Feature-Based Gait Pattern Modeling on a Treadmill

Abstract

In this paper, we present a method of gait analysis on a treadmill based on pressure distribution. We aimed to model the gait patterns of a subject walking at a constant speed on a treadmill based on differences in current consumption. The changes in current consumption were converted into pressure distribution curves, and then specific features were extracted. The extracted features were used to model the walking pattern on a treadmill. To verify the validity of our proposed feature-based gait pattern modeling, we conducted experiments by gender, age, BMI (body mass index), and step-to-step symmetry. The experimental results showed that the heavier the subject, the higher the value of each feature. In particular, our feature point-based gait modeling provides an index that can help determine whether a subject’s gait is abnormal, depending on the difference between the features.