Feasibility of using an artificial neural network model to estimate the elbow flexion force from mechanomyography

Youn, Wonkeun; Kim, Jung

doi:10.1016/j.jneumeth.2010.11.003

Cited by 32 publications

(28 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers have adopted some type of mitigation technique (s) to reduce the effects of motion artifact (see, for example, Alves and Chau, 2008;Beck, 2010;Kim et al, 2008;Youn and Kim, 2011). Others have chosen to investigate the source of noise and even suggest sensing solutions to solve the motion artifact problem altogether (Orizio, 1993).…”

Section: Motion Artifact and Mmgmentioning

confidence: 99%

See 1 more Smart Citation

The effects of motion artifact on mechanomyography: A comparative study of microphones and accelerometers

Posatskiy

Chau

2012

Journal of Electromyography and Kinesiology

View full text Add to dashboard Cite

Section: Motion Artifact and Mmgmentioning

confidence: 99%

“…Mitigation techniques usually involve (a) removing contaminated samples, (b) filtering (e.g., Beck, 2010;Kim et al, 2008), and/or (c) experimental precautions (e.g., Youn and Kim, 2011). Removing contaminated samples is quick but inefficient, since otherwise useful data must be discarded.…”

Section: Motion Artifact and Mmgmentioning

confidence: 99%

The effects of motion artifact on mechanomyography: A comparative study of microphones and accelerometers

Posatskiy

Chau

2012

Journal of Electromyography and Kinesiology

View full text Add to dashboard Cite

“…When the muscle is divided into three parts (proximal, middle and distal), the greater displacement peak occurs at the muscle belly in the middle (McAndrew et al, 2006) and this part is often selected as the position for the MMG sensor (Qi et al, 2011;Youn and Kim, 2011).…”

Section: Sensorsmentioning

confidence: 99%

“…The root mean square (RMS) analysis is widely used in MMG studies and uses the intensity quadratic mean value to indicate the range of muscle displacement represented by its acceleration (RMSa) (Durling, 1969). The zero-crossing (Youn and Kim, 2011) is the number of times that the signal crosses the baseline (time domain). Peak counting corresponds to the number of peaks (within a given sub-window, e.g., 30 ms) in the AWL (time domain).…”

Section: Signal Acquisition Processing and Analysismentioning

confidence: 99%

“…The multiplication of RMSa (energy related) and the zero-crossing (ZC) (frequency related in temporal analyses) can enhance the discriminatory procedure; thus, the RZ (RMSa multiplied by ZC) feature was created . Youn and Kim (2011) studied the sum of RMSa and ZC to investigate the accuracy of the force estimation with MMG. To reach this goal, they have used an artificial neural network (ANN) model.…”

Section: Signal Acquisition Processing and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Advances and perspectives of mechanomyography

Krueger

Scheeren

Nogueira-Neto

et al. 2014

Rev. Bras. Eng. Bioméd.

View full text Add to dashboard Cite

Introduction: The evaluation of muscular tissue condition can be accomplished with mechanomyography (MMG), a technique that registers intramuscular mechanical waves produced during a fi ber's contraction and stretching that are sensed or interfaced on the skin surface. Objective: Considering the scope of MMG measurements and recent advances involving the technique, the goal of this paper is to discuss mechanomyography updates and discuss its applications and potential future applications. Methods: Forty-three MMG studies were published between the years of 1987 and 2013. Results: MMG sensors are developed with different technologies such as condenser microphones, accelerometers, laser-based instruments, etc. Experimental protocols that are described in scientifi c publications typically investigated the condition of the vastus lateralis muscle and used sensors built with accelerometers, third and fourth order Butterworth fi lters, 5-100Hz frequency bandpass, signal analysis using Root Mean Square (RMS) (temporal), Median Frequency (MDF) and Mean Power Frequency (MPF) (spectral) features, with epochs of 1 s. Conclusion: Mechanomyographic responses obtained in isometric contractions differ from those observed during dynamic contractions in both passive and functional electrical stimulation evoked movements. In the near future, MMG features applied to biofeedback closed-loop systems will help people with disabilities, such as spinal cord injury or limb amputation because they may improve both neural and myoelectric prosthetic control. Muscular tissue assessment is a new application area enabled by MMG; it can be useful in evaluating the muscular tonus in anesthetic blockade or in pathologies such as myotonic dystrophy, chronic obstructive pulmonary disease, and disorders including dysphagia, myalgia and spastic hypertonia. New research becomes necessary to improve the effi ciency of MMG systems and increase their application in rehabilitation, clinical and other health areas.

show abstract

Estimation of Knee Extension Force Using Mechanomyography Signals Detected Through Clothing

Wang

Xie

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

Feasibility of using an artificial neural network model to estimate the elbow flexion force from mechanomyography

Cited by 32 publications

References 33 publications

The effects of motion artifact on mechanomyography: A comparative study of microphones and accelerometers

The effects of motion artifact on mechanomyography: A comparative study of microphones and accelerometers

Advances and perspectives of mechanomyography

Estimation of Knee Extension Force Using Mechanomyography Signals Detected Through Clothing

Contact Info

Product

Resources

About