Minimum message length encoding

Conventionally subjective methods are often employed for the assessment of fatigue. These approaches are prone to error and inaccuracy. Quantitative methods in a very limited extent have been applied. Inertial sensors and a Six Minute Walking Test (6MWT) are employed to measure gait and posture characteristics before and after a repeated sit and stand task that induces a degree of fatigue. Using a set of 17 sensors, the inertial signals corresponding to position, velocity, acceleration, orientation, angular velocity and angular acceleration are recorded based on a 23 degree of freedom humanoid model. The data streams obtained are subsequently segmented by an intrinsic clustering algorithm known as Minimum Message Length encoding (MML) forming a Gaussian Mixture Model (GMM). Several postural states (exemplar motion primitives) are captured in the resultant model, which is subsequently utilized to derive a holistic index corresponding to the physical ambulatory status of patient. The proposed method is applied to both data collected pre- and post-fatigue performance. The results are encouraging as they clearly demonstrate that fatigue affects physical status during 6MWT. The current results are promising in the development of an objective fatigue assessment tool for different patients.