Hybrid BF–PSO and fuzzy support vector machine for diagnosis of fatigue status using EMG signal features

Fatigue Detection during Sit-To-Stand Test Based on Surface Electromyography and Acceleration: A Case Study

The latest studies of the 30-second sit-to-stand (30-STS) test aim to describe it by employing kinematic variables, muscular activity, or fatigue through electromyography (EMG) instead of a number of repetitions. The aim of the present study was to develop a detection system based on acceleration measured using a smartphone to analyze fatigue during the 30-STS test with surface electromyography as the criterion. This case study was carried out on one woman, who performed eight trials. EMG data from the lower limbs and trunk muscles, as well as trunk acceleration were recorded. Both signals from eight trials were preprocessed, being averaged and temporarily aligned. The EMG signal was processed, calculating the spectral centroid (SC) by Discrete Fourier Transform, while the acceleration signal was processed by Discrete Wavelet Transform to calculate its energy percentage. Regarding EMG, fatigue in the vastus medialis of the quadriceps appeared as a decrease in SC, with a descending slope of 12% at second 12, indicating fatigue. However, acceleration analysis showed an increase in the percentage of relative energy, acting like fatigue firing at second 19. This assessed fatigue according to two variables of a different nature. The results will help clinicians to obtain information about fatigue using an accessible and inexpensive device, i.e., as a smartphone.

An Intelligent Parkinson's Disease Diagnostic System Based on a Chaotic Bacterial Foraging Optimization Enhanced Fuzzy KNN Approach

Parkinson's disease (PD) is a common neurodegenerative disease, which has attracted more and more attention. Many artificial intelligence methods have been used for the diagnosis of PD. In this study, an enhanced fuzzy k-nearest neighbor (FKNN) method for the early detection of PD based upon vocal measurements was developed. The proposed method, an evolutionary instance-based learning approach termed CBFO-FKNN, was developed by coupling the chaotic bacterial foraging optimization with Gauss mutation (CBFO) approach with FKNN. The integration of the CBFO technique efficiently resolved the parameter tuning issues of the FKNN. The effectiveness of the proposed CBFO-FKNN was rigorously compared to those of the PD datasets in terms of classification accuracy, sensitivity, specificity, and AUC (area under the receiver operating characteristic curve). The simulation results indicated the proposed approach outperformed the other five FKNN models based on BFO, particle swarm optimization, Genetic algorithms, fruit fly optimization, and firefly algorithm, as well as three advanced machine learning methods including support vector machine (SVM), SVM with local learning-based feature selection, and kernel extreme learning machine in a 10-fold cross-validation scheme. The method presented in this paper has a very good prospect, which will bring great convenience to the clinicians to make a better decision in the clinical diagnosis.

Weighted-Cumulated S-EMG Muscle Fatigue Estimator

This paper addresses a new approach to objectively evaluate muscle fatigue in isometric and dynamic physical exertions using surface electromyography (S-EMG). The emphasis of this proposal is to preserve the spectral signature of the muscle fatigue phenomenon while reducing the spatial effects of electrode localization, and decreasing the disparity of results obtained by the same experimental protocol at different times. A cumulated and normalized modeling was sought to make evident the nonstationary characteristics of muscle fatigue that is gradually identified with its inertia and intensity. A metric involving the proposal of temporal, frequency, and time-frequency weighted-cumulated indicators is presented. Results based on real signals are shown for isometric and dynamic experimental protocols. Performance comparison of the various proposed weighted-cumulated indexes is shown and discussed. The presented approach for the objective cumulative evaluation of muscle fatigue with S-EMG signals has shown to be promising.