Classification of human gait based on fine Gaussian support vector machines using a force platform.

A force platform prototype for human gait classification as an alternative to vision-based and wearable sensor-based gait classification technologies is proposed. The primary sensors involved in this prototype were load cells. When a volunteer walks on the force platform, the load cells record signal changes corresponding to the walking pattern of the volunteer. These signals were digitized and amplified and stored in a micro-SD card. Five gait features were extracted from the stored data in the micro-SD card, and MATLAB classification learner was used for classification. An accuracy of 94% was observed with Fine Gaussian Support Vector Machines. This shows that the force platform is a good alternative to vision-based and wearable sensor-based gait classification technologies. [ABSTRACT FROM AUTHOR]