Control of Upper Limb Prostheses: Terminology and Proportional Myoelectric Control—A Review

Fougner, Anders Lyngvi; Stavdahl, Øyvind; Kyberd, Peter; Losier, Yves; Parker, P.A.

doi:10.1109/tnsre.2012.2196711

Cited by 451 publications

(322 citation statements)

References 81 publications

Supporting

Mentioning

314

Contrasting

Unclassified

Order By: Relevance

“…The rest class, except the errors related to delayed transitions, is generally well classified. The movements (3,8,9, and 10) have more samples that are labeled incorrectly as some other movement. The algorithm underperformed when discriminating classes 3, 8, 9, and 10, with class 9 being most problematic as the majority of observations were misclassified as class 3.…”

Section: Resultsmentioning

confidence: 99%

“…Even though information regarding the muscle activity could be obtained in various ways, commercially available prosthetic hands commonly use only a few surface EMG channels. Furthermore, the classification algorithms implemented in such prostheses generally comprise only calculation of an amplitude based EMG feature (e.g., root mean square) that is thresholded to obtain binary control of a single hand function [3]. Even in the case of multifunction prostheses with a plurality of independent joints, the same control paradigm is still employed where switching between different grasps can depend on non-EMG inputs [4], such as smartphone interfaces, specific movements measured using inertial sensors, object recognition algorithms based on camera systems [5], or EMG inputs such as cocontractions (contractions of multiple muscles).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vector Autoregressive Hierarchical Hidden Markov Models for Extracting Finger Movements Using Multichannel Surface EMG Signals

et al. 2018

View full text Add to dashboard Cite

We present a novel computational technique intended for the robust and adaptable control of a multifunctional prosthetic hand using multichannel surface electromyography. The initial processing of the input data was oriented towards extracting relevant time domain features of the EMG signal. Following the feature calculation, a piecewise modeling of the multidimensional EMG feature dynamics using vector autoregressive models was performed. The next step included the implementation of hierarchical hidden semi-Markov models to capture transitions between piecewise segments of movements and between different movements. Lastly, inversion of the model using an approximate Bayesian inference scheme served as the classifier. The effectiveness of the novel algorithms was assessed versus methods commonly used for real-time classification of EMGs in a prosthesis control application. The obtained results show that using hidden semi-Markov models as the top layer, instead of the hidden Markov models, ranks top in all the relevant metrics among the tested combinations. The choice of the presented methodology for the control of prosthetic hand is also supported by the equal or lower computational complexity required, compared to other algorithms, which enables the implementation on low-power microcontrollers, and the ability to adapt to user preferences of executing individual movements during activities of daily living.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vector Autoregressive Hierarchical Hidden Markov Models for Extracting Finger Movements Using Multichannel Surface EMG Signals

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The simplest myos open and close based on the presence of inner-and outer-forearm muscle activity (known as flexion and extension, respectively). However, many other control schemes exist and can work in combination, including proportional (adjusting the speed of motion proportionally with the intensity of muscle contractions), mode-switching (to enable selection between different types of movement), and pattern recognition techniques (for more natural control mappings) [17,33]. In this study, we focus specifically on proportionallycontrolled myoelectric devices (as can be seen in Figure 1), since these are by far the most common type of myo.…”

Section: Background and Related Work Myoelectric Controlmentioning

confidence: 99%

Designing Game-Based Myoelectric Prosthesis Training

Tabor

Bateman

Scheme

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

A myoelectric prosthesis (myo) is a dexterous artificial limb controlled by muscle contractions. Learning to use a myo can be challenging, so extensive training is often required to use a myo prosthesis effectively. Signal visualizations and simple muscle-controlled games are currently used to help patients train their muscles, but are boring and frustrating. Furthermore, current training systems require expensive medical equipment and clinician oversight, restricting training to infrequent clinical visits. To address these limitations, we developed a new game that promotes fun and success, and shows the viability of a low-cost myoelectric input device. We adapted a user-centered design (UCD) process to receive feedback from patients, clinicians, and family members as we iteratively addressed challenges to improve our game. Through this work, we introduce a free and open myo training game, provide new information about the design of myo training games, and reflect on an adapted UCD process for the practical iterative development of therapeutic games.

show abstract

“…SEMG is innately at advantage of fine movement recognition, combined with non-invasion and simple application characteristics, hand gesture recognition and interaction technology based on SEMG signals have become a current hotspot in human-machine interaction technology. Many researchers and institutes have initiated studies involving joint movement recognition and successfully applied in smart artificial limb and control interface (De Luca 1978;Fougner, et al, 2012;Lenzi, et al, 2012) [3][4][5].…”

Section: Introductionmentioning

confidence: 99%