Extraction of time varying information from noisy signals: An approach based on the empirical mode decomposition

摘要: A windowed average technique is designed as an efficient assistance of empirical mode decomposition, aimed especially at extracting components with temporally variant frequencies from heavily noisy signals. Unlike those relying on detection such points local extrema that are highly sensitive to noise interference, the present method evaluates a mean curve reflects slow variation signal in longer time scales by locally integral over sliding window. It adapts component broad frequency range making window width variable response variation. The enhanced performance and robustness new algorithm respect resistance demonstrated comparison other EMD-based methods, examples processing both speech underwater acoustic signals given show success varying information.