Electromyography (Emg) Signal Classification Based on Detrended Fluctuation Analysis

Abstract

Electromyography (EMG) signal is a useful signal in various medical and engineering applications. To extract the useful information in the EMG signal, feature extraction method should be performed. The extracted features of the EMG signal are usually calculated based on linear or statistical methods, but the EMG signal exhibits the nonlinear and more complex in the properties. With recent advances in nonlinear analysis we are proposing the study of the EMG signals from upper-limb movements using Detrended Fluctuation Analysis (DFA) method. This study used EMG signals obtained from eight upper-limb movements and five muscle positions as representative EMG signals. The usefulness of the DFA method has been proposed to discriminate the upper-limb movements. Complete comparative studies of an optimal parameter of the DFA method were performed. From the viewpoints of maximum class separability, robustness, and complexity, scaling exponent obtained from the DFA method shows the appropriateness to be used as a feature in the classification of the EMG signal. From the experimental results, an optimal DFA method is obtained under these conditions: the minimum box size is approximately four, the maximum box size is one-tenth of the signal length, the box size increment is based on a power of two, and the quadratic polynomial fits is used in the fitting procedure. Moreover, the classification performance of the DFA method is better than other existing nonlinear methods, including the Higuchi's method.

Emg Amplitude Estimators Based on Probability Distribution for Muscle–computer Interface

“…Although many advanced time-scale and non-linear algorithms have been developed in the past decade to analyze and identify surface electromyography (EMG) signal [1,2], features based on the amplitude of surface EMG signals have been still widely used as a control input in muscle-computer interfaces (MCIs) [3][4][5][6][7]. One of the major advantage reasons is about the lower complexity and computational cost of the EMG amplitude estimators compared to the advanced time-scale and non-linear algorithms.…”

Identification of low level sEMG signals for individual finger prosthesis

“…Phinyiomark uses DFA in several works to classify low level sEMG signals [35] [48] [49] [50]. In [35] 8 gestures were classified with the wrist, hand and forearm using weak upper-limb sEMG signals for five channels, for 20 healthy subjects.…”

The Relationship between Anthropometric Variables and Features of Electromyography Signal for Human–Computer Interface

“…The experimental results showed that, DFA has better cluster separability than HG (Phinyomark et al, 2011d), as well as classification performance (Phinyomark et al, 2012d). On the other hand, features based on a magnitude detector provide better performance in the classification of high-level EMG signal patterns than fractal features.…”

“…Based on our previous work (Phinyomark, Phukpattaranont, Limsakul, & Phothisonothai, 2011d), the minimum box size n min is set at four, the maximum box size n max is set at one-tenth of the signal length, and the box size increment is based on a power of two. A least-square fit, which is applied to the profiles y k , is the quadratic polynomial fit.…”

“…EMG data were measured from 4 forearm muscles and an upper arm muscle: extensor carpi radialis longus (ECRL), extensor carpi ulnaris (ECU), extensor digitorum communis (EDC), flexor carpi radialis (FCR), and biceps brachii (BB). More details about data acquisition and experiments can be found in Phinyomark et al (2011d).…”