Name
Title | ||
|---|---|---|
Hierarchical Approaches to Estimate Energy Expenditure Using Phone-Based Accelerometers |
Abstract | ||
|---|---|---|
Physical inactivity is linked with increase in risk of cancer, heart disease, stroke, and diabetes. Walking is an easily available activity to reduce sedentary time. Objective methods to accurately assess energy expenditure from walking that is normalized to an individual would allow tailored interventions. Current techniques rely on normalization by weight scaling or fitting a polynomial function of weight and speed. Using the example of steady-state treadmill walking, we present a set of algorithms that extend previous work to include an arbitrary number of anthropometric descriptors. We specifically focus on predicting energy expenditure using movement measured by mobile phone-based accelerometers. The models tested include nearest neighbor models, weight-scaled models, a set of hierarchical linear models, multivariate models, and speed-based approaches. These are compared for prediction accuracy as measured by normalized average root mean-squared error across all participants. Nearest neighbor models showed highest errors. Feature combinations corresponding to sedentary energy expenditure, sedentary heart rate, and sex alone resulted in errors that were higher than speed-based models and nearest-neighbor models. Size-based features such as BMI, weight, and height produced lower errors. Hierarchical models performed better than multivariate models when size-based features were used. We used the hierarchical linear model to determine the best individual feature to describe a person. Weight was the best individual descriptor followed by height. We also test models for their ability to predict energy expenditure with limited training data. Hierarchical models outperformed personal models when a low amount of training data were available. Speed-based models showed poor interpolation capability, whereas hierarchical models showed uniform interpolation capabilities across speeds. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/JBHI.2013.2297055 | Biomedical and Health Informatics, IEEE Journal of |
Keywords | Field | DocType |
accelerometers,biomedical measurement,cancer,gait analysis,interpolation,medical computing,mobile computing,mobile handsets,BMI,anthropometric descriptors,cancer,diabetes,heart disease,hierarchical approaches,hierarchical linear model,hierarchical linear models,interpolation capabilities,mobile phone-based accelerometers,multivariate models,nearest neighbor models,normalized average root mean-squared error,physical inactivity,polynomial function,sedentary energy expenditure estimation,sedentary heart rate,speed-based approaches,speed-based models,steady-state treadmill walking,stroke,training data,weight scaling,weight-scaled models,Accelerometer,energy expenditure,hierarchical model,mobile phone,treadmill walking | k-nearest neighbors algorithm,Data modeling,Normalization (statistics),Pattern recognition,Multilevel model,Multivariate statistics,Accelerometer,Computer science,Interpolation,Artificial intelligence,Statistics,Hierarchical database model | Journal |
Volume | Issue | ISSN |
18 | 4 | 2168-2194 |
Citations | PageRank | References |
6 | 0.63 | 6 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Harshvardhan Vathsangam | 1 | 92 | 8.42 |
| E Todd Schroeder | 2 | 28 | 2.92 |
| Gaurav S. Sukhatme | 3 | 5469 | 548.13 |