Pattern recognition with surface EMG signal based wavelet transformation

A hybrid BMI-based exoskeleton for paresis: EMG control for assisting arm movements

“…Time Linear envelope [62], mean absolute value, root mean square [108], zero crossings, slope sign changes, waveform length [106], wave complexity [74], Willison amplitude [109], log-detector [110], histogram [104] Computational simplicity [74], direct relationship to contraction level and force [3,111] Sensitive to noise [3,61], transient sEMG changes [25,112], amplitude cancellation [111] Frequency Power spectral moments [113], power spectral density [23], spectral magnitude averages [107], short time Fourier transform, median frequency [11], cepstrum [114], short time Thompson transform [107] Fatigue detection [115], distinguish non-stationary signals [113] Computational complexity, poor time resolution [113], spectral leakage, high variance [3] Timefrequency Wavelet packet transform [116][117][118], discrete wavelet transform [24,119] Time and frequency resolution [102], transient and static representation [116] Abstract features, high-dimensional outputs, many design parameters…”

“…With control inputs noninvasively representing nearby motor unit action potentials (MUAPs) through surface electromyography (sEMG), myoelectric control research has been primarily driven by the potential to create prostheses and orthoses which intuitively respond to users' intentions [2,3]. As robotics research trends toward compliant manipulation and multimodal feedback [4][5][6][7][8], these controls also show promise for select applications in robot teleoperation [9][10][11][12][13][14][15][16][17][18] and other humanmachine interfaces [19][20][21][22][23][24]. However, despite a constant research focus and increasing desire for enhanced myoelectric control applications, research advances have struggled to translate to clinical and commercial applications [3,[25][26][27].…”

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

“…Guglielminotti and Merletti [21] theorized that wavelet transform exhibits very good energy localization in the time-scale plane when the shape of the EMG signal is matched with wavelet shape. Recent works of Chowdhury et al [12], Sahin and Sahin [43], and Phinyomark et al [39] reinforced advantages in using wavelet transform for EMG analysis. Chowdhury et al [12] concluded that analyzing sEMG signals using Daubechies function returns successful results by investigating and analyzing various research studies on wavelet transform.…”

Anterior cruciate ligament recovery monitoring system using hybrid computational intelligent techniques

“…The features selection techniques discard some of the features completely and so the information provided by those features is completely lost. In order to avoid this problem, Two popular feature reduction techniques, principal component analysis (PCA) and independent component analysis (ICA) have been used to extract features from bio-signals including EMG, electrocardiograph (ECG) and electroencephalograph (EEG) signals [17,32,54,62,64]. These techniques reduce the dimension of data set by removing the redundancy in the data and replacing the group of variables with a single variable while still not rejecting some of the features completely from the data set.…”