A Framework of Temporal-Spatial Descriptors-Based Feature Extraction for Improved Myoelectric Pattern Recognition

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 25; no. 10; pp. 1821 - 1831
• Main Authors: Khushaba, Rami N., Al-Timemy, Ali H., Al-Ani, Ahmed, Al-Jumaily, Adel
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Algorithms; Amputation Stumps - anatomy & histology; Amputees; Channels; Classification; Computer applications; Data mining; Databases, Factual; Electrodes; Electromyography; Electromyography - methods; Feature extraction; Feature recognition; Female; Fingers; Hand; Humans; Male; Movement; Muscle, Skeletal; Myoelectric control; Myoelectricity; Nonlinear Dynamics; Pattern recognition; Pattern Recognition, Automated; Prostheses; Prostheses and Implants; Prosthetics; Time-domain analysis; transradial amputees; Windows; Windows (intervals); Young Adult

The extraction of the accurate and efficient descriptors of muscular activity plays an important role in tackling the challenging problem of myoelectric control of powered prostheses. In this paper, we present a new feature extraction framework that aims to give an enhanced representation of muscula...