Ramakrishnan Swaminathan

In this work, an attempt has been made to utilise the time-frequency spectrum obtained using generalised Warblet transform (GWT) for fatigue analysis. Signals are acquired from the biceps brachii muscles of 20 healthy volunteers during isometric contractions. The first and last 500 ms lengths of a signal are assumed as non-fatigue and fatigue zones respectively. Further, the signals from these zones are subjected to GWT for the computation of time-frequency spectrum. Features such as instantaneous mean frequency (IMNF), instantaneous median frequency (IMDF), instantaneous spectral entropy (ISPEn), and instantaneous spectral skewness (ISSkw) are estimated. The results show that the IMNF, IMDF and ISPEn increased by 24%, 34% and 36% respectively in non-fatigue condition. In contrast, 22% higher ISSkw is observed for fatigue condition. The statistical analysis indicates that the features are significant with p < 0.001. It appears that the current method is useful in analysing muscle fatigue disorders using sEMG signals.

Muscle fatigue is a neuromuscular condition which causes a decline in muscle performance. Surface electromyography (sEMG) signals are widely used to evaluate muscle fatigue and these signals are highly complex in nature. To address this, advanced signal processing techniques are necessary. In this work, an attempt has been made to analyze the complexity of sEMG signals associated with fatigue conditions using Multiscale Approximate Entropy (MSApEn) technique. Signals are recorded from biceps brachii muscles of fifty healthy subjects while performing curl exercise and it is divided into six equal segments to avoid variability in endurance time. The first and last segments are considered as nonfatigue and fatigue conditions respectively. The signals are preprocessed and MSApEn is evaluated. Further, four features namely median (MED), variance (VAR), high scale sum (HSS) and low scale sum (LSS) are extracted from each segment. The results indicate a distinct variation in the MSApEn values. It is found that the signals are complex in both fatigue and nonfatigue conditions. In addition, features namely the MED, HSS and LSS are found to be low in fatigue case. The t-test performed on these features shows high statistical significance (p-value<0.005). It appears that this method can be used to analyze the complexity of sEMG signals in varied clinical conditions.

Muscle fatigue analysis finds significant applications in the areas of biomechanics, sports medicine and clinical studies. Surface electromyography (sEMG) signals have wide application because of its non invasiveness. By nature, signals recorded using surface electrodes from muscles are highly nonstationary and random. The objective of this work is to analyze muscle related fatigue using sEMG signals and polynomial chirplet transform (PCT). sEMG signals are acquired from biceps brachii muscles of twenty volunteers (Mean (sd): age, 23.5 (4.3) years) in isometric contractions. The initial 500 ms is considered as nonfatigue and final 500 ms of the signals are considered as fatigue zone. Then signals are subjected to polynomial chirplet transform to estimate the time-frequency spectrum. Four features, instantaneous mean frequency (IsMNF), instantaneous median frequency (IsMDF), instantaneous spectral entropy (ISpEn) and instantaneous spectral skewness (ISSkw) are extracted for further analysis. Results show that the PCT is able to characterize the nonstationary and multi component nature of sEMG signals. The IsMNF, IsMDF, ISpEn are found to be high in nonfatigue conditions. Further, all the features are very distinct in muscle nonfatigue and fatigue conditions (p<0.001). This technique can be used in analyzing different neuromuscular disorders.

In this study, the dynamic contractions and the associated fatigue condition in biceps brachii muscle are analysed using Synchrosqueezed Wavelet Transform (SST) and singular value features of surface Electromyography (sEMG) signals. For this, the recorded signals are decomposed into time-frequency matrix using SST. Two analytic functions namely Morlet and Bump wavelets are utilised for the analysis. Singular Value Decomposition method is applied to this time-frequency matrix to derive the features such as Maximum Singular Value (MSV), Singular Value Entropy (SVEn) and Singular Value Energy (SVEr). The results show that both these wavelets are able to characterise nonstationary variations in sEMG signals during dynamic fatiguing contractions. Increase in values of MSV and SVEr with the progression of fatigue denotes the presence of nonstationarity in the sEMG signals. The lower values of SVEn with the progression of fatigue indicate the randomness in the signal. Thus, it appears that the proposed approach could be used to characterise dynamic muscle contractions under varied neuromuscular conditions.

In this, study, an attempt is made to differentiate muscle nonfatigue and fatigue condition using signal complexity metrics derived from phase space network features. A total of 55 healthy adult volunteers performed dynamic contraction of the biceps brachii muscle. The first and last curl are segmented and are considered as nonfatigue and fatigue condition respectively. A weighted phase space network is constructed and reduced to a binary network based on various radii. The mean and median degree centrality features are extracted from these networks and are used for classification. The results of the classification indicate that these features are capable of differentiating nonfatigue and fatigue condition with 91% accuracy. This method of analysis can be extended to applications such as diagnosis of neuromuscular disorder where fatigue is a symptom.

