Nalan OzkurtOzkurt, Nalan2025-10-062018978-1-5386-4695-3978153864695310.1109/TSP.2018.84414042-s2.0-85053509978https://gcris.yasar.edu.tr/handle/123456789/6352https://doi.org/10.1109/TSP.2018.8441404Tunable Q wavelet transform (TQWT) was recently proposed as an efficient wavelet decomposition method which can match to the oscillatory behaviour of the signal. The selection of Q-factor is an important issue in obtaining a sparser signal representation by TQWT. Morphological component analysis (MCA) is a signal separation method which uses the tuning property of TQWT by selecting a low and a high Q-factor matches the signal components. However the Q-factors are usually chosen experimentally or using the prior information. Thus in this study a signal adaptive Q-factor selection method which can be used with TQWT based analysis was proposed. The performance of the proposed algorithm is illustrated with two examples using MCA signal separation.Englishinfo:eu-repo/semantics/closedAccessMorphological component analysis, tunable-Q wavelet transform, wavelet energy-entropy ratioTunable-Q Wavelet TransformWavelet Energy-Entropy RatioMorphological Component AnalysisConference Object