EMG Signal Filtering Based on Independent Component Analysis and Empirical Mode Decomposition for Estimation of Motor Activation Patterns

Tapia, Claudio; Daud, Omar A.; Ruiz‐del‐Solar, Javier

doi:10.1007/s40846-016-0201-5

Cited by 19 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raw EMG data were filtered using a low bandpass Butterworth filter with a cut-off frequency of 500 Hz and a high-pass Butterworth filter with a cut-off at 20 Hz. The signals were preprocessed using full-wave rectification, then lowpass filtered at 10 Hz, and a linear envelope was obtained using the root mean square (RMS) approach with a window size of 100 ms [31,32], which included normalization of the amplitudes of the EMG signals (Figure 4) [33][34][35]. Subjects were asked to perform several straight walking trials over a 12-m walkway at three different familiar speeds: slow, normal, and fast, walking characteristics described in results.…”

Section: Data Processingmentioning

confidence: 99%

Muscle Co-Activation around the Knee during Different Walking Speeds in Healthy Females

Akl

Gonçalves

Fonseca

et al. 2021

Sensors

View full text Add to dashboard Cite

The purpose of this study was to examine the changes in co-activation around the knee joint during different walking speeds in healthy females using the co-activation index. Ten healthy females (age: 21.20 ± 7.21 years, height: 164.00 ± 4.00 cm, mass: 60.60 ± 4.99 kg) participated in this study and performed three walking speeds (slow, normal, and fast). A Qualisys 11-camera motion analysis system sampling at a frequency of 200 Hz was synchronized with a Trigno EMG Wireless system operating at a 2000 Hz sampling frequency. A significant decrease in the co-activation index of thigh muscles was observed between the slow and fast, and between the normal and fast, walking speeds during all walking phases. A non-significant difference was observed between the slow and normal walking speeds during most walking phases, except the second double support phase, during which the difference was significant. A negative relationship was found between walking speed and the co-activation index of thigh muscles in all speeds during walking phases: first double support (r = −0.3386, p < 0.001), single support (r = −0.2144, p < 0.01), second double support (r = −0.4949, p < 0.001), and Swing (r = −0.1639, p < 0.05). In conclusion, the results indicated high variability of thigh muscle co-activation in healthy females during the different walking speeds, and a decrease in the co-activation of the thigh muscles with the increase of speed.

show abstract

Section: Data Processingmentioning

confidence: 99%

Muscle Co-Activation around the Knee during Different Walking Speeds in Healthy Females

Akl

Gonçalves

Fonseca

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…where X id is the dth dimension of ith tree, MR is the mutation rate, and rand is the random number distributed between 0 and 1. Note that the mutation rate is linearly decreasing from 0.9 to 0, as shown in Equation (12).…”

Section: Modified Binary Tree Growth Algorithmmentioning

confidence: 99%

“…The global best tree is set. For each iteration, the mutation is computed as shown in Equation (12). In the next step, the N 1 trees are assigned into the first group.…”

Section: Modified Binary Tree Growth Algorithmmentioning

confidence: 99%

“…However, the signal presented in TD does not offer frequency or spectral information. For this reason, many studies have analyzed the EMG signal using time-frequency transformation, especially for those involving the classification and diagnosis [10][11][12]. Unlike TD, time-frequency distribution (TFD) allows the representation of time and frequency information simultaneously, which provides more accurate signal information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection Based on Binary Tree Growth Algorithm for the Classification of Myoelectric Signals

et al. 2018

View full text Add to dashboard Cite

Electromyography (EMG) has been widely used in rehabilitation and myoelectric prosthetic applications. However, a recent increment in the number of EMG features has led to a high dimensional feature vector. This in turn will degrade the classification performance and increase the complexity of the recognition system. In this paper, we have proposed two new feature selection methods based on a tree growth algorithm (TGA) for EMG signals classification. In the first approach, two transfer functions are implemented to convert the continuous TGA into a binary version. For the second approach, the swap, crossover, and mutation operators are introduced in a modified binary tree growth algorithm for enhancing the exploitation and exploration behaviors. In this study, short time Fourier transform (STFT) is employed to transform the EMG signals into time-frequency representation. The features are then extracted from the STFT coefficient and form a feature vector. Afterward, the proposed feature selection methods are applied to evaluate the best feature subset from a large available feature set. The experimental results show the superiority of MBTGA not only in terms of feature reduction, but also the classification performance.

show abstract

“…Ai et al combined acceleration and sEMG signals to identify five motion intentions of the lower extremities [14]. To identify the lower extremity knee, ankle, and hip joint motions, Tapia et al extracted sEMG signals from sixteen muscles of the lower extremities [15]. Zhang et al extracted single channel sEMG signals for four motion intention recognition of lower limb knee joints [16].…”

Section: Introductionmentioning

confidence: 99%

Lower Limb Motion Recognition Method Based on Improved Wavelet Packet Transform and Unscented Kalman Neural Network

Shi

Qin

Zhu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Exoskeleton robot is a typical application to assist the motion of lower limbs. To make the lower extremity exoskeleton more flexible, it is necessary to identify various motion intentions of the lower limbs of the human body. Although more sEMG sensors can be used to identify more lower limb motion intention, with the increase in the number of sensors, more and more data need to be processed. In the process of human motion, the collected sEMG signal is easy to be interfered with noise. To improve the practicality of the lower extremity exoskeleton robot, this paper proposed a wavelet packet transform- (WPT-) based sliding window difference average filtering feature extract algorithm and the unscented Kalman neural network (UKFNN) recognition algorithm. We established an sEMG energy feature model, using a sliding window difference average filtering method to suppress noise interference and extracted stable feature values and using UKF filtering to optimize the neural network weights to improve the adaptability and accuracy of the recognition model. In this paper, we collected the sEMG signals of three muscles to identify six lower limb motion intentions. The average accuracy of 94.83% is proposed in this paper. Experiments show that the algorithm improves the accuracy and anti-interference of motion intention recognition of lower limb sEMG signals. The algorithm is superior to the backpropagation neural network (BPNN) recognition algorithm in the lower limb motion intention recognition and proves the effectiveness, novelty, and reliability of the method in this paper.

show abstract

EMG Signal Filtering Based on Independent Component Analysis and Empirical Mode Decomposition for Estimation of Motor Activation Patterns

Cited by 19 publications

References 22 publications

Muscle Co-Activation around the Knee during Different Walking Speeds in Healthy Females

Muscle Co-Activation around the Knee during Different Walking Speeds in Healthy Females

Feature Selection Based on Binary Tree Growth Algorithm for the Classification of Myoelectric Signals

Lower Limb Motion Recognition Method Based on Improved Wavelet Packet Transform and Unscented Kalman Neural Network

Contact Info

Product

Resources

About