Improving EMG Signal Change Point Detection for Low SNR by Using Extended Teager-Kaiser Energy Operator

Tigrini, Andrea; Mengarelli, Alessandro; Cardarelli, Stefano; Fioretti, Sandro; Verdini, Federica

doi:10.1109/tmrb.2020.3014517

Cited by 22 publications

(24 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outcomes are reported in the lower four rows of Table IV. Results in this four-range subsets are directly compared with results achieved by the following four different onset-detection algorithms in the same 52-signal dataset and reported in [44]: a method based on the doublethreshold statistical algorithm, DT [23]; the wavelet approach introduced in [39], WLT; the procedure founded on the CUSUM logic [46], CUSUM; and the recent approach grounded on the profile-likelihood maximization, employing discrete Fibonacci search, PROLIFIC [47]. Two filtering procedures are also considered (TKEO and ETKEO).…”

Section: B Real Semg Signalsmentioning

confidence: 99%

“…Detection of offset timing is not computed, given that the ground-truth offset is not available. The choice of this dataset has been driven by the following considerations: it is a large and complete sEMG dataset available for free; it includes a reliable ground truth for onset detection, which is already used and tested in previous studies [19,44,47]; the peculiarities of knee extension and elbow flexion allow a simple and accurate visual detection of the muscle onset and, consequently, reliable identification of the ground truth; results of the application to this dataset of four onset-detection techniques and two filters are available for a direct comparison [44]. A recent and exciting study proposes an onset and offset detection algorithm for muscle activation validated during hand-close movement of 10 subjects [27].…”

Section: B Real Semg Signalsmentioning

confidence: 99%

“…The aim is to filter the sEMG signal and, thus, increase SNR value to limit the errors in detecting activation events. Despite this, worsening detection performances could also be observed when TKEO is implemented to improve signal quality [41,44]. A further issue to consider is that SNR could assume different values in an other portion of the sEMG signal, especially in prolonged tasks like walking, running, cycling, and in specific conditions as muscle fatigue assessment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wavelet-Based Assessment of the Muscle-Activation Frequency Range by EMG Analysis

et al. 2022

View full text Add to dashboard Cite

The assessment of muscle-recruitment timing from surface EMG signal (sEMG) is relevant in different fields, including clinical gait analysis and robotic systems to interpret user's motion intention. However, available methods typically provide only information in time domain without evaluating muscleactivation frequency content. This study aims to propose a novel adaptative algorithm for detecting muscle activation in time-frequency domain based on continuous wavelet transform (CWT) analysis. Precisely, the novel contribution of the proposed algorithm consists of evaluating the frequency range of every muscle activations detected in time domain. Performances are evaluated on a test bench of 720 simulated sEMG signals and 105 real sEMG signals, stratified for signal-to-noise ratio (SNR), and then validated against different reference algorithms. Outcomes indicate that the proposed approach can provide an accurate prediction of muscle onset and offset timing in both simulated (mean absolute error, MAE ≈ 10 ms) and real datasets (MAE < 30 ms), minimally affected by the SNR variability and compatible with the timing of sEMGdriven assistive devices. Concomitantly, the maximum frequency of the activations is computed, ranging from around 100 Hz up to almost 500 Hz. This suggest a large within-muscle between-muscle variability of the frequency range. In conclusion, the current study introduces a novel reliable wavelet-based algorithm to detect both time and frequency content of muscle activation, suitable in different conditions of signal quality.INDEX TERMS surface EMG signal, onset-offset detection, muscle activation, time-frequency domain, wavelet transform.

show abstract

Section: B Real Semg Signalsmentioning

confidence: 99%

Section: B Real Semg Signalsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wavelet-Based Assessment of the Muscle-Activation Frequency Range by EMG Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, these methods suffer from two main limitations: (i) the extraction of the onset/offset time instants rely on the extraction of time- and frequency-domain features which may not be sufficient to properly assess dynamic muscle activity and (ii) their performance are strongly affected by the amount of noise superimposed to the sEMG signal. Even if different studies proposing models able to efficiently work even at very low SNR of sEMG signals have been published in the last years [ 13 , 31 , 50 ], these methods still suffer from the first of the above-mentioned limitations (i.e., the necessity of a feature extraction step before muscle activation interval detection).…”

Section: Discussionmentioning

confidence: 99%

Long short-term memory (LSTM) recurrent neural network for muscle activity detection

Ghislieri

Cerone

Knaflitz

et al. 2021

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks. Methods First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager–Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis. Results The proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR. Conclusions The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.

show abstract

“…In microwave radar, radar signal processing is usually full of challenges, under non-ideal conditions including lower signal-to-clutter-and-noise ratio (SCNR) [28] and interference [29]. Similarly, the low SCNR is also a major problem in the respiration signal detection via UWB radar.…”

Section: Introductionmentioning

confidence: 99%

A Method for Reducing Timing Jitter’s Impact in Through-Wall Human Detection by Ultra-Wideband Impulse Radar

Shi

Pan

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Ultra-wideband (UWB) impulse radar is widely used for through-wall human respiration detection due to its high range resolution and high penetration capability. UWB impulse radar emits very narrow time pulses, which can directly obtain the impulse response of the target. However, the time interval between successive pulses emitted is not ideally fixed because of timing jitter. This results in the impulse response position of the same target not being fixed, but it is related to slow-time. The clutter scattered by the stationary target becomes non-stationary clutter, which affects the accurate extraction of the human respiration signal. In this paper, we propose a method for reducing timing jitter’s impact in through-wall human detection by UWB impulse radar. After the received signal is processed by the Fast Fourier transform (FFT) in slow-time, we model the range-frequency matrix in the frequency domain as a superposition of the low-rank representation of jitter-induced clutter data and the sparse representation of human respiratory data. By only extracting the sparse component, the impact of timing jitter in human respiration detection can be reduced. Both numerical simulated data and experimental data demonstrate that our proposed method can effectively remove non-stationary clutter induced by timing jitter and improve the accuracy of the human target signal extraction.

show abstract

Improving EMG Signal Change Point Detection for Low SNR by Using Extended Teager-Kaiser Energy Operator

Cited by 22 publications

References 58 publications

Wavelet-Based Assessment of the Muscle-Activation Frequency Range by EMG Analysis

Wavelet-Based Assessment of the Muscle-Activation Frequency Range by EMG Analysis

Long short-term memory (LSTM) recurrent neural network for muscle activity detection

A Method for Reducing Timing Jitter’s Impact in Through-Wall Human Detection by Ultra-Wideband Impulse Radar

Contact Info

Product

Resources

About