A
Ali Ameri
Researcher at Shahid Beheshti University of Medical Sciences and Health Services
Publications - 21
Citations - 665
Ali Ameri is an academic researcher from Shahid Beheshti University of Medical Sciences and Health Services. The author has contributed to research in topics: Deep learning & Support vector machine. The author has an hindex of 10, co-authored 21 publications receiving 425 citations. Previous affiliations of Ali Ameri include Shahid Beheshti University & Sharif University of Technology.
Papers
More filters
Journal ArticleDOI
Support Vector Regression for Improved Real-Time, Simultaneous Myoelectric Control
TL;DR: The first application of a support vector machine (SVM) based scheme for real-time simultaneous and proportional myoelectric control of multiple degrees of freedom (DOFs) appears to be due to its higher estimation accuracy of all DOFs during inactive and low amplitude segments.
Journal ArticleDOI
Regression convolutional neural network for improved simultaneous EMG control.
TL;DR: Results indicate that the CNN model can extract underlying motor control information from EMG signals during single and multiple degree-of-freedom (DoF) tasks, due to higher regression accuracies especially with high EMG amplitudes.
Journal ArticleDOI
Real-Time, Simultaneous Myoelectric Control Using Force and Position-Based Training Paradigms
TL;DR: The constrained control method outperformed unconstrained control in two real-time testing metrics including completion time and path efficiency and suggests that the quality of control using constrained and unconStrained contraction-based myoelectric schemes is not appreciably different when using comparable levels of muscle activation.
Journal ArticleDOI
A Deep Transfer Learning Approach to Reducing the Effect of Electrode Shift in EMG Pattern Recognition-Based Control
TL;DR: A novel supervised adaptation approach based on transfer learning (TL) with convolutional neural networks (CNNs) which requires only a short training session to recalibrate the system and demonstrates superior performance than previous LDA and QDA-based adaptation approaches.
Journal ArticleDOI
Real-time, simultaneous myoelectric control using a convolutional neural network
TL;DR: This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration and demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals.