ELECTROMYOGRAPHY (EMG) SIGNAL CLASSIFICATION BASED ON DETRENDED FLUCTUATION ANALYSIS

摘要

Electromyography (EMG) signal is a useful signal in various medical and engineeringnapplications. To extract the useful information in the EMG signal, feature extractionnmethod should be performed. The extracted features of the EMG signal are usually calculatednbased on linear or statistical methods, but the EMG signal exhibits the nonlinearnand more complex in the properties. With recent advances in nonlinear analysis we arenproposing the study of the EMG signals from upper-limb movements using DetrendednFluctuation Analysis (DFA) method. This study used EMG signals obtained from eightnupper-limb movements and five muscle positions as representative EMG signals. Thenusefulness of the DFA method has been proposed to discriminate the upper-limb movements.nComplete comparative studies of an optimal parameter of the DFA method werenperformed. From the viewpoints of maximum class separability, robustness, and complexity,nscaling exponent obtained from the DFA method shows the appropriateness tonbe used as a feature in the classification of the EMG signal. From the experimentalnresults, an optimal DFA method is obtained under these conditions: the minimum boxnsize is approximately four, the maximum box size is one-tenth of the signal length, thenbox size increment is based on a power of two, and the quadratic polynomial fits is usednin the fitting procedure. Moreover, the classification performance of the DFA method isnbetter than other existing nonlinear methods, including the Higuchi’s method.