*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: A Physical Therapy System for Encouraging Specific Motion in Wrist Rehabilitation Exercises
Committee:
Dr. Ayanna Howard, ECE, Chair , Advisor
Dr. Linda Wills, ECE
Dr. Aaron Lanterman, ECE
Dr. David Anderson, ECE
Dr. Irfan Essa, CoC
Abstract:
The objective this research is to design a passive therapy device with rehabilitation gaming suite that employs an adaptive algorithm that alters game play in order to best fit the needs of the user. The goal of physical therapeutic exercises is to increase proficiency of a motor skill. Physical therapeutic exercises are commonly prescribed to individuals with motor disabilities. During the physical therapy process, individuals will usually practice once a week with the assistance of a clinician and six days a week in isolation. When practicing exercises in the presence of a skilled clinician, an individual receives several benefits including: (1) real-time feedback on accuracy of motions; (2) real-time adaptations to an exercise plan that accommodates the client's skill level and performance; (3) social interactions that increase engagement; and (4) positive feedback that increases morale. These benefits are not realized by the client when practicing exercises in isolation, causing clients to struggle with complying with therapeutic regimens at home. To create this system, first, we designed a passive exoskeleton with a rehabilitation gaming suite that encourages therapeutic motions. Then, we verified its ability to increase participant engagement while completing therapeutic exercises. Next, we verified the ability of our system to encourage accurate therapeutic motions. We then used machine learning techniques to process data from popular video games in order to classify task difficulty and make the rehabilitation game adaptive, so it has the capability to learn and grow with users. A final experiment was conducted with elderly adults and stroke survivors that suggests that adaptive user experiences help promote expedited learning of the task.
