310 5

Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon d ...[more]

PMID: 32164235

Similar Datasets

Project description:Background: Performance of wrist actigraphy in assessing sleep not only depends on the sensor technology of the actigraph hardware but also on the attributes of the interpretative algorithm (IA). The objective of our research was to improve assessment of sleep quality, relative to existing IAs, through development of a novel IA using deep learning methods, utilizing as input activity count and heart rate variability (HRV) metrics of different window length (number of epochs of data). Methods: Simultaneously recorded polysomnography (PSG) and wrist actigraphy data of 222 participants were utilized. Classic deep learning models were applied to: (a) activity count alone (without HRV), (b) activity count + HRV (30-s window), (c) activity count + HRV (3-min window), and (d) activity count + HRV (5-min window) to ascertain the best set of inputs. A novel deep learning model (Haghayegh Algorithm, HA), founded on best set of inputs, was developed, and its sleep scoring performance was then compared with the most popular University of California San Diego (UCSD) and Actiwatch proprietary IAs. Results: Activity count combined with HRV metrics calculated per 5-min window produced highest agreement with PSG. HA showed 84.5% accuracy (5.3-6.2% higher than comparator IAs), 89.5% sensitivity (6.2% higher than UCSD IA and 6% lower than Actiwatch proprietary IA), 70.0% specificity (8.2-34.3% higher than comparator IAs), and 58.7% Kappa agreement (16-23% higher than comparator IAs) in detecting sleep epochs. HA did not differ significantly from PSG in deriving sleep parameters-sleep efficiency, total sleep time, sleep onset latency, and wake after sleep onset; moreover, bias and mean absolute error of the HA model in estimating them was less than the comparator IAs. HA showed, respectively, 40.9% and 54.0% Kappa agreement with PSG in detecting rapid and non-rapid eye movement (REM and NREM) epochs. Conclusions: The HA model simultaneously incorporating activity count and HRV metrics calculated per 5-min window demonstrates significantly better sleep scoring performance than existing popular IAs.

Project description:OBJECTIVE:Although high intensity physical activities may represent a great proportion of the total energy expenditure in active people, only sparse studies have investigated the accuracy of wearable monitors to assess activity related energy expenditure (AEE) during high intensity exercises. Therefore, the purpose of the present study was to investigate the accuracy of the Actiheart, a light portable monitor estimating AEE based on heart rate (HR) and activity counts (ACT), during two popular activities (running and cycling) performed at high intensities. The benefit of an individual calibration of the HR-AEE relationship established during a preliminary maximal test was also evaluated. METHODS:AEE was estimated in eighteen active adults (4 women and 14 men; 25 ± 4 yr) with indirect calorimetry using a respiratory gas analysis system (reference method) and the Actiheart during 5-min running and cycling at 60, 75 and 85% of maximal oxygen uptake (VO2max) previously determined during a maximal test performed on a treadmill or cycle ergometer. For the Actiheart, AEE was estimated either using the group or individual calibrated equations available in the dedicated software, and their respective HR, ACT or combined HR/ACT algorithms. RESULTS:When the HR algorithm was used for cycling and the HR or HR/ACT algorithms for running, AEE measured by the Actiheart increased proportionally to exercise intensity from 60 to 85% VO2max (P<0.001). Compared to indirect calorimetry, the Actiheart group calibrated equations slightly to moderately underestimated (3 to 20%) AEE for the three exercise intensities (P<0.001). Accuracy of AEE estimation was greatly improved by individual calibration of the HR-AEE relationship (underestimation below 5% and intraclass correlation coefficient [ICC]: 0.79-0.93) compared to group calibration (ICC: 0.64-0.79). CONCLUSION:The Actiheart enables to assess AEE during high intensity running and cycling when the appropriate algorithm is applied. Since an underestimation was present for group calibration, an individual and sport-specific calibration should be performed when a high accuracy is required.

Project description:Because of unreliable self-report, accelerometry is increasingly used to objectively monitor physical activity (PA). However, results of accelerometric studies vary depending on the chosen cutpoints between activity intensities. Population-specific activity patterns likely affect the size of these differences. To establish their size and stability we apply three sets of cutpoints, including two calibrated to a single reference, to our accelerometric data and compare PA estimates.1402 German adolescents from the GINIplus and LISAplus cohorts wore triaxial accelerometers (Actigraph GT3x) for one week (mean 6.23 days, 14.7 hours per day) at the hip. After validation of wear, we applied three sets of cutpoints for youth, including the most common standard (Freedson, 2005) and two calibrated to a single reference, (Romanzini uni- and triaxial, from Romanzini, 2014) to these data, estimating daily sedentary, light, moderate, vigorous and moderate-to-vigorous PA (MPA, VPA, MVPA). Stability of differences was assessed by comparing Romanzini's two sets of cutpoints.Relative agreement between cutpoints was closer for activity of lower intensities (largest difference for sedentary behaviour 9%) but increased for higher intensities (largest difference for light activity 40%, MPA 102%, VPA 88%; all p<0.01). Romanzini's uniaxial and triaxial cutpoints agreed no more closely with each other than with Freedson's.Estimated PA differed significantly between different sets of cutpoints, even when those cutpoints agreed perfectly on another dataset (i.e. Romanzini's.) This suggests that the detected differences in estimated PA depend on population-specific activity patterns, which cannot be easily corrected for: converting activity estimates from one set of cutpoints to another may require access to raw data. This limits the utility of accelerometry for comparing populations in place and time. We suggest that accelerometric research adopt a standard for data processing, and apply and present the results of this standard in addition to those from any other method.

Project description:IntroductionThe heart rate (HR) method is a promising approach for evaluating oxygen uptake ([Formula: see text]), energy demands and exercise intensities in different forms of physical activities. It would be valuable if the HR method, established on ergometer cycling, is interchangeable with other regular activities, such as level walking. This study therefore aimed to examine the interchangeability of the HR method when estimating [Formula: see text] for ergometer cycling and level treadmill walking in submaximal conditions.MethodsTwo models of [Formula: see text] regression equations for cycle ergometer exercise (CEE) and treadmill exercise (TE) were established with 34 active commuters. Model 1 consisted of three submaximal intensities of ergometer cycling or level walking, model 2 included also one additional workload of maximal ergometer cycling or running. The regression equations were used for estimating [Formula: see text] with seven individual HR values based on 25-85% of HR reserve (HRR). The [Formula: see text] estimations were compared between CEE and TE, within and between each model.ResultsOnly minor, and in most cases non-significant, average differences were observed when comparing the estimated [Formula: see text] levels between CEE and TE. Model 1 ranged from -0.4 to 4.8% (n.s.) between 25-85%HRR. In model 2, the differences between 25-65%HRR ranged from 1.3 to -2.7% (n.s.). At the two highest intensities, 75 and 85%HRR, [Formula: see text] was slightly lower (3.7%, 4.4%; P < 0.05), for CEE than TE. The inclusion of maximal exercise in the [Formula: see text] relationships reduced the individual [Formula: see text] variations between the two exercise modalities.ConclusionThe HR methods, based on submaximal ergometer cycling and level walking, are interchangeable for estimating mean [Formula: see text] levels between 25-85% of HRR. Essentially, the same applies when adding maximal exercise in the [Formula: see text] relationships. The inter-individual [Formula: see text] variation between ergometer cycling and treadmill exercise is reduced when using the HR method based on both submaximal and maximal workloads.

Dataset Information

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis.

Publications

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets