RCMFRDE: Refined Composite Multiscale Fluctuation-Based Reverse Dispersion Entropy for Feature Extraction of Ship-Radiated Noise

Yuxing Li,Bo Geng,Shangbin Jiao,Xinru Jiang,Mohammad Yaghoub Abdollahzadeh Jamalabadi

doi:10.1155/2021/7150921

Abstract

Dispersion entropy (DE), as a newly proposed entropy, has achieved remarkable results in its application. In this paper, on the basis of DE, combined with coarse-grained processing, we introduce the fluctuation and distance information of signal and propose the refined composite multiscale fluctuation-based reverse dispersion entropy (RCMFRDE). As an emerging complexity analysis mode, RCMFRDE has been used for the first time for the feature extraction of ship-radiated noise signals to mitigate the loss caused by the misclassification of ships on the ocean. Meanwhile, a classification and recognition method combined with K-nearest neighbor (KNN) came into being, namely, RCMFRDE-KNN. The experimental results indicated that RCMFRDE has the highest recognition rate in the single feature case and up to 100% in the double feature case, far better than multiscale DE (MDE), multiscale fluctuation-based DE (MFDE), multiscale permutation entropy (MPE), and multiscale reverse dispersion entropy (MRDE), and all the experimental results show that the RCMFRDE proposed in this paper improves the separability of the commonly used entropy in the hydroacoustic domain.

Highlights

In a nutshell, the physical meaning of LZC is that it reflects the rate at which new patterns appear in a time series as the length increases. e higher the LZC value of a sequence, the more new changes occur in the sequence and the more disordered and uncertain the sequence is, while the lower the LZC value, the more regular the sequence is [22, 23]
In 2002, Bandt and Pompe first proposed Permutation Entropy (PE) [27], which was quickly applied to characterize the randomness of information in various fields, and many scholars improved it on this basis, such as weighted PE (WPE) [28] and multiscale PE (MPE) [29]; compared with PE, these improved PE-based measures have more substantial stability
Under different entropies and different scale factors differ to different degrees; for refined composite multiscale fluctuation-based reverse dispersion entropy (RCMFRDE), three samples of ship IV are misidentified when the scale is 1; with the increase of scale, the number of misidentified samples of ship I, ship II, and ship III gradually increases, leading to a decrease in the average recognition rate of RCMFRDE; for multiscale DE (MDE) and multiscale fluctuation-based DE (MFDE), the three samples of ship IV are incorrectly recognized when SF is 1, while ship IV can be correctly recognized under other scale factors

Summary

RCMFRDE

Step 1: for a known time series A(j) 􏽮aj(j 1, 2, . . . , N)}, x(ks)(k 1, 2, . . . , s) is the kth coarse-grained time series of A(j) as follows: x(ks). S) is the kth coarse-grained time series of A(j) as follows: x(ks). Step 4: phase space reconstruction of z(ks) according to embedding dimension m and time delay τ, and embedding vectors zck,n, zck,n+τ, . Step 5: each embedding vector is mapped to fluctuation-based dispersion patterns Tmk ,τ. The total number of vectors is V h − (m − 1)τ, with a maximum of (2c − 1)(m− 1) types of possible fluctuationbased dispersion patterns. C, τ, Tmk ,τ can be expressed as. Step 6: each Tmk ,τ corresponds to a fluctuation-based ttducki,sanp+ti(eomrns− i-1ob)τna sepdvamtt−de2ri)sn;petπhrvse0in,ov1,n,..t.h,vpmea− t2p(tertrockn,bn a Pbi(kvlsi0)t(,ytkcko,n f+τ1e,a 2c,hv.1.,fl..u,.cs.-), can be estimated by. Where Num􏽮i|i ≤ h − (m − 1)τ, πv0,v1,...,vm− 2􏽯 is the number of fluctuation-based dispersion pattern of πv0,v1,...,vm− 2 assigned to Zmk ,τ.

Feature Extraction Method

Single Feature Extraction of the Four Types of S-NS

Double Feature Extraction of the Four Types of S-NS

Findings

Conclusions