Resolving the Limb Position Effect in Myoelectric Pattern Recognition

Fougner, Anders Lyngvi; Scheme, Erik; Chan, Adrian D. C.; Englehart, Kevin; Stavdahl, Øyvind

doi:10.1109/tnsre.2011.2163529

Cited by 330 publications

(319 citation statements)

References 21 publications

Supporting

Mentioning

304

Contrasting

Unclassified

Order By: Relevance

“…Low classification errors, in the range of 2.2 to 11.3 percent, have been reported for varying numbers (6 to 10) of wrist and hand movements using EMG pattern recognition techniques, such as linear discriminant analysis (LDA), artificial neural networks, and support vector machines (SVMs) [13][14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…The position effect is also a challenging problem that has recently been the focus of several researchers [14][15][16]. The position effect refers to the degradation of myoelectric pattern recognition performance when the classifier is trained in one fixed position but is used in other positions or during dynamic activities [16].…”

Section: Introductionmentioning

confidence: 99%

“…HD-FMG uses standard pattern recognition algorithms to discriminate the patterns and determine the user's intent. In this study, we compared the performance of HD-FMG with that of previously reported pattern recognition-based EMG control approaches using an experimental protocol similar to those reported in the literature [13][14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…In real-world prosthetic use, however, a user must elicit contractions in a variety of positions and orientations and under different loading conditions. These conditions affect signal patterns and erode the accuracy of EMG pattern recognition methods [14][15][16]. In this work, we determined the effect of limb position on the accuracy of HD-FMG by conducting trials with static and dynamic variation in limb position.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

High-density force myography: A possible alternative for upper-limb prosthetic control

Radmand¹,

Scheme²,

Englehart³

2016

J Rehabil Res Dev

Self Cite

111

View full text Add to dashboard Cite

Abstract-Several multiple degree-of-freedom upper-limb prostheses that have the promise of highly dexterous control have recently been developed. Inadequate controllability, however, has limited adoption of these devices. Introducing more robust control methods will likely result in higher acceptance rates. This work investigates the suitability of using highdensity force myography (HD-FMG) for prosthetic control. HD-FMG uses a high-density array of pressure sensors to detect changes in the pressure patterns between the residual limb and socket caused by the contraction of the forearm muscles. In this work, HD-FMG outperforms the standard electromyography (EMG)-based system in detecting different wrist and hand gestures. With the arm in a fixed, static position, eight hand and wrist motions were classified with 0.33% error using the HD-FMG technique. Comparatively, classification errors in the range of 2.2%-11.3% have been reported in the literature for multichannel EMG-based approaches. As with EMG, position variation in HD-FMG can introduce classification error, but incorporating position variation into the training protocol reduces this effect. Channel reduction was also applied to the HD-FMG technique to decrease the dimensionality of the problem as well as the size of the sensorized area. We found that with informed, symmetric channel reduction, classification error could be decreased to 0.02%.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-density force myography: A possible alternative for upper-limb prosthetic control

Radmand¹,

Scheme²,

Englehart³

2016

J Rehabil Res Dev

Self Cite

111

View full text Add to dashboard Cite

show abstract

“…One of the ways that EMG control of the limb is being enhanced is to train a computer to recognise the patterns of muscle signals across the residual limb [79,80] as an arm is moved. One flaw in the ability to detect signals is that the amputation reduces the number of possible sites to derive a control signal.…”

Section: Controlmentioning

confidence: 99%

Bridging the gap between robotic technology and health care

Andrade

Pereira

Walter

et al. 2014

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Although technology and computation power have become more and more present in our daily lives, we have yet to see the same tendency in robotics applied to health care. In this work we focused on the study of four distinct applications of robotic technology to health care, named Robotic Assisted Surgery, Robotics in Rehabilitation, Prosthetics and Companion Robotic Systems. We identified the main roadblocks that are limiting the progress of such applications by an extensive examination of recent reports. Based on the limitations of the practical use of current robotic technology for health care we proposed a general modularization approach for the conception and implementation of specific robotic devices. The main conclusions of this review are: (i) There is a clear need of the adaptation of robotic technology (closed loop) to the user, so that robotics can be widely accepted and used in the context of heath care; (ii) For all studied robotic technologies cost is still prohibitive and limits their wide use. The reduction of costs influences technology acceptability, thus innovation by using cheaper computer systems and sensors are relevant and should be taken into account in the implementation of robotic systems.

show abstract

Neural Prostheses

Osborn¹,

Betthauser

Thakor

2019

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Millions of people worldwide are affected by some disability, including but not limited to limb loss, hearing loss, spinal cord injury, or visual impairment. Neural prostheses are designed to provide or replace lost functionality to these individuals. In the case of upper limb loss, simplified hook‐like body‐powered controlled prostheses can be used; however, recent technological developments have led to anthropomorphic dexterous manipulators that require more advanced control strategies. Further, direct control of these manipulators via neural motor signals is seen as a more natural and biomimetic solution. Recent work has utilized direct neural interfacing with the brain to measure motor commands for prosthesis control and to deliver sensory percepts to the user, either through the peripheral nervous system or through the cortex. Current upper limb prosthesis interfaces mainly rely on forward motor commands for control, but recent research has also focused on providing sensory feedback to the user, specifically the sense of touch. This article provides an introductory overview of neural prostheses, such as visual and auditory devices, and an in‐depth look at the state of the art in bidirectional neural prostheses, including control of a dexterous limbs with motor signals from the nervous system and the incorporation of sensory feedback.

show abstract

Resolving the Limb Position Effect in Myoelectric Pattern Recognition

Cited by 330 publications

References 21 publications

High-density force myography: A possible alternative for upper-limb prosthetic control

High-density force myography: A possible alternative for upper-limb prosthetic control

Bridging the gap between robotic technology and health care

Neural Prostheses

Contact Info

Product

Resources

About