Surrogate analysis of fractal dimensions from SEMG sensor array as a predictor of chronic low back pain

In this paper, a method based on nonlinear analysis of sEMG sensor array signals (2 arrays of 5×13 sensors) to detect chronic low back pain is presented. The use of an FFT based surrogate analysis method isolates the nonlinear structure of the signals from the effect of the power spectrum. The fractal dimension is used for the nonlinear characteristic. From the sensor arrays, a certain number of channels which exhibits the most nonlinearity for a subject are kept as input of a small neural network. A leave-one-out type cross-validation method shows a success rate of 80%.