K
Kevin Englehart
Researcher at University of New Brunswick
Publications - 146
Citations - 13489
Kevin Englehart is an academic researcher from University of New Brunswick. The author has contributed to research in topics: Proportional myoelectric control & Artificial neural network. The author has an hindex of 46, co-authored 144 publications receiving 11835 citations.
Papers
More filters
Journal ArticleDOI
A robust, real-time control scheme for multifunction myoelectric control
Kevin Englehart,B. Hudgins +1 more
TL;DR: It is shown that, by exploiting the processing power inherent in current computing systems, substantial gains in classifier accuracy and response time are possible and other important characteristics for prosthetic control systems are met.
Journal ArticleDOI
Targeted muscle reinnervation for real-time myoelectric control of multifunction artificial arms.
Todd A. Kuiken,Guanglin Li,Blair A. Lock,Robert D. Lipschutz,Laura A. Miller,K.A. Stubblefield,Kevin Englehart +6 more
TL;DR: The results suggest that reinnervated muscles can produce sufficient EMG information for real-time control of advanced artificial arms, as well as improving the function of prosthetic arms.
Journal ArticleDOI
Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use.
Erik Scheme,Kevin Englehart +1 more
TL;DR: The pertinent issues and best practices in EMG pattern recognition are described, the major challenges in deploying robust control are identified, and research directions that may have an effect in the near future are advocated.
Journal ArticleDOI
A wavelet-based continuous classification scheme for multifunction myoelectric control
TL;DR: It is shown that four channels of myoelectric data greatly improve the classification accuracy, as compared to one or two channels, and a robust online classifier is constructed, which produces class decisions on a continuous stream of data.
Journal ArticleDOI
Classification of the myoelectric signal using time-frequency based representations
TL;DR: It is shown that feature sets based upon the short-time Fourier transform, the wavelets transform, and the wavelet packet transform provide an effective representation for classification, provided that they are subject to an appropriate form of dimensionality reduction.