On the Use of Fuzzy and Permutation Entropy in Hand Gesture Characterization from EMG Signals: Parameters Selection and Comparison

Abstract

The surface electromyography signal (sEMG) is widely used for gesture characterization; its reliability is strongly connected to the features extracted from sEMG recordings. This study aimed to investigate the use of two complexity measures, i.e., fuzzy entropy (FEn) and permutation entropy (PEn) for hand gesture characterization. Fourteen upper limb movements, sorted into three sets, were collected on ten subjects and the performances of FEn and PEn for gesture descriptions were analyzed for different computational parameters. FEn and PEn were able to properly cluster the expected numbers of gestures, but computational parameters were crucial for ensuring clusters’ separability and proper gesture characterization. FEn and PEn were also compared with other eighteen classical time and frequency domain features through the minimum redundancy maximum relevance algorithm and showed the best predictive importance scores in two gesture sets; they also had scores within the subset of the best five features in the remaining one. Further, the classification accuracies of four different feature sets presented remarkable increases when FEn and PEn are included as additional features. Outcomes support the use of FEn and PEn for hand gesture description when computational parameters are properly selected, and they could be useful in supporting the development of robotic arms and prostheses myoelectric control.

Exploration and Application of a Muscle Fatigue Assessment Model Based on NMF for Multi-Muscle Synergistic Movements

“…The PE of EMG signals serves as a signal analysis metric. By quantifying the probability distribution of different permutation patterns in EMG signals, it effectively reflects the irregularity of muscle activity, providing an objective method to assess muscle fatigue status [39,40]. The calculation method for PE can be expressed as follows:…”

Research on Lower Limb Step Speed Recognition Method Based on Electromyography

“…The time window plays an important role in the processing of the EMG signal pattern. Many studies [ 24 , 25 , 26 ] have discussed this problem in depth. Based on the above research, in gait recognition, we need to detect the initial moment of gait and, on this basis, conduct window division.…”

“…As shown in Figure 3 b, similar time domain and frequency domain characteristics are displayed between the 100th to 200th and the 200th to 300th sampling points, etc. Combined with the selection of the length of sliding window in [ 24 , 25 , 26 ], we choose 200 ms as the length of time window and the overlapping ratio is set at 50%, which can not only ensure the efficiency of data use but also does not cause data loss. In the process of data acquisition, the current sampling time is taken as the time node and the data of the first 1 s are intercepted as the sliding time window.…”

Gesture Recognition by Ensemble Extreme Learning Machine Based on Surface Electromyography Signals

“…In the feature-based method, features are first extracted manually by experience and then fed into the classification models, which are mainly constructed based on the machine learning algorithms. The diverse features can be roughly divided into four categories: time domain features, frequency domain features, time–frequency domain features, and non-linear features such as fuzzy entropy (FEn) and permutation entropy (PEn) (Mengarelli et al, 2020 ). Although the suitability of each feature in accurately classifying sEMG signals has been extensively investigated (Du et al, 2010 ; Phinyomark et al, 2013 ), there still exists information redundancy among the features inevitably.…”