A Method to Differentiate Fatiguing Conditions in Surface Electromyography Signals using Instantaneous Spectral Centroid
01 Jul 2020-Vol. 2020, pp 690-693
TL;DR: The preliminary results show that the topological features are able to quantify the nonstationarity in sEMG signal and can be used as a fatigue index for diagnosing various neuromuscular disorders.
Abstract: The nonstationarity measure of surface Electromyography (sEMG) signals provide an index for muscle fatigue conditions. In this paper, a new framework has been proposed for the analysis of sEMG signal using Instantaneous Spectral Centroid (ISC). The novelty of the proposed work is use of topological signal processing method to quantify the nonstationarity of sEMG signal. For this, the signals are recorded from the biceps brachii muscles of 25 healthy subjects in isometric contraction. The analytical signals corresponding to nonfatigue and fatigue segments are computed using Hilbert Transform. Further, topological features such as center of gravity (CoG), triangular area function (TAF) and ISC are calculated from the geometrical representation of a transformed signal. The result indicates the increase of TAF in fatigue condition and the significant right shift of CoG in x-axis for 80% of subjects. Importantly, the ISC estimate is decreased by 17% upon fatiguing for 84% of subjects. The obtained results show statistical significance with p < 0.05. It is observed that the shape parameters are varied in accordance with the changes observed in global characteristics of sEMG signals during muscle fatigue. The preliminary results show that the topological features are able to quantify the nonstationarity in sEMG signal. Therefore, the proposed method can be used as a fatigue index for diagnosing various neuromuscular disorders.Clinical Relevance—This method can be used to establish metrics of muscle fatigue for the benefit of physicians especially in the field of fitness, sports, pre and post-surgery surveillance and rehabilitation.
Citations
More filters
TL;DR: The objective of this study is to develop an automated system for an effective detection of preterm birth by developing an efficient technique that aids in early diagnosis.
5 citations
TL;DR: In this paper , the authors used the discrete wavelet transform (DWT) to detect muscle fatigue in the shoulder and forearm caused by repetitive and continuous strain associated with the computer mouse.
2 citations
26 Jul 2021
TL;DR: In this article, a fatigue detection method to muscle fatigue detection based on integrating multi-source sEMG signals is proposed, where long shortterm memories (LSTM) and one attention layer are used as an inference model.
Abstract: Muscle fatigue detection can be of good help to many tasks such as athletes’ physical training and soldiers’ body status monitoring. Surface elecrtromyography (sEMG) signals are widely used in muscle fatigue detection. However, sEMG signals exist only when the muscle contracts and disappear when it relaxes, making muscle fatigue detection methods cannot work well in realistic applications. To solve this problem, a method based on phase space reconstruction is proposed to automatically filter useless signals and retain useful ones from raw sensor data, improving the practicality of the detection methods. In previous works on muscle fatigue detection, most researchers took only sEMG signals of the target muscle into consideration. However, in reality, when someone is doing physical work, several cooperative muscles rather than some single one participate in the task. Therefore, the exercise status of one muscle not only resides in its own sEMG signals, but also is included in its partners’. For this reason, a fatigue detection method to muscle fatigue detection based on integrating multi-source sEMG signals is proposed, where long short-term memories (LSTM) and one attention layer are used as an inference model. Moreover, a series of sequential detection results are integrated to make a final result to deal with accidental wrong judgements, which further improves the practicality. In our experiments, our LSTM-Attention-based method achieves an detection accuracy of 90.4%, which is much better than the method based on LSTM processing sEMG signals only from the target muscle.
References
More filters
28 Jan 2005
TL;DR: This work focuses on the development of models for Surface EMG Signal Generation based on the principles of Structure--Based SEMG models, which were developed in the context of motor control and Muscle Contraction.
