Login / Signup

Optimized Ship-Radiated Noise Feature Extraction Approaches Based on CEEMDAN and Slope Entropy.

Yuxing LiBingzhao TangShangbin Jiao
Published in: Entropy (Basel, Switzerland) (2022)
Slope entropy (Slopen) has been demonstrated to be an excellent approach to extracting ship-radiated noise signals (S-NSs) features by analyzing the complexity of the signals; however, its recognition ability is limited because it extracts the features of undecomposed S-NSs. To solve this problem, in this study, we combined complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to explore the differences of Slopen between the intrinsic mode components (IMFs) of the S-NSs and proposed a single-IMF optimized feature extraction approach. Aiming to further enhance its performance, the optimized combination of dual-IMFs was selected, and a dual-IMF optimized feature extraction approach was also proposed. We conducted three experiments to demonstrate the effectiveness of CEEMDAN, Slopen, and the proposed approaches. The experimental and comparative results revealed both of the proposed single- and dual-IMF optimized feature extraction approaches based on Slopen and CEEMDAN to be more effective than the original ship signal-based and IMF-based feature extraction approaches.
Keyphrases
  • machine learning
  • deep learning
  • air pollution
  • neural network
  • randomized controlled trial
  • systematic review
  • convolutional neural network