Initial features considered for testing in the model

FactorsComment or explanation
Fourier transform of Respeck signalNormalised as Embedded Image
Mean, median and standard deviation of individual breathing ratesExtreme values are less likely to be reliable
A smaller standard deviation reflects more regular breathing
Maximum–minimum rateA large range of rates within the sampling window would be less trustworthy
Mean and median of differencesMean and median of frequency differences between one breath and the next within the window
Standard deviation of axis acceleration valuesA measure of large changes in axis signal, often associated with posture changes
Standard deviation, median and skew of activity levelsActivity level is computed as the length of the vector differences using the x, y and z coordinates
Standard deviation of Respeck signalA large standard deviation indicates probable posture change
Number of valid breathsA small number of detected breaths suggests the signal is unreliable
Standard deviation of Respeck amplitude peaksGreater variation in the size of breaths in a window suggests unstable breathing
Mean and median of peak differencesLarge differences between breath amplitudes suggest unstable breathing
Mean and median of peak intervalsTimes between successive peaks in the window should be similar

These are derived from the waveform of the Respeck signal, the accelerometer signals and the breath timing measurements.