Abstract: Introduction. Contributors. 1 BASIC PHYSIOLOGY AND BIOPHYSICS OF EMG SIGNAL GENERATION (T. Moritani, D. Stegeman, R. Merletti). 1.1 Introduction. 1.2 Basic Physiology of Motor Control and Muscle Contraction. 1.3 Basic Electrophysiology of the Muscle Cell Membrane. References. 2 NEEDLE AND WIRE DETECTION TECHNIQUES (J. V. Trontelj, J. Jabre, M. Mihelin). 2.1 Anatomical and Physiological Background of Intramuscular Recording. 2.2 Recording Characteristics of Needle Electrodes. 2.3 Conventional Needle EMG. 2.4 Special Needle Recording Techniques. 2.5 Physical Characteristics of Needle EMG Signals. 2.6 Recording Equipment. References. 3 DECOMPOSITION OF INTRAMUSCULAR EMG SIGNALS (D. W. Stashuk, D. Farina, K. Sogaard). 3.1 Introduction. 3.2 Basic Steps for EMG Signal Decomposition. 3.3 Evaluation of Performance of EMG Signal Decomposition Algorithms. 3.4 Applications of Results of the Decomposition of an Intramuscular EMG Signal. 3.5 Conclusions. References. 4 BIOPHYSICS OF THE GENERATION OF EMG SIGNALS (D. Farina, R. Merletti, D. F. Stegeman). 4.1 Introduction. 4.2 EMG Signal Generation. 4.3 Crosstalk. 4.4 Relationships between Surface EMG Features and Developed Force. 4.5 Conclusions. References. 5 DETECTION AND CONDITIONING OF THE SURFACE EMG SIGNAL (R. Merletti, H. Hermens). 5.1 Introduction. 5.2 Electrodes: Their Transfer Function. 5.3 Electrodes: Their Impedance, Noise, and dc Voltages. 5.4 Electrode Configuration, Distance, Location. 5.5 EMG Front--End Amplifiers. 5.6 EMG Filters: Specifications. 5.7 Sampling and A/D Conversion. 5.8 European Recommendations on Electrodes and Electrode Locations. References. 6 SINGLE--CHANNEL TECHNIQUES FOR INFORMATION EXTRACTION FROM THE SURFACE EMG SIGNAL (E. A. Clancy, D. Farina, G. Filligoi). 6.1 Introduction. 6.2 Spectral Estimation of Deterministic Signals and Stochastic Processes. 6.3 Basic Surface EMG Signal Models. 6.4 Surface EMG Amplitude Estimation. 6.5 Extraction of Information in Frequency Domain from Surface EMG Signals. 6.6 Joint Analysis of EMG Spectrum and Amplitude (JASA). 6.7 Recurrence Quantification Analysis of Surface EMG Signals. 6.8 Conclusions. References. 7 MULTI--CHANNEL TECHNIQUES FOR INFORMATION EXTRACTION FROM THE SURFACE EMG (D. Farina, R. Merletti, C. Disselhorst--Klug). 7.1 Introduction. 7.2 Spatial Filtering. 7.3 Spatial Sampling. 7.4 Estimation of Muscle--Fiber Conduction Velocity. 7.5 Conclusions. References. 8 EMG MODELING AND SIMULATION (D. F. Stegeman, R. Merletti, H. J. Hermens). 8.1 Introduction. 8.2 Phenomenological Models of EMG. 8.3 Elements of Structure--Based SEMG Models. 8.4 Basic Assumptions. 8.5 Elementary Sources of Bioelectric Muscle Activity. 8.6 Fiber Membrane Activity Profiles, Their Generation, Propagation, and Extinction. 8.7 Structure of the Motor Unit. 8.8 Volume Conduction. 8.9 Modeling EMG Detection Systems. 8.10 Modeling Motor Unit Recruitment and Firing Behavior. 8.11 Inverse Modeling. 8.12 Modeling of Muscle Fatigue. 8.13 Other Applications of Modeling. 8.14 Conclusions. References. 9 MYOELECTRIC MANIFESTATIONS OF MUSCLE FATIGUE (R. Merletti, A. Rainoldi, D. Farina). 9.1 Introduction. 9.2 Definitions and Sites of Neuromuscular Fatigue. 9.3 Assessment of Muscle Fatigue. 9.4 How Fatigue Is Reflected in Surface EMG Variables. 9.5 Myoelectric Manifestations of Muscle Fatigue in Isometric Voluntary Contractions. 9.6 Fiber Typing and Myoelectric Manifestations of Muscle Fatigue. 9.7 Factors Affecting Surface EMG Variable. 9.8 Repeatability of Estimates of EMG Variables and Fatigue Indexes. 