Fusion of Heart Rate, Respiration and Motion Measurements from a Wearable Sensor System to Enhance Energy Expenditure Estimation

Abstract

This paper presents a new method that integrates heart rate, respiration, and motion information obtained from a wearable sensor system to estimate energy expenditure. The system measures electrocardiography, impedance pneumography, and acceleration from upper and lower limbs. A multilayer perceptron neural network model was developed, evaluated, and compared to two existing methods, with data from 11 subjects (mean age, 27 years, range, 21–65 years) who performed a 3-h protocol including submaximal tests, simulated work tasks, and periods of rest. Oxygen uptake was measured with an indirect calorimeter as a reference, with a time resolution of 15 s. When compared to the reference, the new model showed a lower mean absolute error (MAE = 1.65 mL/kg/min, R2 = 0.92) than the two existing methods, i.e., the flex-HR method (MAE = 2.83 mL/kg/min, R2 = 0.75), which uses only heart rate, and arm-leg HR+M method (MAE = 2.12 mL/kg/min, R2 = 0.86), which uses heart rate and motion information. As indicated, this new model may, in combination with a wearable system, be useful in occupational and general health applications.

Statistical Learning Methods to Predict Activity Intensity from Body-Worn Accelerometers

“…Similar findings were shown by Mackintosh et al (2016), who found that two-accelerometer systems had superior accuracy to systems of 3-8 accelerometers when assessing energy expenditure in children. As an alternate to using more accelerometers, using additional sensors alongside an accelerometer (within a single monitor or as a multi-monitor system), such as heart rate or gyroscope, has been shown to improve measurement of energy expenditure and may be considered as an option for further improvement of physical activity intensity assessment (O'Driscoll et al, 2018;Lu et al, 2018;Hibbing et al, 2018).…”

Fundamentals, Recent Advances, and Future Challenges in Bioimpedance Devices for Healthcare Applications

“…TIP has been used to measure lung volume changes [255], to evaluate respiratory condition during normal and deep breathing [256], the assessment of asthma risk from tidal flow variability [257], sleep disorders [258], energy expenditure estimation [259], or even the detection of body posture changes [260]. Another application of TIP is the gating of positron-emission tomography (PET) and singlephoton emission computed tomography (SPECT) images.…”

Data Analytics and Applications of the Wearable Sensors in Healthcare: An Overview

“…The promising results provided by this method showed its capability in characterizing high-dimensional time series patterns and providing useful information with wearable sensors in table tennis coaching. Lu et al [15] developed and tested a new method that combined information from heart rate, respiration, and accelerations measurements to estimate energy expenditure. These data measurements were taken from wearable sensor system and were integrated by neural network based model.…”