手法を比較

	CEEMDAN	経験的ウェーブレット変換	変分モード分解（VMD）
分野	時系列解析	時系列解析	信号処理
系統	Process / pipeline	Process / pipeline	Machine learning
提唱年	2011	2013	2014
提唱者	María E. Torres	Jérémie Gilles	Konstantin Dragomiretskiy & Dominique Zosso
種類	Non-stationary signal decomposition	Non-stationary signal decomposition	Adaptive variational signal decomposition algorithm
原典	Torres, M. E., Colominas, M. A., Schlotthauer, G., & Flandrin, P. (2011). A complete ensemble empirical mode decomposition with adaptive noise. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4144–4147).	Gilles, J. (2013). Empirical wavelet transform. IEEE Transactions on Signal Processing, 61(16), 3999–4010.	Dragomiretskiy, K., & Zosso, D. (2014). Variational mode decomposition. IEEE Transactions on Signal Processing, 62(3), 531–544.
別名	CEEMDAN, Ensemble EMD with noise	EWT, Empirical wavelets	VMD, Adaptive Signal Decomposition, Variational Signal Decomposition, Varyasyonel Mod Ayrıştırma
関連	3	3	2
概要	Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is an improved variant of empirical mode decomposition (EMD) that addresses mode-mixing artifacts through ensemble averaging with adaptive noise. Introduced by Torres and colleagues (2011), CEEMDAN decomposes signals into intrinsic mode functions (IMFs) representing oscillations at different scales. The method adds controlled noise to multiple realizations and averages the results, producing more stable, physically meaningful components than standard EMD.	The empirical wavelet transform (EWT) is a data-driven wavelet decomposition method that automatically defines wavelet bases adapted to the frequency content of the signal. Introduced by Jérémie Gilles (2013), it overcomes a key limitation of classical wavelets—which use fixed, predefined bases—by constructing custom wavelets from the signal's own spectrum. This adaptive approach is particularly effective for analyzing non-stationary signals with complex, multi-component structures.	Variational Mode Decomposition (VMD) is a fully adaptive, non-recursive signal decomposition method introduced by Konstantin Dragomiretskiy and Dominique Zosso in 2014. It decomposes a real-valued input signal into a discrete number of sub-signals, called intrinsic mode functions (IMFs), each with a specific sparsity in the frequency domain. Unlike Empirical Mode Decomposition, VMD frames decomposition as a variational optimization problem solved via the Alternating Direction Method of Multipliers (ADMM), yielding robust and physically meaningful components.