The measurement and analysis of the electrical activity of muscle provide information that aids in the control of assistive devices. The investigation of these signals under varied physiological conditions, such as fatigue, enables reliable control. Muscle fatigue is a muscular condition associated with loss of muscle function. The early detection of muscle fatigue using surface Electromyography (sEMG)-based electrical measurements is challenging due to the nonlinear variations of the signal. In this work, an attempt has been made to understand the effect of dynamic nonlinear variations in the characteristics of the signal to develop a reliable fatigue index. The methodology involves the acquisition of myoelectric signals from the biceps brachii muscle of 52 healthy participants during dynamic contractions. The acquired signals are preprocessed and are analyzed with symbolic transition networks. Features such as symbolic entropy, network entropy, uniformity, and, minimum and maximum effective degrees (EDs) are extracted for further analysis. Appropriate decision boundaries are established for each feature using receiver operator characteristics (ROCs) and machine learning algorithms. The results indicate a decrease in signal complexity with fatigue. All the extracted features show a statistically significant difference (p < 0.05) between both conditions. Symbolic entropy achieves an accuracy of 89%, and the maximum ED yields an accuracy of 90% based on thresholds estimated with ROC. Furthermore, only a marginal improvement is observed with the combination of these features and the Naive Bayes classifier. It appears that the proposed maximum ED could be used as a reliable fatigue index in real-time applications for the improvement of rehabilitation efficacy.

An attempt has been made to analyse the progression of muscle fatigue using mean power ratios (MPRs) derived from B‐distribution time–frequency spectrum of surface electromyography signals. For this purpose, signals are recorded from the biceps brachii muscle of 30 healthy adult volunteers. Fifteen subjects carried out isometric contractions and the rest performed dynamic muscle contractions until task failure. The signals are preprocessed and subjected to B‐distribution‐based time–frequency analysis. Subsequently, the MPR of medium‐to‐low‐frequency band (M/LFB) and high‐to‐LFB (H/LFB) are extracted from the time–frequency spectrum. Furthermore, the slope is calculated using the linear regression technique. Results show that MPR of M/LFB and H/LFB exhibit a decreasing trend during the progression of muscle fatigue condition. The strength of the peaks present in MPR of M/LFB progressively reduces and approaches zero at task failure for all subjects. Additionally, higher slope values are found in MPR of M/LFB in comparison with H/LFB. It appears that MPR of M/LFB is more sensitive for muscle fatigue analysis and may be used as an index for real‐time monitoring in work place.

Accurate detection of seizure types is one of the important research in the field of epilepsy for effective treatment and management. The identification of potential biomarkers is difficult and challenging as the nonlinear and nonstationary characteristics of the electroencephalogram (EEG) vary within a seizure type and among the seizure types. In this work, a novel variational mode decomposition (VMD) based feature fusion approach is proposed to detect the evolution of seizures into electrographic seizures, complex partial seizures, and focal to bilateral tonic-clonic seizures. The scalp EEGs of these seizures are decomposed using VMD. The features, namely, zero crossing, Shannon entropy, approximate entropy, and root squared zeroth moment (RSZM) are extracted from bandlimited oscillatory modes. These features are employed to design a three-class classification model using random forest. In order to enhance the performance further, a fusion of RSZM measures is adapted. The proposed framework is experimented with ictal EEGs of Temple University and Hospital database. The results indicate that the six-level VMD performs better in terms of differentiating seizure types. Among the features, the RSZM is found to effectively recognize the seizure types from the first few seconds of ictal EEG. Further the fusion of RSZM results with a maximum accuracy of 96.91% for ten-fold cross-validation and 85.2% for patient-wise cross-validation. In addition, the performance of our approach is also found to be promising for the differentiation of ictal and normal EEGs when we tested on wider datasets. Therefore, the proposed framework has great potential in epilepsy diagnosis.