Electromyogram (EMG) based fingers movement recognition using sparse filtering of wavelet packet coefficients

Bhagwat, Smita; Mukherji, Prachi

doi:10.1007/s12046-019-1231-9

Cited by 29 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with previous literature [20][21][22][23][24] , in this research work we introduced a detailed investigation of the quality of the sEMG signals we acquired via inkjet-printing. In the most recent studies [26][27][28] , however, more attention has been dedicated to evaluating the repeatability of a sEMG pattern during the same task.…”

Section: Resultsmentioning

confidence: 99%

Inkjet-printed fully-customizable and low-cost electrodes matrix for gesture recognition

Rosati

Cisotto

Sili

et al. 2021

Preprint

View full text Add to dashboard Cite

The use of surface electromyography (sEMG) is rapidly spreading, from robotic prostheses and, muscle computer interfaces, to rehabilitation devices controlled by residual muscular activities. In this context, sEMG-based gesture recognition plays an enabling role to control prosthetics and devices in real-life settings. The aim of our work was to develop a low-cost, print-and-play platform to acquire and analyse sEMG signals that can be arranged in a fully customized way, depending on the application and the users’ needs. We produced 8-channel sEMG matrices to measure muscular activity of the forearm using innovative nanoparticle-based inks to print the sensors embedded into each matrix using a commercial inkjet printer. Then, we acquired the multi-channel sEMG data from 12 participants, while they were repeatedly performing 12 standard finger movements (6 extension and 6 flexion). Our results showed that inkjet printing-based sEMG signals ensured significant similarity values across repetitions in every participant, a large enough difference between movements (dissimilarity index above 0.2), and an overall classification accuracy of 93%-95% for flexion and extension, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Inkjet-printed fully-customizable and low-cost electrodes matrix for gesture recognition

Rosati

Cisotto

Sili

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The decomposition of sub-signals into different frequency bands will also increase the amount of calculation. Therefore, in actual engineering practice, it is necessary to consider the frequency domain resolution and time domain resolution to determine the number of wavelet packet decomposition layers [ 33 ]. Here, we separately used the original data and the wavelet packet to decompose the reconstructed signal after 1–4 layers as the original input of the LSTM network.…”

Section: Resultsmentioning

confidence: 99%

Research on Voltage Waveform Fault Detection of Miniature Vibration Motor Based on Improved WP-LSTM

et al. 2020

View full text Add to dashboard Cite

To solve the problem of vibration motor fault detection accuracy and inefficiency in smartphone components, this paper proposes a fault diagnosis method based on the wavelet packet and improves long and short-term memory network. First, the voltage signal of the vibration motor is decomposed by a wavelet packet to reconstruct the signal. Secondly, the reconstructed signal is input into the improved three-layer LSTM network as a feature vector. The memory characteristics of the LSTM network are used to fully learn the time-series fault feature information in the unsteady state signal, and then, the model is used to diagnose the motor fault. Finally, the feasibility of the proposed method is verified through experiments and can be applied to engineering practice. Compared with the existing motor fault diagnosis method, the improved WP-LSTM diagnosis method has a better diagnosis effect and improves fault diagnosis.

show abstract

“…The higher amplitude often occurs on the period of maximum contraction, with a signal pattern which is often called EMG "burst" [18]. EMG is one of biofeedback modalities that investigates actively in medical rehabilitation exercise [12,3,5]. In exercise, repetitive/periodic movement can increase the improvement of motor skills and the smoothness of movement progressively.…”

Section: A Emg and Eeg Signal Characteristic On Motoricmentioning

confidence: 99%

“…For bio-feedback, muscle activities could be evaluated using electromyography (EMG). The conventional EMG quantification is focused for fatigue evaluation for specific activities [2,3] and characteristic of muscle contraction [4,5].…”

Section: Introductionmentioning

confidence: 99%

Automatic Segmentation Scheme for Effective Synchronization of EMG-EEG Quantification

2020

International Journal of Biology and Biomedical Engineering

View full text Add to dashboard Cite

Effective segmentation of electromyography (EMG) burst that synchronizes with electroencephalography (EEG) for long-duration recording is important steps to better understand the quantification of brain-muscle connectivity in periodic motoric activities. The work proposes an alternative automatic EMG segmentation scheme consists of four main steps, i.e. denoising of EMG burst signal using discrete wavelet transform, enveloping signal using time-windows averaging of RMS amplitude, an adaptive threshold to detect start/end burst envelope with accommodation of muscle contraction characteristic and the final step is conversion enveloping signal to binary segmentation signal.The proposed scheme is evaluated to detect contraction period/duration of EMG for the subject under repetitive holding and releasing grasp using a physiotherapy device. During exercise, the bio-amplifier board is customized to acquire simultaneous EEG and EMG from the region of flexor digitorum superficialis (FDS) of muscle and cortical motor of the brain, with total 284 EMG burst that counting by manual segmentation. The automatic segmentation can detect the total EMG burst by 6.25% error of false burst detection.The usefulness of proposed scheme is also tested to association analysis according to the power of EMG burst and the power of mu-wave of EEG recorded on the motor cortex. The changing trend of the power of mu-wave associated with muscle relaxation, muscle contraction strength and the synchronization level on the motor cortex during exercise are analyzed with integrated information that is relevant with biofeedback concept. The results demonstrate that proposed scheme has potential to be an effective method for the evaluation of biofeedback rehabilitation exercise.

show abstract

Electromyogram (EMG) based fingers movement recognition using sparse filtering of wavelet packet coefficients

Cited by 29 publications

References 23 publications

Inkjet-printed fully-customizable and low-cost electrodes matrix for gesture recognition

Inkjet-printed fully-customizable and low-cost electrodes matrix for gesture recognition

Research on Voltage Waveform Fault Detection of Miniature Vibration Motor Based on Improved WP-LSTM

Automatic Segmentation Scheme for Effective Synchronization of EMG-EEG Quantification

Contact Info

Product

Resources

About