Linguistic description of the human gait quality

摘要

The human gait is a complex phenomenon that is repeated in time following an approximated pattern. Using a three-axial accelerometer fixed in the waist, we can obtain a temporal series of measures that contains a numerical description of this phenomenon. Nevertheless, even when we represent graphically these data, it is difficult to interpret them due to the complexity of the phenomenon and the huge amount of available data. This paper describes our research on designing a computational system able to generate linguistic descriptions of this type of quasi-periodic complex phenomena. We used our previous work on both, Granular Linguistic Models of Phenomena and Fuzzy Finite State Machines, to create a basic linguistic model of the human gait. We have used this model to generate a human friendly linguistic description of this phenomenon focused on the assessment of the gait quality. We include a practical application where we analyze the gait quality of healthy individuals and people with lesions in their limbs.