9.9 Conclusions. References. 10 ADVANCED SIGNAL PROCESSING TECHNIQUES (D. Zazula, S. Karlsson, C. Doncarli). 10.1 Introduction. 10.2 Theoretical Background. 10.3 Decomposition of EMG Signals. 10.4 Applications to Monitoring Myoelectric Manifestations of Muscle Fatigue. 10.5 Conclusions. Acknowledgment. References. 11 SURFACE MECHANOMYOGRAM (C. Orizio). 11.1 The Mechanomyogram (MMG): General Aspects during Stimulated and Voluntary Contraction. 11.2 Detection Techniques and Sensors Comparison. 11.3 Comparison between Different Detectors. 11.4 Simulation. 11.5 MMG Versus Force: Joint and Adjunct Information Content. 11.6 MMG Versus EMG: Joint and Adjunct Information Content. 11.7 Area of Application. References. 12 SURFACE EMG APPLICATIONS IN NEUROLOGY (M. J. Zwarts, D. F. Stegeman, J. G. van Dijk). 12.1 Introduction. 12.2 Central Nervous System Disorders and SEMG. 12.3 Compound Muscle Action Potential and Motor Nerve Conduction. 12.4 CMAP Generation. 12.5 Clinical Applications. 12.6 Pathological Fatigue. 12.7 New Avenues: High--Density Multichannel Recording. 12.8 Conclusion. References. 13 APPLICATIONS IN ERGONOMICS (G. M. Hagg, B. Melin, R. Kadefors). 13.1 Historic Perspective. 13.2 Basic Workload Concepts in Ergonomics. 13.3 Basic Surface EMG Signal Processing. 13.4 Load Estimation and SEMG Normalization and Calibration. 13.5 Amplitude Data Reduction over Time. 13.6 Electromyographic Signal Alterations Indicating Muscle Fatigue in Ergonomics. 13.7 SEMG Biofeedback in Ergonomics. 13.8 Surface EMG and Musculoskeletal Disorders. 13.9 Psychological Effects on EMG. References. 14 APPLICATIONS IN EXERCISE PHYSIOLOGY (F. Felici). 14.1 Introduction. 14.2 A Few "Tips and Tricks". 14.3 Time and Frequency Domain Analysis of sEMG: What Are We Looking For? 14.4 Application of sEMG to the Study of Exercise. 14.5 Strength and Power Training. 14.6 Muscle Damage Studied by Means of sEMG. References. 15 APPLICATIONS IN MOVEMENT AND GAIT ANALYSIS (C. Frigo, R. Shiavi). 15.1 Relevance of Electromyography in Kinesiology. 15.2 Typical Acquisition Settings. 15.3 Study of Motor Control Strategies. 15.4 Investigation on the Mechanical Effect of Muscle Contraction. 15.5 Gait Analysis. 15.6 Identification of Pathophysiologic Factors. 15.7 Workload Assessment in Occupational Biomechanics. 15.8 Biofeedback. 15.9 The Linear Envelope. 15.10 Information Enhancement through Multifactorial Analysis. References. 16 APPLICATIONS IN REHABILITATION MEDICINE AND RELATED FIELDS (A. Rainoldi, R. Casale, P. Hodges, G. Jull). 16.1 Introduction. 16.2 Electromyography as a Tool in Back and Neck Pain. 16.3 EMG of the Pelvic Floor: A New Challenge in Neurological Rehabilitation. 16.4 Age--Related Effects on EMG Assessment of Muscle Physiology. 16.5 Surface EMG and Hypobaric Hipoxia. 16.6 Microgravity Effects on Neuromuscular System. References. 17 BIOFEEDBACK APPLICATIONS (J. R. Cram). 17.1 Introduction. 17.2 Biofeedback Application to Impairment Syndromes. 17.3 SEMG Biofeedback Techniques. 17.4 Summary. References. 18 CONTROL OF POWERED UPPER LIMB PROSTHESES (P. A. Parker, K. B. Englehart, B. S. Hudgins). 18.1 Introduction. 18.2 Myoelectric Signal as a Control Input. 18.3 Conventional Myoelectric Control. 18.4 Emerging MEC Strategies. 18.5 Summary. References. Index.
1,078 citations
01 Nov 2008
TL;DR: Content-based image retrieval (CBIR), emerged as a promising mean for retrieving images and browsing large images databases and is the process of retrieving images from a collection based on automatically extracted features.
