EFD in Comparison with EWT for Synthetic and EEG Signal Decomposition and Classification of Alzheimer's Disease and Mild Cognitive Impairment.

purposeThis paper investigates the well-known Empirical Wavelet Transform (EWT) and the recently introduced Empirical Fourier Decomposition (EFD) for the early diagnosis of Alzheimer's disease (AD). Both synthetic signals and real EEG data are decomposed and reconstructed, particularly under noisy conditions.

methodsEWT and EFD were applied to decompose non-stationary EEG signals into five sub-bands (Delta, Theta, Alpha, Beta, and Gamma). From each sub-band, eight features were extracted and used to classify subjects into AD and Mild Cognitive Impairment (MCI) groups. Among the five classifiers tested, Random Forest (RF) yielded the best performance for both EWT and EFD. In addition to conventional evaluation metrics, Dynamic Time Warping (DTW) and the Kolmogorov-Smirnov (KS) statistic were used for algorithm assessment.

resultsThe results show that EFD outperforms EWT and achieves competitive performance compared to state-of-the-art approaches.

conclusionEFD is a novel decomposition method that demonstrates robust performance on both synthetic and real EEG signals, supporting its potential use in the early diagnosis of Alzheimer's disease.