Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Valentini, Riccardo; Michieletto, Stefano; Spolaor, Fabiola; Sawacha, Z.; Pagello, Enrico

doi:10.1109/icorr.2015.7281325

Cited by 6 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EMG signals were obtained from the biceps and triceps. Recently, Valentini et al [82] used a GMM to estimate the angle of a human joint with wavelet transform features obtained from sEMG signals. Their system achieved realtime performance with a processing time below 3 ms.…”

Section: Figurementioning

confidence: 99%

A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction

et al. 2019

View full text Add to dashboard Cite

This paper presents a literature review on pattern recognition of electromyography (EMG) signals and its applications. The EMG technology is introduced and the most relevant aspects for the design of an EMG-based system are highlighted, including signal acquisition and filtering. EMG-based systems have been used with relative success to control upper-and lower-limb prostheses, electronic devices and machines, and for monitoring human behavior. Nevertheless, the existing systems are still inadequate and are often abandoned by their users, prompting for further research. Besides controlling prostheses, EMG technology is also beneficial for the development of machine learning-based devices that can capture the intention of able-bodied users by detecting their gestures, opening the way for new human-machine interaction (HMI) modalities. This paper also reviews the current feature extraction techniques, including signal processing and data dimensionality reduction. Novel classification methods and approaches for detecting non-trained gestures are discussed. Finally, current applications are reviewed, through the comparison of different EMG systems and discussion of their advantages and drawbacks.INDEX TERMS EMG, human-machine interaction, pattern classification, regression.

show abstract

Section: Figurementioning

confidence: 99%

A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The GMM, which can be viewed as the weighted sum of several Gaussian components that best approximate the inputs, 38 was described as follows p(xjl) = where x denotes the input vector;w i represents the mixture weight; and N (xjm i , S i ) represents the Gaussian distribution of the ith mixture component defined by m i and S i . If the dimension of x was D, then the component Gaussian density was modeled as follows:…”

Section: Gmmmentioning

confidence: 99%

Surface electromyography–based hand movement recognition using the Gaussian mixture model, multilayer perceptron, and AdaBoost method

Zhou

Yin

Fei

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Human movement is closely linked with muscle activities. Research has indicated that predicting human movements with surface electromyography signals is feasible. However, the classification accuracy of surface electromyography signalbased movements is still limited due to the low signal to noise ratio, especially when multiple movement categories are investigated. In this study, six representative time-domain feature extraction techniques and four frequency-domain feature extraction techniques with three different types of classifiers (the statistical classifier Gaussian mixture model, the neural network classifier multilayer perceptron, and the ensemble method AdaBoost) were applied for the recognition of 52 movements in Non-Invasive Adaptive Prosthetics database 1. From the experimental results, we observed that the performance of Gaussian mixture model was superior to that of the multilayer perceptron in both classification accuracy and computational load. When AdaBoost was introduced into the multilayer perceptron, the classification accuracy significantly improved, such that the performance was comparable with that of the Gaussian mixture model. Using the combination of the Gaussian mixture model and the mean of absolute value, we achieved an accuracy rate of 89.5% for the classification of the 52 movements, which was much higher than the 76% rate reported in previous studies.

show abstract

“…2. For the EMG information, we started from the results obtained in previous studies [15] in order to compute the Wavelet Transform (Wavelet Transform) of the signal, with the intent of analyzing the information in both time and frequency. The procedure extracts a feature value by considering only a small window of the signal at each time instant t, in order to highly characterize the small portion of information available.…”

Section: A Signal Analysismentioning

confidence: 99%

“…The original signal is decomposed using a multi-resolution analysis by means of a base function called mother wavelet (ψ(t)), so that a set of M wavelets, each represented by a coefficient (γ m ), are generated by scaling and translating the mother wavelet to represent the signal in input. As mother wavelet for representing the input EMG and accelerometers in this work we selected the db2 function from the Daubechies family, by looking at the good performances in either accuracy and time we obtained in previous works for both subjectspecific [15] and subject-independent [3] approaches. We choose to synthesize the M wavelet coefficients by using the Mean Average Value (MAV) (Eq.…”

Section: A Signal Analysismentioning

confidence: 99%

“…We choose to synthesize the M wavelet coefficients by using the Mean Average Value (MAV) (Eq. 1) function, as showed in [15] This phase has two main objectives: (1) to obtain a single value representing the wavelet decomposition and (2) to provide a certain level of smoothness in order to avoid sudden changes from one instant to another. The major reason for selecting MAV as synthesis function is the computational time, in fact this operation should be fast enough to be computed online.…”

Section: A Signal Analysismentioning

confidence: 99%

See 1 more Smart Citation

Toward a Better Robotic Hand Prosthesis Control: Using EMG and IMU Features for a Subject Independent Multi Joint Regression Model

Stival

Michieletto

Agnoi

et al. 2018

2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob)

Self Cite

View full text Add to dashboard Cite

The interest on wearable prosthetic devices has boost the research for a robust framework to help injured subjects to regain their lost functionality. A great number of solutions exploit physiological human signals, such as Electromyography (EMG), to naturally control the prosthesis, reproducing what happens in the human limbs. In this paper, we propose for the first time a way to integrate EMG signals with Inertial Measurement Unit (IMU) information, as a way to improve subject-independent models for controlling robotic hands. EMG data are very sensitive to both physical and physiological variations, and this is particularly true between different subjects. The introduction of IMUs aims at enriching the subject-independent model, making it more robust with information not strictly dependent from the physiological characteristics of the subject. We compare three different models: the first based on EMG solely, the second merging data from EMG and the 2 best IMUs available, and the third using EMG and IMUs information corresponding to the same 3 electrodes. The three techniques are tested on two different movements executed by 35 healthy subjects, by using a leaveone-out approach. The framework is able to estimate online the bending angles of the joints involved in the motion, obtaining an accuracy up to 0.8634. The resulting joint angles are used to actuate a robotic hand in a simulated environment.

show abstract

Processing of sEMG signals for online motion of a single robot joint through GMM modelization

Cited by 6 publications

References 44 publications

A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction

A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction

Surface electromyography–based hand movement recognition using the Gaussian mixture model, multilayer perceptron, and AdaBoost method

Toward a Better Robotic Hand Prosthesis Control: Using EMG and IMU Features for a Subject Independent Multi Joint Regression Model

Contact Info

Product

Resources

About