Asynchronous Averaging of Gait Cycles for Classification of Gait and Device Modes

The problem of joint classification gait and device mode from inertial measurement units (IMU) measurements is considered. For this, an approach for computing unique signature using collected body-worn (IMUs) proposed.The represents one full cycle the human gait, suitable off-line or on-line mode. can also be used to jointly classify identifies how IMU-equipped being carried by user. method based on precise segmentation resampling measured IMU signal, as initial step, further tuned minimizing variability obtained within each cycle. Finally, a Fourier series expansion introduced which provides low-dimensional feature vector well suited purposes. proposed evaluated large dataset involving several subjects, containing two different modes four modes.