Electromyogram (EMG) signal detection, classification of EMG signals and diagnosis of neuropathy muscle disease

Sadıkoğlu, Fahreddin; Kavalcıoğlu, Cemal; Dağman, Berk

doi:10.1016/j.procs.2017.11.259

Cited by 66 publications

(45 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The signals associated with nonperiodic tremors are differentiable with FFT [57]. The EMG signal from neuropathic patients with SCI also exhibited distinct power spectrum density and amplitude in comparison to healthy individuals [58]. The application of FFT to the EMG envelope revealed muscle burst discharge in frequency domain ranging from 4 to 7 Hz [15].…”

Section: Frequency and Time-frequency Analysismentioning

confidence: 99%

A Review of EMG Techniques for Detection of Gait Disorders

Singh¹,

Iqbal²,

White³

et al. 2019

Artificial Intelligence - Applications in Medicine and Biology

View full text Add to dashboard Cite

Electromyography (EMG) is a commonly used technique to record myoelectric signals, i.e., motor neuron signals that originate from the central nervous system (CNS) and synergistically activate groups of muscles resulting in movement. EMG patterns underlying movement, recorded using surface or needle electrodes, can be used to detect movement and gait abnormalities. In this review article, we examine EMG signal processing techniques that have been applied for diagnosing gait disorders. These techniques span from traditional statistical tests to complex machine learning algorithms. We particularly emphasize those techniques are promising for clinical applications. This study is pertinent to both medical and engineering research communities and is potentially helpful in advancing diagnostics and designing rehabilitation devices.

show abstract

Section: Frequency and Time-frequency Analysismentioning

confidence: 99%

A Review of EMG Techniques for Detection of Gait Disorders

Singh¹,

Iqbal²,

White³

et al. 2019

Artificial Intelligence - Applications in Medicine and Biology

View full text Add to dashboard Cite

show abstract

“…The parameters are then inserted into (1) which is the general formula of transformation matrix. The 4 0 matrix is obtained as show in (2). Cos and sin are substituted with c and s respectively to simplify the equation.…”

Section: Table-iii: Dh Parameters Definition Parameters Definition Dmentioning

confidence: 99%

“…An EMG [1] is basically the summation of all the action potential recorded using electrodes from the muscle fiber. The motor units [2] which is made up of muscle fiber exhibits electrical properties when muscles undergoes contraction. The acquisition of EMG signals would help in providing useful information from the Motor Unit Action Potential (MUAP) for the application of modern technologies.…”

Section: Introductionmentioning

confidence: 99%

Design and Construction of 4-DOF EMG-Based Robot Arm System

2019

IJITEE

View full text Add to dashboard Cite

Electromyography (EMG) provides an alternative way of providing signal responses from the muscle. As such, the recent trend in developing myoelectric devices has spark the interest in this specific field of study. This is because the traditional controllers lack in certain parts which reduce the utilization of limbs to control devices mainly the robotic arm. However, noise such as crosstalk, motion artifact, ambient noise and inherent noise have become a major issue when handling EMG signals. The preparation of electromyography requires more attention in terms of muscle group selection, electrode placement and condition of the surrounding as it will affect the signal output. The aim of this project is to develop a 4 degree-offreedom (DOF) robotic arm that can be controlled using EMG signals. The correlation between the EMG signal and the robotic arm are required to be identified in order to analyze the performance of robotic arm. Review on the actuator, electromyography methods and microcontroller are done to evaluate the techniques used from past researches. The methods of this project include hardware development of robotics arm, development of forward kinematic, sensor calibration and electrode positioning and experiment on classification and validation of EMG signals based on hand gestures. The experiment showed that the sampling rate and arm position affect the EMG signal output. In addition, the controllability of the robotic arm was low because the motors are controlled independently. The objective of the project has been achieved as the EMG-controlled robotic arm has been successfully developed. The robotic arm is still available for improvement by adding multiple channel sensors and implementing a wireless system.

show abstract

“…In the field of machine learning, accuracy is a technical term referring to the percentage of classifications performed by the ANN that match the true manual classification. Using ANNs, researchers have successfully distinguished between different wrist and thumb movements used to control an active hand prosthesis (Arvetti et al, 2007), detected different phases of the gait cycle (Joshi et al, 2013) and differentiated between sEMG acquired from healthy and neuropathic individuals (Sadikoglu et al, 2017), thus demonstrating the potential of ANNs for human movement applications.…”

Section: Introductionmentioning

confidence: 99%

Development of a deep neural network for automated electromyographic pattern classification

Akhundov

Saxby

Edwards

et al. 2019

Journal of Experimental Biology

View full text Add to dashboard Cite

Determining the signal quality of surface electromyography (sEMG) recordings is time consuming and requires the judgement of trained observers. An automated procedure to evaluate sEMG quality would streamline data processing and reduce time demands. This paper compares the performance of two supervised and three unsupervised artificial neural networks (ANNs) in the evaluation of sEMG quality. Manually classified sEMG recordings from various lower-limb muscles during motor tasks were used to train (n=28,000), test performance (n=12,000) and evaluate accuracy (n=47,000) of the five ANNs in classifying signals into four categories. Unsupervised ANNs demonstrated a 30-40% increase in classification accuracy (>98%) compared with supervised ANNs. AlexNet demonstrated the highest accuracy (99.55%) with negligible false classifications. The results indicate that sEMG quality evaluation can be automated via an ANN without compromising human-like classification accuracy. This classifier will be publicly available and will be a valuable tool for researchers and clinicians using electromyography.

show abstract

Electromyogram (EMG) signal detection, classification of EMG signals and diagnosis of neuropathy muscle disease

Cited by 66 publications

References 18 publications

A Review of EMG Techniques for Detection of Gait Disorders

A Review of EMG Techniques for Detection of Gait Disorders

Design and Construction of 4-DOF EMG-Based Robot Arm System

Development of a deep neural network for automated electromyographic pattern classification

Contact Info

Product

Resources

About