| Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 88 === Due to better nutrition and medical treatment as well as improved living environment and the rapidly growing elderly population, how to develop an easy operating and yet effective ambulatory rehabilitation system becomes an important rehabilitation issue. This thesis presents an intelligent automated walking training assistant system. Trainee’s joint maker tracking, which implement through the modified backprojection algorithm, is integrated with the electrical treadmill. It can monitor, record, and quantify the trainee’s joint data instantaneously. A set of force sensors to measure trainee’s ground reaction force is arranged bellow the force plates under the belt. The gait phases are detected using a Bayesian neural network that inputs the force measurements directly. To realize the system in real applications, we represent a fuzzy assistant control strategy, which interpret the rehabilitation expert knowledge by fuzzy membership functions and rules. The velocity tuning commands to assist the rehabilitation process are generated through the fuzzy inference engine in each detection cycle. We have completed the integration of these techniques in experimental tests. The result demonstrates the system is able to adapt the trainee walking and get more similar gait to overground walking.
|
|---|
