Affiliations: Air Navigation and Traffic System Department, Korea
Aerospace Research Institute, 45 Eoeun-dong, Yuseong-gu, Daejeon 305-333,
Korea | Department of Computer Engineering, Dongguk
University, 3-26 Pil-dong, Chung-gu, Seoul 100-715, Korea | Department of Electrical Engineering and Computer
Science, Korea Advanced Institute of Science and Technology, 373-1
Guseong-dong, Yuseong-gu, Daejeon 305-701, Korea
Abstract: The main goal of this paper is to design an electromyogram (EMG)
pattern classifier which is robust against muscular fatigue effects for powered
wheelchair control. When a user operates a powered wheelchair using EMG-based
interface for a long time, muscular fatigue often arises from sustained
duration of muscle contraction. The recognition rate thus is degraded and
controlling wheelchair gets more difficult. In this paper, an important
observation is addressed that the variations of feature values due to the
effect of the muscular fatigue are consistent for sustained duration. Based on
this observation, we design a robust pattern classifier through the adaptation
process of hyperboxes of Fuzzy Min-Max Neural Network. We present, as a result,
a significantly improved performance in terms of the continuous usage of
wheelchair.
