Traditionally, functional networks in resting-state data were investigated with Fourier and wavelet-related methods to characterize their frequency content. In this study, Empirical Mode Decomposition (EMD), a nonlinear method, is used to determine energy-period profiles of Intrinsic Mode Functions (IMFs) for different resting-state networks. In an application to early Parkinson’s disease (PD) vs. normal controls (NC), energy and period content were computed with EMD and compared with results using short-time Fourier transform (STFT) and maximal overlap discrete wavelet transform (MODWT) methods. Using a support vector machine, EMD achieved highest prediction accuracy in classifying NC and PD subjects among the three methods.
This abstract and the presentation materials are available to members only; a login is required.