Prolonged and repeated fatigue conditions can cause muscle damage and adversely impact coordination in dynamic contractions. Hence it is important to determine the onset of muscle fatigue (OMF) in clinical rehabilitation and sports medicine. The aim of this study is to propose a method for analyzing surface electromyography (sEMG) signals and identify OMF using multifractal detrending moving average algorithm (MFDMA). Signals are recorded from biceps brachii muscles of twenty two healthy volunteers while performing standard curl exercise. The first instance of muscle discomfort during curl exercise is considered as experimental OMF. Signals are pre-processed and divided into 1-second epoch for MFDMA analysis. Degree of multifractality (DOM) feature is calculated from multifractal spectrum. Further, the variance of DOM is computed and OMF is calculated from instances of high peaks. The analysis is carried out by dividing the entire duration into six equal zones for time axis normalization. High peaks are observed in zones where subjects reported muscle discomfort. First muscle discomfort occurred in third and forth zones for majority of subjects. The calculated and experimental muscle discomfort zone closely matched in 72% of subjects indicating that multifractal technique may be a good method for detecting onset of fatigue. The experimental data may have an element of subjectivity in identifying muscle discomfort. This work can also be useful to analyze progressive changes in muscle dynamics in neuromuscular condition and co-contraction activity.

Muscle fatigue is commonly experienced in both normal and subjects with neuromuscular disorders. Surface electromyography (sEMG) signals are useful technique for analyzing muscle fatigue. sEMG signals are highly nonstationary and exhibit complex nonlinear characteristic in dynamic contractions. In this work, an attempt is made to classify sEMG signals recorded from biceps brachii muscles in nonfatigue and fatigue using multifractal features. The signals are recorded from 26 healthy normal adult subjects while performing standard experimental protocol involving dynamic contraction. The preprocessed signals are divided into six segments. The first and last segments are considered as nonfatigue and fatigue conditions respectively. The signals are then subjected to multifractal detrended moving average algorithm and eight multifractal features are extracted from both conditions. Further, information gain (IG) based ranking is used for reducing the number of features. Three different classification algorithms are employed namely, k-Nearest Neighbor algorithm (kNN), Naive Bayes (NB) and logistic regression (LR) for classification. The results show that signals exhibit multifractal characteristics and the multifractal features such as, generalized Hurst exponent, degree of multifractality and scaling exponent slope are significantly different in fatigue condition. The Hurst exponent for small fluctuation and degree of multifractality are found to be very highly significant feature. The LR and kNN classifier performance gave an accuracy of 84% and 82% respectively. This method of using multifractal features appears to be useful in classifying sEMG signals in dynamic contraction. This study can also be extended to classify fatigue condition in various neuromuscular disorders.

In this, study, we have investigated to identify the muscle fatigue using spatial maps of High-Density Electromyography (HDEMG). The experiment involves subjects performing plantar flexion at 40% maximum voluntary contraction until fatigue. During the experiment, HDEMG signal was recorded from the tibialis anterior muscle. The monopolar and bipolar spatial intensity maps were extracted from the HDEMG signal. The random forest classifier with different tree configurations was tested to distinguish nonfatigue and fatigue condition. The results indicate that selected electrodes from the differential intensity map results in an accuracy of 83.3% with the number of trees set at 17. This method of spatial analysis of HDEMG signals may be extended to assess fatigue in real life scenarios. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this work, an attempt has been made to differentiate surface electromyography signals under fatigue and non-fatigue conditions. Signals are recorded from the biceps brachii muscles of 50 healthy volunteers. A well-established experimental protocol is followed for this purpose. Signals are subjected to further processing and features namely amplitude of first burst, myopulse percentage rate, Willison amplitude, power spectrum ratio and variance of central frequency are extracted. Three types of logistic regression classifiers, linear logistic, polykemel logistic regression and multinomial regression with ridge estimator are used for automated analysis. Classifier parameters are tuned to enhance the accuracy and performance indices of algorithms, and are compared. The results show distinct values for extracted features in fatigue conditions which are statistically significant (0.0027 ≤ P ≤ 0.03). All classifiers are found to be effective in demarcating the signals. The linear logistic regression algorithm provides 79% accuracy with 40 iterations. However, in the case of multinomial regression with ridge estimator, only 7 iterations are required to achieve 80% accuracy. The polykernel logistic regression algorithm (0.06 ≤ λ ≤ 0.1) also provides 80% accuracy but with a marginal increment (1% to 4%) for precision, recall and specificity compared to other two classifiers. Copyright 2014, ISA All Rights Reserved.

Purpose: In this work, an attempt has been made to analyze surface electromyography (sEMG) signals in dynamic contractions using bispectrum features.