A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses

By Yonghong Huang, Kevin B. Englehart, B. Hudgins, Adrian D. C. Chan. IEEE Transactions on Biomedical Engineering, 2005

625 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cellular and Molecular Neuroscience, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/df6344d68a0dcf21da209dbc02f3d2a2d330b527

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cellular and Molecular Neuroscience

In Cognitive Neuroscience

Citations in the corpus

A Comparison of Surface and Intramuscular Myoelectric Signal Classification (2007, methodology): “To illustrate the classification performance resulting from some selected feature sets and classifiers, consider the 6 class problem described in [ 13 ].”
Characterization of Surface EMG Signal Based on Fuzzy Entropy (2007, neutral): “the electrophysiology and the recording environment [2].”
On the Shared Control of an EMG-Controlled Prosthetic Hand: Analysis of User–Prosthesis Interaction (2008, background): “Nevertheless, current smart classifiers do not provide more than six recognized classes (or primitives) [17], [18], and their practical reliability must be evaluated; moreover, their controllability in prostheses application is neither natural nor intuitive.”
Feature Extraction and Selection for Myoelectric Control Based on Wearable EMG Sensors (2018, positive): “• MS1 (Hudgins’ set of TD features): MAV, WL, ZC, and SSC [44] • MS2: RMS and AR6 [42] • MS3: MAV, WL, ZC, SSC, RMS, and AR6 [42] • MS4: AR4 and HIST9 [41] • MS5: WL, LD, SSC, and AR9 [43] • MS6: WL, SSC, AR9, and CC9 [43] • MS7: RMS, VAR, LD, and HIST9 [43] • MS8: WL, RMS, SampEn, and CC4 [24]”
Design of a cybernetic hand for perception and action (2006, background): “…been achieved by several groups extracting motor information (Micera et al. 1999; Englehart and Hudgins 2003; Reischl et al. 2004; Ajiboye and R. Weir 2005; Chan and Englehart 2005; Huang et al. 2005), extracting users’ voluntary intentions is still difficult and hampered by several limitations.”
A Strategy for Identifying Locomotion Modes Using Surface Electromyography (2009, methodology): “The simple LDA was reported as having comparable classification performance to more complex types [20]–[22] and as being computationally efficient for real-time myoelectric prosthesis control [8].”
Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation (2019, methodology): “25 × Sample frequency (SF) (256 ms for SF of 1000 Hz) for continuous myoelectric classification [30].”
A Framework for Hand Gesture Recognition Based on Accelerometer and EMG Sensors (2011, methodology): “It has been shown that some successful applications can be achieved by time-domain parameters [19], for example, zero-crossing rate and root mean square (rms).”
Myoelectric control systems - A survey (2007, background): “[3] omitted three segments of training data during each motion changeover; in”
A Review of Intent Detection, Arbitration, and Communication Aspects of Shared Control for Physical Human-Robot Interaction (2018, background): “Typically, this problem is resolved with pattern recognition techniques [43,44].”
Autonomy in Rehabilitation Robotics: An Intersection (2018, positive): “Therefore, a large body of pattern-recognition research focuses on advancing EMG decoding paradigms—evaluating a variety, even cascades (40), of machine learning algorithms (41, 42) and different input features for these algorithms (41, 42, 43), as well as exploring different output classes (44, 45,”
Upper limb prosthesis use and abandonment: A survey of the last 25 years (2007, background): “Initiatives to improve control strategies, (Chan and Englehart 2003; Nishikawa et al. 2000; Ajiboye and Weir 2005, Huang et al. 2005; Khadivi et al. 2005; Sibelius et al. 2005a, 2005b), to exploit mechanomyography as a means of circumventing problems of perspiration and electrode placement (Silva…”
Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use. (2011, background): “A comparison of feature sets has shown that for slowly varying EMG patterns, a concatenated TD/AR (TDAR) feature set outperform s all others [16,24] but the slight improvement in performance over simple TD fe atures incurs considerable processing overhead.”
Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb (2008, positive): “Furthermore, Huang et al. [13] and Fukuda et al. [14] developed a GMM as a classifier in their MCS; the former showed an accuracy of approximately 97%.”