•  
  •  
 

Abstract

Many tetraplegics must wear wrist braces to support paralyzed wrists and hands. However, current wrist orthoses have limited functionality to assist a person’s ability to perform typical activities of daily living other than a small pocket to hold utensils. To enhance the functionality of wrist orthoses, gesture recognition technology can be applied to control mechatronic tools attached to a novel fabricated wrist brace. Gesture recognition is a growing technology for providing touchless human-computer interaction that can be particularly useful for tetraplegics with limited upper-extremity mobility. In this study, three gesture recognition models were compared—two dynamic time-warping models and a hidden Markov model—in terms of their classification accuracy of gestures from a gesture lexicon known to be accessible to tetraplegics. Gesture data from participants with and without spinal cord injuries was collected using a prototype wrist orthosis. Leave-one-subject-out cross-validation was used to develop a user-independent gesture recognition library. The trained models were then tested using a combination of data from both populations and data separated by population. The classification accuracy and classification time were computed and compared to determine the optimal gesture recognition model.

Share

COinS