Abstract: "A picture is worth one thousand words". This proverb comes from Confucius a Chinese philosopher before about 2500 years ago. Now, the essence of these words is universally understood. A picture can be magical in its ability to quickly communicate a complex story or a set of ideas that can be recalled by the viewer later in time. Visual information plays an important role in our society, it will play an increasingly pervasive role in our lives, and there will be a growing need to have these sources processed further. The pictures or images are used in many application areas like architectural and engineering design, fashion, journalism, advertising, entertainment, etc. Thus it provides the necessary opportunity for us to use the abundance of images. However, the knowledge will be useless if one can't _nd it. In the face of the substantive and increasing apace images, how to search and to retrieve the images that we interested with facility is a fatal problem: it brings a necessity for image retrieval systems. As we know, visual features of the images provide a description of their content. Content-based image retrieval (CBIR), emerged as a promising mean for retrieving images and browsing large images databases. CBIR has been a topic of intensive research in recent years. It is the process of retrieving images from a collection based on automatically extracted features.
727 citations
"A Method to Differentiate Fatiguing..." refers background in this paper
...The most common shape-based features include axis of least inertia, center of gravity, eccentricity, bending energy, circularity ratio, rectangularity, elliptic variance and convexity [7]....
[...]
TL;DR: The classification (Artificial Neural Network) based results have been presented for detecting different pre-defined arm motions in order to discriminate SEMG signals and indicates that a neural network classifier performs best with an average classification rate of 92.50%.
Abstract: This paper presents the detailed evaluation and classification of Surface Electromyogram (SEMG) signals at different upper arm muscles for different operations. After acquiring the data from selected locations, interpretation of signals was done for the estimation of parameters using simulated algorithm. First, different types of arm operations were analysed; then statistical techniques were implemented for investigating muscle force relationships in terms of amplitude estimation. The classification (Artificial Neural Network) based results have been presented for detecting different pre-defined arm motions in order to discriminate SEMG signals. The outcome of research indicates that a neural network classifier performs best with an average classification rate of 92.50%. Finally, the result also inferred the operations which were observed to be easy for arm recognition and the study is a step forward to develop powerful, flexible and efficient prosthetic designs.
300 citations
Posted Content•
TL;DR: The results demonstrate that MMNF can be used for new robust feature extraction and shows the better recognition result in noisy environment than other success feature candidates.
Abstract: Varieties of noises are major problem in recognition of Electromyography (EMG) signal. Hence, methods to remove noise become most significant in EMG signal analysis. White Gaussian noise (WGN) is used to represent interference in this paper. Generally, WGN is difficult to be removed using typical filtering and solutions to remove WGN are limited. In addition, noise removal is an important step before performing feature extraction, which is used in EMG-based recognition. This research is aimed to present a novel feature that tolerate with WGN. As a result, noise removal algorithm is not needed. Two novel mean and median frequencies (MMNF and MMDF) are presented for robust feature extraction. Sixteen existing features and two novelties are evaluated in a noisy environment. WGN with various signal-to-noise ratios (SNRs), i.e. 20-0 dB, was added to the original EMG signal. The results showed that MMNF performed very well especially in weak EMG signal compared with others. The error of MMNF in weak EMG signal with very high noise, 0 dB SNR, is about 5-10% and closed by MMDF and Histogram, whereas the error of other features is more than 20%. While in strong EMG signal, the error of MMNF is better than those from other features. Moreover, the combination of MMNF, Histrogram of EMG and Willison amplitude is used as feature vector in classification task. The experimental result shows the better recognition result in noisy environment than other success feature candidates. From the above results demonstrate that MMNF can be used for new robust feature extraction. Index Terms—Electromyography (EMG), Feature extraction, Pattern recognition, Robustness, Man-machine interfaces. —————————— a ——————————
278 citations
Additional excerpts
...On the other hand, spectral changes are studied using the frequency domain features such as mean and median frequency for characterizing the progression of fatigue [3]....
[...]
TL;DR: An analysis technique for biological shape based on the concept of bending energy provides several new results concerning image processing including a sampling theorem for simply connected closed contours and a fast algorithm for calculation of the bending energy.
Abstract: An analysis technique for biological shape based on the concept of bending energy has been developed. The technique permits the calculation of the amount of energy (work) that would have to be expended to form typical biological shapes out of a linear, thin-shelled medium. In addition the development of this analysis procedure provides several new results concerning image processing including a sampling theorem for simply connected closed contours and a fast algorithm for calculation of the bending energy.
244 citations
"A Method to Differentiate Fatiguing..." refers background in this paper
...Commonly, the boundary points of a shape are obtained from the polar coordinates of (i) an analytical signal and (ii) Fourier descriptors of the signal [5,6]....
[...]